polymech/mono
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

maintainence love:)

Browse Source
This commit is contained in:
lovebird 2025-06-28 10:37:04 +02:00
parent c5eadead31
commit 95b75a1903
21 changed files with 3485 additions and 2517 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
packages/kbot/dist-in/data/openai_models.json
View File

@ -1,5 +1,5 @@
{
"timestamp": 1749149893739,
"timestamp": 1751099810190,
"models": [
{
"id": "gpt-4-0613",
@ -20,21 +20,9 @@
"owned_by": "openai"
},
{
"id": "gpt-4o-audio-preview-2025-06-03",
"id": "o4-mini-deep-research-2025-06-26",
"object": "model",
"created": 1748908498,
"owned_by": "system"
},
{
"id": "gpt-4.1-nano",
"object": "model",
"created": 1744321707,
"owned_by": "system"
},
{
"id": "gpt-image-1",
"object": "model",
"created": 1745517030,
"created": 1750866121,
"owned_by": "system"
},
{
@ -49,6 +37,18 @@
"created": 1748907838,
"owned_by": "system"
},
{
"id": "gpt-4o-audio-preview-2025-06-03",
"object": "model",
"created": 1748908498,
"owned_by": "system"
},
{
"id": "o4-mini-deep-research",
"object": "model",
"created": 1749685485,
"owned_by": "system"
},
{
"id": "davinci-002",
"object": "model",
@ -427,6 +427,18 @@
"created": 1744321025,
"owned_by": "system"
},
{
"id": "gpt-4.1-nano",
"object": "model",
"created": 1744321707,
"owned_by": "system"
},
{
"id": "gpt-image-1",
"object": "model",
"created": 1745517030,
"owned_by": "system"
},
{
"id": "gpt-3.5-turbo-16k",
"object": "model",

4497
packages/kbot/dist-in/data/openrouter_models.json
View File

File diff suppressed because it is too large Load Diff

2
packages/kbot/dist-in/src/models/cache/openai.ts vendored
View File

File diff suppressed because one or more lines are too long

2
packages/kbot/dist-in/src/models/cache/openrouter.ts vendored
View File

File diff suppressed because one or more lines are too long

4
packages/kbot/dist/main_node.js vendored
View File

File diff suppressed because one or more lines are too long

4
packages/kbot/dist/package-lock.json generated vendored
View File

@ -1,12 +1,12 @@
{
"name": "@plastichub/kbot",
"version": "1.1.40",
"version": "1.1.41",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@plastichub/kbot",
"version": "1.1.40",
"version": "1.1.41",
"license": "ISC",
"dependencies": {
"node-emoji": "^2.2.0"

2
packages/kbot/dist/package.json vendored
View File

@ -1,6 +1,6 @@
{
"name": "@plastichub/kbot",
"version": "1.1.40",
"version": "1.1.41",
"main": "main_node.js",
"author": "",
"license": "ISC",

2
packages/kbot/logs/params.json
View File

@ -1,5 +1,5 @@
{
"model": "anthropic/claude-sonnet-4",
"model": "deepseek/deepseek-r1:free",
"messages": [
{
"role": "user",

2
packages/kbot/schema.json
View File

File diff suppressed because one or more lines are too long

2
packages/kbot/schema_ui.json
View File

File diff suppressed because one or more lines are too long

8
packages/kbot/src/models/cache/openai-models.ts vendored
View File

@ -2,11 +2,11 @@ export enum E_OPENAI_MODEL {
MODEL_GPT_4_0613 = "gpt-4-0613",
MODEL_GPT_4 = "gpt-4",
MODEL_GPT_3_5_TURBO = "gpt-3.5-turbo",
MODEL_GPT_4O_AUDIO_PREVIEW_2025_06_03 = "gpt-4o-audio-preview-2025-06-03",
MODEL_GPT_4_1_NANO = "gpt-4.1-nano",
MODEL_GPT_IMAGE_1 = "gpt-image-1",
MODEL_O4_MINI_DEEP_RESEARCH_2025_06_26 = "o4-mini-deep-research-2025-06-26",
MODEL_CODEX_MINI_LATEST = "codex-mini-latest",
MODEL_GPT_4O_REALTIME_PREVIEW_2025_06_03 = "gpt-4o-realtime-preview-2025-06-03",
MODEL_GPT_4O_AUDIO_PREVIEW_2025_06_03 = "gpt-4o-audio-preview-2025-06-03",
MODEL_O4_MINI_DEEP_RESEARCH = "o4-mini-deep-research",
MODEL_DAVINCI_002 = "davinci-002",
MODEL_BABBAGE_002 = "babbage-002",
MODEL_GPT_3_5_TURBO_INSTRUCT = "gpt-3.5-turbo-instruct",
@ -70,6 +70,8 @@ export enum E_OPENAI_MODEL {
MODEL_GPT_4_1_MINI_2025_04_14 = "gpt-4.1-mini-2025-04-14",
MODEL_GPT_4_1_MINI = "gpt-4.1-mini",
MODEL_GPT_4_1_NANO_2025_04_14 = "gpt-4.1-nano-2025-04-14",
MODEL_GPT_4_1_NANO = "gpt-4.1-nano",
MODEL_GPT_IMAGE_1 = "gpt-image-1",
MODEL_GPT_3_5_TURBO_16K = "gpt-3.5-turbo-16k",
MODEL_TTS_1 = "tts-1",
MODEL_WHISPER_1 = "whisper-1",

22
packages/kbot/src/models/cache/openrouter-models-free.ts vendored
View File

@ -1,16 +1,12 @@
export enum E_OPENROUTER_MODEL_FREE {
MODEL_FREE_MISTRALAI_MISTRAL_SMALL_3_2_24B_INSTRUCT_FREE = "mistralai/mistral-small-3.2-24b-instruct:free",
MODEL_FREE_MINIMAX_MINIMAX_M1_EXTENDED = "minimax/minimax-m1:extended",
MODEL_FREE_MOONSHOTAI_KIMI_DEV_72B_FREE = "moonshotai/kimi-dev-72b:free",
MODEL_FREE_DEEPSEEK_DEEPSEEK_R1_0528_QWEN3_8B_FREE = "deepseek/deepseek-r1-0528-qwen3-8b:free",
MODEL_FREE_DEEPSEEK_DEEPSEEK_R1_0528_FREE = "deepseek/deepseek-r1-0528:free",
MODEL_FREE_SARVAMAI_SARVAM_M_FREE = "sarvamai/sarvam-m:free",
MODEL_FREE_MISTRALAI_DEVSTRAL_SMALL_FREE = "mistralai/devstral-small:free",
MODEL_FREE_GOOGLE_GEMMA_3N_E4B_IT_FREE = "google/gemma-3n-e4b-it:free",
MODEL_FREE_META_LLAMA_LLAMA_3_3_8B_INSTRUCT_FREE = "meta-llama/llama-3.3-8b-instruct:free",
MODEL_FREE_NOUSRESEARCH_DEEPHERMES_3_MISTRAL_24B_PREVIEW_FREE = "nousresearch/deephermes-3-mistral-24b-preview:free",
MODEL_FREE_MICROSOFT_PHI_4_REASONING_PLUS_FREE = "microsoft/phi-4-reasoning-plus:free",
MODEL_FREE_MICROSOFT_PHI_4_REASONING_FREE = "microsoft/phi-4-reasoning:free",
MODEL_FREE_OPENGVLAB_INTERNVL3_14B_FREE = "opengvlab/internvl3-14b:free",
MODEL_FREE_OPENGVLAB_INTERNVL3_2B_FREE = "opengvlab/internvl3-2b:free",
MODEL_FREE_DEEPSEEK_DEEPSEEK_PROVER_V2_FREE = "deepseek/deepseek-prover-v2:free",
MODEL_FREE_QWEN_QWEN3_30B_A3B_FREE = "qwen/qwen3-30b-a3b:free",
MODEL_FREE_QWEN_QWEN3_8B_FREE = "qwen/qwen3-8b:free",
MODEL_FREE_QWEN_QWEN3_14B_FREE = "qwen/qwen3-14b:free",
@ -29,27 +25,21 @@ export enum E_OPENROUTER_MODEL_FREE {
MODEL_FREE_META_LLAMA_LLAMA_4_MAVERICK_FREE = "meta-llama/llama-4-maverick:free",
MODEL_FREE_META_LLAMA_LLAMA_4_SCOUT_FREE = "meta-llama/llama-4-scout:free",
MODEL_FREE_DEEPSEEK_DEEPSEEK_V3_BASE_FREE = "deepseek/deepseek-v3-base:free",
MODEL_FREE_QWEN_QWEN2_5_VL_3B_INSTRUCT_FREE = "qwen/qwen2.5-vl-3b-instruct:free",
MODEL_FREE_GOOGLE_GEMINI_2_5_PRO_EXP_03_25 = "google/gemini-2.5-pro-exp-03-25",
MODEL_FREE_QWEN_QWEN2_5_VL_32B_INSTRUCT_FREE = "qwen/qwen2.5-vl-32b-instruct:free",
MODEL_FREE_DEEPSEEK_DEEPSEEK_CHAT_V3_0324_FREE = "deepseek/deepseek-chat-v3-0324:free",
MODEL_FREE_FEATHERLESS_QWERKY_72B_FREE = "featherless/qwerky-72b:free",
MODEL_FREE_MISTRALAI_MISTRAL_SMALL_3_1_24B_INSTRUCT_FREE = "mistralai/mistral-small-3.1-24b-instruct:free",
MODEL_FREE_OPEN_R1_OLYMPICCODER_32B_FREE = "open-r1/olympiccoder-32b:free",
MODEL_FREE_GOOGLE_GEMMA_3_1B_IT_FREE = "google/gemma-3-1b-it:free",
MODEL_FREE_GOOGLE_GEMMA_3_4B_IT_FREE = "google/gemma-3-4b-it:free",
MODEL_FREE_GOOGLE_GEMMA_3_12B_IT_FREE = "google/gemma-3-12b-it:free",
MODEL_FREE_REKAAI_REKA_FLASH_3_FREE = "rekaai/reka-flash-3:free",
MODEL_FREE_GOOGLE_GEMMA_3_27B_IT_FREE = "google/gemma-3-27b-it:free",
MODEL_FREE_DEEPSEEK_DEEPSEEK_R1_ZERO_FREE = "deepseek/deepseek-r1-zero:free",
MODEL_FREE_QWEN_QWQ_32B_FREE = "qwen/qwq-32b:free",
MODEL_FREE_MOONSHOTAI_MOONLIGHT_16B_A3B_INSTRUCT_FREE = "moonshotai/moonlight-16b-a3b-instruct:free",
MODEL_FREE_NOUSRESEARCH_DEEPHERMES_3_LLAMA_3_8B_PREVIEW_FREE = "nousresearch/deephermes-3-llama-3-8b-preview:free",
MODEL_FREE_COGNITIVECOMPUTATIONS_DOLPHIN3_0_R1_MISTRAL_24B_FREE = "cognitivecomputations/dolphin3.0-r1-mistral-24b:free",
MODEL_FREE_COGNITIVECOMPUTATIONS_DOLPHIN3_0_MISTRAL_24B_FREE = "cognitivecomputations/dolphin3.0-mistral-24b:free",
MODEL_FREE_QWEN_QWEN2_5_VL_72B_INSTRUCT_FREE = "qwen/qwen2.5-vl-72b-instruct:free",
MODEL_FREE_MISTRALAI_MISTRAL_SMALL_24B_INSTRUCT_2501_FREE = "mistralai/mistral-small-24b-instruct-2501:free",
MODEL_FREE_DEEPSEEK_DEEPSEEK_R1_DISTILL_QWEN_32B_FREE = "deepseek/deepseek-r1-distill-qwen-32b:free",
MODEL_FREE_DEEPSEEK_DEEPSEEK_R1_DISTILL_QWEN_14B_FREE = "deepseek/deepseek-r1-distill-qwen-14b:free",
MODEL_FREE_DEEPSEEK_DEEPSEEK_R1_DISTILL_LLAMA_70B_FREE = "deepseek/deepseek-r1-distill-llama-70b:free",
MODEL_FREE_DEEPSEEK_DEEPSEEK_R1_FREE = "deepseek/deepseek-r1:free",
@ -57,13 +47,9 @@ export enum E_OPENROUTER_MODEL_FREE {
MODEL_FREE_GOOGLE_GEMINI_2_0_FLASH_EXP_FREE = "google/gemini-2.0-flash-exp:free",
MODEL_FREE_META_LLAMA_LLAMA_3_3_70B_INSTRUCT_FREE = "meta-llama/llama-3.3-70b-instruct:free",
MODEL_FREE_QWEN_QWEN_2_5_CODER_32B_INSTRUCT_FREE = "qwen/qwen-2.5-coder-32b-instruct:free",
MODEL_FREE_QWEN_QWEN_2_5_7B_INSTRUCT_FREE = "qwen/qwen-2.5-7b-instruct:free",
MODEL_FREE_META_LLAMA_LLAMA_3_2_3B_INSTRUCT_FREE = "meta-llama/llama-3.2-3b-instruct:free",
MODEL_FREE_META_LLAMA_LLAMA_3_2_1B_INSTRUCT_FREE = "meta-llama/llama-3.2-1b-instruct:free",
MODEL_FREE_META_LLAMA_LLAMA_3_2_11B_VISION_INSTRUCT_FREE = "meta-llama/llama-3.2-11b-vision-instruct:free",
MODEL_FREE_META_LLAMA_LLAMA_3_2_1B_INSTRUCT_FREE = "meta-llama/llama-3.2-1b-instruct:free",
MODEL_FREE_QWEN_QWEN_2_5_72B_INSTRUCT_FREE = "qwen/qwen-2.5-72b-instruct:free",
MODEL_FREE_QWEN_QWEN_2_5_VL_7B_INSTRUCT_FREE = "qwen/qwen-2.5-vl-7b-instruct:free",
MODEL_FREE_META_LLAMA_LLAMA_3_1_405B_FREE = "meta-llama/llama-3.1-405b:free",
MODEL_FREE_META_LLAMA_LLAMA_3_1_8B_INSTRUCT_FREE = "meta-llama/llama-3.1-8b-instruct:free",
MODEL_FREE_MISTRALAI_MISTRAL_NEMO_FREE = "mistralai/mistral-nemo:free",
MODEL_FREE_GOOGLE_GEMMA_2_9B_IT_FREE = "google/gemma-2-9b-it:free",

84
packages/kbot/src/models/cache/openrouter-models.ts vendored
View File

@ -1,25 +1,38 @@
export enum E_OPENROUTER_MODEL {
MODEL_INCEPTION_MERCURY = "inception/mercury",
MODEL_MORPH_MORPH_V2 = "morph/morph-v2",
MODEL_MISTRALAI_MISTRAL_SMALL_3_2_24B_INSTRUCT_FREE = "mistralai/mistral-small-3.2-24b-instruct:free",
MODEL_MISTRALAI_MISTRAL_SMALL_3_2_24B_INSTRUCT = "mistralai/mistral-small-3.2-24b-instruct",
MODEL_MINIMAX_MINIMAX_M1_EXTENDED = "minimax/minimax-m1:extended",
MODEL_MINIMAX_MINIMAX_M1 = "minimax/minimax-m1",
MODEL_GOOGLE_GEMINI_2_5_FLASH_LITE_PREVIEW_06_17 = "google/gemini-2.5-flash-lite-preview-06-17",
MODEL_GOOGLE_GEMINI_2_5_FLASH = "google/gemini-2.5-flash",
MODEL_GOOGLE_GEMINI_2_5_PRO = "google/gemini-2.5-pro",
MODEL_MOONSHOTAI_KIMI_DEV_72B_FREE = "moonshotai/kimi-dev-72b:free",
MODEL_OPENAI_O3_PRO = "openai/o3-pro",
MODEL_X_AI_GROK_3_MINI = "x-ai/grok-3-mini",
MODEL_X_AI_GROK_3 = "x-ai/grok-3",
MODEL_MISTRALAI_MAGISTRAL_SMALL_2506 = "mistralai/magistral-small-2506",
MODEL_MISTRALAI_MAGISTRAL_MEDIUM_2506 = "mistralai/magistral-medium-2506",
MODEL_MISTRALAI_MAGISTRAL_MEDIUM_2506_THINKING = "mistralai/magistral-medium-2506:thinking",
MODEL_GOOGLE_GEMINI_2_5_PRO_PREVIEW = "google/gemini-2.5-pro-preview",
MODEL_SENTIENTAGI_DOBBY_MINI_UNHINGED_PLUS_LLAMA_3_1_8B = "sentientagi/dobby-mini-unhinged-plus-llama-3.1-8b",
MODEL_DEEPSEEK_DEEPSEEK_R1_DISTILL_QWEN_7B = "deepseek/deepseek-r1-distill-qwen-7b",
MODEL_DEEPSEEK_DEEPSEEK_R1_0528_QWEN3_8B_FREE = "deepseek/deepseek-r1-0528-qwen3-8b:free",
MODEL_DEEPSEEK_DEEPSEEK_R1_0528_QWEN3_8B = "deepseek/deepseek-r1-0528-qwen3-8b",
MODEL_GOOGLE_GEMMA_2B_IT = "google/gemma-2b-it",
MODEL_DEEPSEEK_DEEPSEEK_R1_0528_FREE = "deepseek/deepseek-r1-0528:free",
MODEL_DEEPSEEK_DEEPSEEK_R1_0528 = "deepseek/deepseek-r1-0528",
MODEL_SARVAMAI_SARVAM_M_FREE = "sarvamai/sarvam-m:free",
MODEL_SARVAMAI_SARVAM_M = "sarvamai/sarvam-m",
MODEL_THEDRUMMER_VALKYRIE_49B_V1 = "thedrummer/valkyrie-49b-v1",
MODEL_ANTHROPIC_CLAUDE_OPUS_4 = "anthropic/claude-opus-4",
MODEL_ANTHROPIC_CLAUDE_SONNET_4 = "anthropic/claude-sonnet-4",
MODEL_MISTRALAI_DEVSTRAL_SMALL_FREE = "mistralai/devstral-small:free",
MODEL_MISTRALAI_DEVSTRAL_SMALL = "mistralai/devstral-small",
MODEL_GOOGLE_GEMMA_3N_E4B_IT_FREE = "google/gemma-3n-e4b-it:free",
MODEL_GOOGLE_GEMMA_3N_E4B_IT = "google/gemma-3n-e4b-it",
MODEL_GOOGLE_GEMINI_2_5_FLASH_PREVIEW_05_20 = "google/gemini-2.5-flash-preview-05-20",
MODEL_GOOGLE_GEMINI_2_5_FLASH_PREVIEW_05_20_THINKING = "google/gemini-2.5-flash-preview-05-20:thinking",
MODEL_OPENAI_CODEX_MINI = "openai/codex-mini",
MODEL_META_LLAMA_LLAMA_3_3_8B_INSTRUCT_FREE = "meta-llama/llama-3.3-8b-instruct:free",
MODEL_NOUSRESEARCH_DEEPHERMES_3_MISTRAL_24B_PREVIEW_FREE = "nousresearch/deephermes-3-mistral-24b-preview:free",
MODEL_MISTRALAI_MISTRAL_MEDIUM_3 = "mistralai/mistral-medium-3",
MODEL_GOOGLE_GEMINI_2_5_PRO_PREVIEW_05_06 = "google/gemini-2.5-pro-preview-05-06",
MODEL_ARCEE_AI_CALLER_LARGE = "arcee-ai/caller-large",
@ -29,13 +42,10 @@ export enum E_OPENROUTER_MODEL {
MODEL_ARCEE_AI_CODER_LARGE = "arcee-ai/coder-large",
MODEL_ARCEE_AI_VIRTUOSO_MEDIUM_V2 = "arcee-ai/virtuoso-medium-v2",
MODEL_ARCEE_AI_ARCEE_BLITZ = "arcee-ai/arcee-blitz",
MODEL_MICROSOFT_PHI_4_REASONING_PLUS_FREE = "microsoft/phi-4-reasoning-plus:free",
MODEL_MICROSOFT_PHI_4_REASONING_PLUS = "microsoft/phi-4-reasoning-plus",
MODEL_MICROSOFT_PHI_4_REASONING_FREE = "microsoft/phi-4-reasoning:free",
MODEL_INCEPTION_MERCURY_CODER_SMALL_BETA = "inception/mercury-coder-small-beta",
MODEL_OPENGVLAB_INTERNVL3_14B_FREE = "opengvlab/internvl3-14b:free",
MODEL_OPENGVLAB_INTERNVL3_2B_FREE = "opengvlab/internvl3-2b:free",
MODEL_DEEPSEEK_DEEPSEEK_PROVER_V2_FREE = "deepseek/deepseek-prover-v2:free",
MODEL_OPENGVLAB_INTERNVL3_14B = "opengvlab/internvl3-14b",
MODEL_OPENGVLAB_INTERNVL3_2B = "opengvlab/internvl3-2b",
MODEL_DEEPSEEK_DEEPSEEK_PROVER_V2 = "deepseek/deepseek-prover-v2",
MODEL_META_LLAMA_LLAMA_GUARD_4_12B = "meta-llama/llama-guard-4-12b",
MODEL_QWEN_QWEN3_30B_A3B_FREE = "qwen/qwen3-30b-a3b:free",
@ -81,9 +91,7 @@ export enum E_OPENROUTER_MODEL {
MODEL_META_LLAMA_LLAMA_4_SCOUT = "meta-llama/llama-4-scout",
MODEL_ALL_HANDS_OPENHANDS_LM_32B_V0_1 = "all-hands/openhands-lm-32b-v0.1",
MODEL_DEEPSEEK_DEEPSEEK_V3_BASE_FREE = "deepseek/deepseek-v3-base:free",
MODEL_SCB10X_LLAMA3_1_TYPHOON2_8B_INSTRUCT = "scb10x/llama3.1-typhoon2-8b-instruct",
MODEL_SCB10X_LLAMA3_1_TYPHOON2_70B_INSTRUCT = "scb10x/llama3.1-typhoon2-70b-instruct",
MODEL_QWEN_QWEN2_5_VL_3B_INSTRUCT_FREE = "qwen/qwen2.5-vl-3b-instruct:free",
MODEL_GOOGLE_GEMINI_2_5_PRO_EXP_03_25 = "google/gemini-2.5-pro-exp-03-25",
MODEL_QWEN_QWEN2_5_VL_32B_INSTRUCT_FREE = "qwen/qwen2.5-vl-32b-instruct:free",
MODEL_QWEN_QWEN2_5_VL_32B_INSTRUCT = "qwen/qwen2.5-vl-32b-instruct",
@ -93,8 +101,6 @@ export enum E_OPENROUTER_MODEL {
MODEL_OPENAI_O1_PRO = "openai/o1-pro",
MODEL_MISTRALAI_MISTRAL_SMALL_3_1_24B_INSTRUCT_FREE = "mistralai/mistral-small-3.1-24b-instruct:free",
MODEL_MISTRALAI_MISTRAL_SMALL_3_1_24B_INSTRUCT = "mistralai/mistral-small-3.1-24b-instruct",
MODEL_OPEN_R1_OLYMPICCODER_32B_FREE = "open-r1/olympiccoder-32b:free",
MODEL_GOOGLE_GEMMA_3_1B_IT_FREE = "google/gemma-3-1b-it:free",
MODEL_GOOGLE_GEMMA_3_4B_IT_FREE = "google/gemma-3-4b-it:free",
MODEL_GOOGLE_GEMMA_3_4B_IT = "google/gemma-3-4b-it",
MODEL_AI21_JAMBA_1_6_LARGE = "ai21/jamba-1.6-large",
@ -113,10 +119,8 @@ export enum E_OPENROUTER_MODEL {
MODEL_PERPLEXITY_SONAR_REASONING_PRO = "perplexity/sonar-reasoning-pro",
MODEL_PERPLEXITY_SONAR_PRO = "perplexity/sonar-pro",
MODEL_PERPLEXITY_SONAR_DEEP_RESEARCH = "perplexity/sonar-deep-research",
MODEL_DEEPSEEK_DEEPSEEK_R1_ZERO_FREE = "deepseek/deepseek-r1-zero:free",
MODEL_QWEN_QWQ_32B_FREE = "qwen/qwq-32b:free",
MODEL_QWEN_QWQ_32B = "qwen/qwq-32b",
MODEL_MOONSHOTAI_MOONLIGHT_16B_A3B_INSTRUCT_FREE = "moonshotai/moonlight-16b-a3b-instruct:free",
MODEL_NOUSRESEARCH_DEEPHERMES_3_LLAMA_3_8B_PREVIEW_FREE = "nousresearch/deephermes-3-llama-3-8b-preview:free",
MODEL_OPENAI_GPT_4_5_PREVIEW = "openai/gpt-4.5-preview",
MODEL_GOOGLE_GEMINI_2_0_FLASH_LITE_001 = "google/gemini-2.0-flash-lite-001",
@ -145,7 +149,6 @@ export enum E_OPENROUTER_MODEL {
MODEL_DEEPSEEK_DEEPSEEK_R1_DISTILL_QWEN_1_5B = "deepseek/deepseek-r1-distill-qwen-1.5b",
MODEL_MISTRALAI_MISTRAL_SMALL_24B_INSTRUCT_2501_FREE = "mistralai/mistral-small-24b-instruct-2501:free",
MODEL_MISTRALAI_MISTRAL_SMALL_24B_INSTRUCT_2501 = "mistralai/mistral-small-24b-instruct-2501",
MODEL_DEEPSEEK_DEEPSEEK_R1_DISTILL_QWEN_32B_FREE = "deepseek/deepseek-r1-distill-qwen-32b:free",
MODEL_DEEPSEEK_DEEPSEEK_R1_DISTILL_QWEN_32B = "deepseek/deepseek-r1-distill-qwen-32b",
MODEL_DEEPSEEK_DEEPSEEK_R1_DISTILL_QWEN_14B_FREE = "deepseek/deepseek-r1-distill-qwen-14b:free",
MODEL_DEEPSEEK_DEEPSEEK_R1_DISTILL_QWEN_14B = "deepseek/deepseek-r1-distill-qwen-14b",
@ -191,58 +194,54 @@ export enum E_OPENROUTER_MODEL {
MODEL_ANTHROPIC_CLAUDE_3_5_HAIKU = "anthropic/claude-3.5-haiku",
MODEL_ANTHROPIC_CLAUDE_3_5_HAIKU_20241022_BETA = "anthropic/claude-3.5-haiku-20241022:beta",
MODEL_ANTHROPIC_CLAUDE_3_5_HAIKU_20241022 = "anthropic/claude-3.5-haiku-20241022",
MODEL_NEVERSLEEP_LLAMA_3_1_LUMIMAID_70B = "neversleep/llama-3.1-lumimaid-70b",
MODEL_ANTHRACITE_ORG_MAGNUM_V4_72B = "anthracite-org/magnum-v4-72b",
MODEL_ANTHROPIC_CLAUDE_3_5_SONNET_BETA = "anthropic/claude-3.5-sonnet:beta",
MODEL_ANTHROPIC_CLAUDE_3_5_SONNET = "anthropic/claude-3.5-sonnet",
MODEL_ANTHRACITE_ORG_MAGNUM_V4_72B = "anthracite-org/magnum-v4-72b",
MODEL_NEVERSLEEP_LLAMA_3_1_LUMIMAID_70B = "neversleep/llama-3.1-lumimaid-70b",
MODEL_X_AI_GROK_BETA = "x-ai/grok-beta",
MODEL_MISTRALAI_MINISTRAL_8B = "mistralai/ministral-8b",
MODEL_MISTRALAI_MINISTRAL_3B = "mistralai/ministral-3b",
MODEL_QWEN_QWEN_2_5_7B_INSTRUCT_FREE = "qwen/qwen-2.5-7b-instruct:free",
MODEL_QWEN_QWEN_2_5_7B_INSTRUCT = "qwen/qwen-2.5-7b-instruct",
MODEL_NVIDIA_LLAMA_3_1_NEMOTRON_70B_INSTRUCT = "nvidia/llama-3.1-nemotron-70b-instruct",
MODEL_INFLECTION_INFLECTION_3_PRODUCTIVITY = "inflection/inflection-3-productivity",
MODEL_INFLECTION_INFLECTION_3_PI = "inflection/inflection-3-pi",
MODEL_INFLECTION_INFLECTION_3_PRODUCTIVITY = "inflection/inflection-3-productivity",
MODEL_GOOGLE_GEMINI_FLASH_1_5_8B = "google/gemini-flash-1.5-8b",
MODEL_THEDRUMMER_ROCINANTE_12B = "thedrummer/rocinante-12b",
MODEL_ANTHRACITE_ORG_MAGNUM_V2_72B = "anthracite-org/magnum-v2-72b",
MODEL_LIQUID_LFM_40B = "liquid/lfm-40b",
MODEL_META_LLAMA_LLAMA_3_2_3B_INSTRUCT_FREE = "meta-llama/llama-3.2-3b-instruct:free",
MODEL_ANTHRACITE_ORG_MAGNUM_V2_72B = "anthracite-org/magnum-v2-72b",
MODEL_THEDRUMMER_ROCINANTE_12B = "thedrummer/rocinante-12b",
MODEL_META_LLAMA_LLAMA_3_2_3B_INSTRUCT = "meta-llama/llama-3.2-3b-instruct",
MODEL_META_LLAMA_LLAMA_3_2_1B_INSTRUCT_FREE = "meta-llama/llama-3.2-1b-instruct:free",
MODEL_META_LLAMA_LLAMA_3_2_1B_INSTRUCT = "meta-llama/llama-3.2-1b-instruct",
MODEL_META_LLAMA_LLAMA_3_2_90B_VISION_INSTRUCT = "meta-llama/llama-3.2-90b-vision-instruct",
MODEL_META_LLAMA_LLAMA_3_2_11B_VISION_INSTRUCT_FREE = "meta-llama/llama-3.2-11b-vision-instruct:free",
MODEL_META_LLAMA_LLAMA_3_2_11B_VISION_INSTRUCT = "meta-llama/llama-3.2-11b-vision-instruct",
MODEL_META_LLAMA_LLAMA_3_2_1B_INSTRUCT_FREE = "meta-llama/llama-3.2-1b-instruct:free",
MODEL_META_LLAMA_LLAMA_3_2_1B_INSTRUCT = "meta-llama/llama-3.2-1b-instruct",
MODEL_QWEN_QWEN_2_5_72B_INSTRUCT_FREE = "qwen/qwen-2.5-72b-instruct:free",
MODEL_QWEN_QWEN_2_5_72B_INSTRUCT = "qwen/qwen-2.5-72b-instruct",
MODEL_NEVERSLEEP_LLAMA_3_1_LUMIMAID_8B = "neversleep/llama-3.1-lumimaid-8b",
MODEL_OPENAI_O1_PREVIEW = "openai/o1-preview",
MODEL_OPENAI_O1_MINI_2024_09_12 = "openai/o1-mini-2024-09-12",
MODEL_OPENAI_O1_PREVIEW_2024_09_12 = "openai/o1-preview-2024-09-12",
MODEL_OPENAI_O1_MINI = "openai/o1-mini",
MODEL_OPENAI_O1_MINI_2024_09_12 = "openai/o1-mini-2024-09-12",
MODEL_MISTRALAI_PIXTRAL_12B = "mistralai/pixtral-12b",
MODEL_COHERE_COMMAND_R_PLUS_08_2024 = "cohere/command-r-plus-08-2024",
MODEL_COHERE_COMMAND_R_08_2024 = "cohere/command-r-08-2024",
MODEL_QWEN_QWEN_2_5_VL_7B_INSTRUCT_FREE = "qwen/qwen-2.5-vl-7b-instruct:free",
MODEL_QWEN_QWEN_2_5_VL_7B_INSTRUCT = "qwen/qwen-2.5-vl-7b-instruct",
MODEL_SAO10K_L3_1_EURYALE_70B = "sao10k/l3.1-euryale-70b",
MODEL_MICROSOFT_PHI_3_5_MINI_128K_INSTRUCT = "microsoft/phi-3.5-mini-128k-instruct",
MODEL_NOUSRESEARCH_HERMES_3_LLAMA_3_1_70B = "nousresearch/hermes-3-llama-3.1-70b",
MODEL_NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B = "nousresearch/hermes-3-llama-3.1-405b",
MODEL_OPENAI_CHATGPT_4O_LATEST = "openai/chatgpt-4o-latest",
MODEL_SAO10K_L3_LUNARIS_8B = "sao10k/l3-lunaris-8b",
MODEL_AETHERWIING_MN_STARCANNON_12B = "aetherwiing/mn-starcannon-12b",
MODEL_SAO10K_L3_LUNARIS_8B = "sao10k/l3-lunaris-8b",
MODEL_OPENAI_GPT_4O_2024_08_06 = "openai/gpt-4o-2024-08-06",
MODEL_META_LLAMA_LLAMA_3_1_405B_FREE = "meta-llama/llama-3.1-405b:free",
MODEL_META_LLAMA_LLAMA_3_1_405B = "meta-llama/llama-3.1-405b",
MODEL_NOTHINGIISREAL_MN_CELESTE_12B = "nothingiisreal/mn-celeste-12b",
MODEL_META_LLAMA_LLAMA_3_1_405B = "meta-llama/llama-3.1-405b",
MODEL_PERPLEXITY_LLAMA_3_1_SONAR_SMALL_128K_ONLINE = "perplexity/llama-3.1-sonar-small-128k-online",
MODEL_PERPLEXITY_LLAMA_3_1_SONAR_LARGE_128K_ONLINE = "perplexity/llama-3.1-sonar-large-128k-online",
MODEL_META_LLAMA_LLAMA_3_1_8B_INSTRUCT_FREE = "meta-llama/llama-3.1-8b-instruct:free",
MODEL_META_LLAMA_LLAMA_3_1_8B_INSTRUCT = "meta-llama/llama-3.1-8b-instruct",
MODEL_META_LLAMA_LLAMA_3_1_405B_INSTRUCT = "meta-llama/llama-3.1-405b-instruct",
MODEL_META_LLAMA_LLAMA_3_1_70B_INSTRUCT = "meta-llama/llama-3.1-70b-instruct",
MODEL_META_LLAMA_LLAMA_3_1_8B_INSTRUCT_FREE = "meta-llama/llama-3.1-8b-instruct:free",
MODEL_META_LLAMA_LLAMA_3_1_8B_INSTRUCT = "meta-llama/llama-3.1-8b-instruct",
MODEL_MISTRALAI_MISTRAL_NEMO_FREE = "mistralai/mistral-nemo:free",
MODEL_MISTRALAI_MISTRAL_NEMO = "mistralai/mistral-nemo",
MODEL_OPENAI_GPT_4O_MINI = "openai/gpt-4o-mini",
@ -257,31 +256,31 @@ export enum E_OPENROUTER_MODEL {
MODEL_SAO10K_L3_EURYALE_70B = "sao10k/l3-euryale-70b",
MODEL_COGNITIVECOMPUTATIONS_DOLPHIN_MIXTRAL_8X22B = "cognitivecomputations/dolphin-mixtral-8x22b",
MODEL_QWEN_QWEN_2_72B_INSTRUCT = "qwen/qwen-2-72b-instruct",
MODEL_MISTRALAI_MISTRAL_7B_INSTRUCT_V0_3 = "mistralai/mistral-7b-instruct-v0.3",
MODEL_NOUSRESEARCH_HERMES_2_PRO_LLAMA_3_8B = "nousresearch/hermes-2-pro-llama-3-8b",
MODEL_MISTRALAI_MISTRAL_7B_INSTRUCT_FREE = "mistralai/mistral-7b-instruct:free",
MODEL_MISTRALAI_MISTRAL_7B_INSTRUCT = "mistralai/mistral-7b-instruct",
MODEL_NOUSRESEARCH_HERMES_2_PRO_LLAMA_3_8B = "nousresearch/hermes-2-pro-llama-3-8b",
MODEL_MISTRALAI_MISTRAL_7B_INSTRUCT_V0_3 = "mistralai/mistral-7b-instruct-v0.3",
MODEL_MICROSOFT_PHI_3_MINI_128K_INSTRUCT = "microsoft/phi-3-mini-128k-instruct",
MODEL_MICROSOFT_PHI_3_MEDIUM_128K_INSTRUCT = "microsoft/phi-3-medium-128k-instruct",
MODEL_NEVERSLEEP_LLAMA_3_LUMIMAID_70B = "neversleep/llama-3-lumimaid-70b",
MODEL_GOOGLE_GEMINI_FLASH_1_5 = "google/gemini-flash-1.5",
MODEL_OPENAI_GPT_4O_2024_05_13 = "openai/gpt-4o-2024-05-13",
MODEL_META_LLAMA_LLAMA_GUARD_2_8B = "meta-llama/llama-guard-2-8b",
MODEL_OPENAI_GPT_4O = "openai/gpt-4o",
MODEL_OPENAI_GPT_4O_EXTENDED = "openai/gpt-4o:extended",
MODEL_META_LLAMA_LLAMA_GUARD_2_8B = "meta-llama/llama-guard-2-8b",
MODEL_OPENAI_GPT_4O_2024_05_13 = "openai/gpt-4o-2024-05-13",
MODEL_NEVERSLEEP_LLAMA_3_LUMIMAID_8B = "neversleep/llama-3-lumimaid-8b",
MODEL_SAO10K_FIMBULVETR_11B_V2 = "sao10k/fimbulvetr-11b-v2",
MODEL_META_LLAMA_LLAMA_3_8B_INSTRUCT = "meta-llama/llama-3-8b-instruct",
MODEL_META_LLAMA_LLAMA_3_70B_INSTRUCT = "meta-llama/llama-3-70b-instruct",
MODEL_MISTRALAI_MIXTRAL_8X22B_INSTRUCT = "mistralai/mixtral-8x22b-instruct",
MODEL_MICROSOFT_WIZARDLM_2_8X22B = "microsoft/wizardlm-2-8x22b",
MODEL_GOOGLE_GEMINI_PRO_1_5 = "google/gemini-pro-1.5",
MODEL_OPENAI_GPT_4_TURBO = "openai/gpt-4-turbo",
MODEL_GOOGLE_GEMINI_PRO_1_5 = "google/gemini-pro-1.5",
MODEL_COHERE_COMMAND_R_PLUS = "cohere/command-r-plus",
MODEL_COHERE_COMMAND_R_PLUS_04_2024 = "cohere/command-r-plus-04-2024",
MODEL_SOPHOSYMPATHEIA_MIDNIGHT_ROSE_70B = "sophosympatheia/midnight-rose-70b",
MODEL_COHERE_COMMAND = "cohere/command",
MODEL_COHERE_COMMAND_R = "cohere/command-r",
MODEL_COHERE_COMMAND = "cohere/command",
MODEL_ANTHROPIC_CLAUDE_3_HAIKU_BETA = "anthropic/claude-3-haiku:beta",
MODEL_ANTHROPIC_CLAUDE_3_HAIKU = "anthropic/claude-3-haiku",
MODEL_ANTHROPIC_CLAUDE_3_OPUS_BETA = "anthropic/claude-3-opus:beta",
@ -293,20 +292,18 @@ export enum E_OPENROUTER_MODEL {
MODEL_OPENAI_GPT_3_5_TURBO_0613 = "openai/gpt-3.5-turbo-0613",
MODEL_OPENAI_GPT_4_TURBO_PREVIEW = "openai/gpt-4-turbo-preview",
MODEL_NOUSRESEARCH_NOUS_HERMES_2_MIXTRAL_8X7B_DPO = "nousresearch/nous-hermes-2-mixtral-8x7b-dpo",
MODEL_MISTRALAI_MISTRAL_MEDIUM = "mistralai/mistral-medium",
MODEL_MISTRALAI_MISTRAL_SMALL = "mistralai/mistral-small",
MODEL_MISTRALAI_MISTRAL_TINY = "mistralai/mistral-tiny",
MODEL_MISTRALAI_MISTRAL_7B_INSTRUCT_V0_2 = "mistralai/mistral-7b-instruct-v0.2",
MODEL_MISTRALAI_MIXTRAL_8X7B_INSTRUCT = "mistralai/mixtral-8x7b-instruct",
MODEL_NEVERSLEEP_NOROMAID_20B = "neversleep/noromaid-20b",
MODEL_ANTHROPIC_CLAUDE_2_1_BETA = "anthropic/claude-2.1:beta",
MODEL_ANTHROPIC_CLAUDE_2_1 = "anthropic/claude-2.1",
MODEL_ANTHROPIC_CLAUDE_2_BETA = "anthropic/claude-2:beta",
MODEL_ANTHROPIC_CLAUDE_2 = "anthropic/claude-2",
MODEL_ANTHROPIC_CLAUDE_2_1_BETA = "anthropic/claude-2.1:beta",
MODEL_ANTHROPIC_CLAUDE_2_1 = "anthropic/claude-2.1",
MODEL_UNDI95_TOPPY_M_7B = "undi95/toppy-m-7b",
MODEL_ALPINDALE_GOLIATH_120B = "alpindale/goliath-120b",
MODEL_OPENROUTER_AUTO = "openrouter/auto",
MODEL_OPENAI_GPT_3_5_TURBO_1106 = "openai/gpt-3.5-turbo-1106",
MODEL_OPENAI_GPT_4_1106_PREVIEW = "openai/gpt-4-1106-preview",
MODEL_OPENAI_GPT_3_5_TURBO_INSTRUCT = "openai/gpt-3.5-turbo-instruct",
MODEL_MISTRALAI_MISTRAL_7B_INSTRUCT_V0_1 = "mistralai/mistral-7b-instruct-v0.1",
@ -317,9 +314,6 @@ export enum E_OPENROUTER_MODEL {
MODEL_ANTHROPIC_CLAUDE_2_0 = "anthropic/claude-2.0",
MODEL_UNDI95_REMM_SLERP_L2_13B = "undi95/remm-slerp-l2-13b",
MODEL_GRYPHE_MYTHOMAX_L2_13B = "gryphe/mythomax-l2-13b",
MODEL_META_LLAMA_LLAMA_2_70B_CHAT = "meta-llama/llama-2-70b-chat",
MODEL_OPENAI_GPT_3_5_TURBO = "openai/gpt-3.5-turbo",
MODEL_OPENAI_GPT_3_5_TURBO_0125 = "openai/gpt-3.5-turbo-0125",
MODEL_OPENAI_GPT_4 = "openai/gpt-4",
MODEL_OPENAI_GPT_4_0314 = "openai/gpt-4-0314"
}

50
packages/kbot/src/zod_types.ts
View File

@ -87,10 +87,8 @@ export interface IKBotOptions {
cohere/command-r-plus-08-2024 | paid
cohere/command-r7b-12-2024 | paid
deepseek/deepseek-prover-v2 | paid
deepseek/deepseek-prover-v2:free | free
deepseek/deepseek-r1-0528-qwen3-8b | paid
deepseek/deepseek-r1-0528-qwen3-8b:free | free
deepseek/deepseek-r1-zero:free | free
deepseek/deepseek-chat | paid
deepseek/deepseek-chat:free | free
deepseek/deepseek-chat-v3-0324 | paid
@ -107,7 +105,6 @@ export interface IKBotOptions {
deepseek/deepseek-r1-distill-qwen-14b | paid
deepseek/deepseek-r1-distill-qwen-14b:free | free
deepseek/deepseek-r1-distill-qwen-32b | paid
deepseek/deepseek-r1-distill-qwen-32b:free | free
deepseek/deepseek-r1-distill-qwen-7b | paid
cognitivecomputations/dolphin-mixtral-8x22b | paid
cognitivecomputations/dolphin3.0-mistral-24b:free | free
@ -124,28 +121,33 @@ export interface IKBotOptions {
google/gemini-2.0-flash-001 | paid
google/gemini-2.0-flash-exp:free | free
google/gemini-2.0-flash-lite-001 | paid
google/gemini-2.5-flash | paid
google/gemini-2.5-flash-lite-preview-06-17 | paid
google/gemini-2.5-flash-preview | paid
google/gemini-2.5-flash-preview:thinking | paid
google/gemini-2.5-flash-preview-05-20 | paid
google/gemini-2.5-flash-preview-05-20:thinking | paid
google/gemini-2.5-pro | paid
google/gemini-2.5-pro-exp-03-25 | paid
google/gemini-2.5-pro-preview-05-06 | paid
google/gemini-2.5-pro-preview | paid
google/gemma-2-27b-it | paid
google/gemma-2b-it | paid
google/gemma-2-9b-it | paid
google/gemma-2-9b-it:free | free
google/gemma-3-12b-it | paid
google/gemma-3-12b-it:free | free
google/gemma-3-1b-it:free | free
google/gemma-3-27b-it | paid
google/gemma-3-27b-it:free | free
google/gemma-3-4b-it | paid
google/gemma-3-4b-it:free | free
google/gemma-3n-e4b-it | paid
google/gemma-3n-e4b-it:free | free
inception/mercury | paid
inception/mercury-coder-small-beta | paid
infermatic/mn-inferor-12b | paid
inflection/inflection-3-pi | paid
inflection/inflection-3-productivity | paid
moonshotai/kimi-dev-72b:free | free
liquid/lfm-3b | paid
liquid/lfm-40b | paid
liquid/lfm-7b | paid
@ -154,11 +156,9 @@ export interface IKBotOptions {
anthracite-org/magnum-v2-72b | paid
anthracite-org/magnum-v4-72b | paid
mancer/weaver | paid
meta-llama/llama-2-70b-chat | paid
meta-llama/llama-3-70b-instruct | paid
meta-llama/llama-3-8b-instruct | paid
meta-llama/llama-3.1-405b | paid
meta-llama/llama-3.1-405b:free | free
meta-llama/llama-3.1-405b-instruct | paid
meta-llama/llama-3.1-70b-instruct | paid
meta-llama/llama-3.1-8b-instruct | paid
@ -168,11 +168,9 @@ export interface IKBotOptions {
meta-llama/llama-3.2-1b-instruct | paid
meta-llama/llama-3.2-1b-instruct:free | free
meta-llama/llama-3.2-3b-instruct | paid
meta-llama/llama-3.2-3b-instruct:free | free
meta-llama/llama-3.2-90b-vision-instruct | paid
meta-llama/llama-3.3-70b-instruct | paid
meta-llama/llama-3.3-70b-instruct:free | free
meta-llama/llama-3.3-8b-instruct:free | free
meta-llama/llama-4-maverick | paid
meta-llama/llama-4-maverick:free | free
meta-llama/llama-4-scout | paid
@ -182,24 +180,26 @@ export interface IKBotOptions {
microsoft/mai-ds-r1:free | free
microsoft/phi-4 | paid
microsoft/phi-4-multimodal-instruct | paid
microsoft/phi-4-reasoning:free | free
microsoft/phi-4-reasoning-plus | paid
microsoft/phi-4-reasoning-plus:free | free
microsoft/phi-3-medium-128k-instruct | paid
microsoft/phi-3-mini-128k-instruct | paid
microsoft/phi-3.5-mini-128k-instruct | paid
sophosympatheia/midnight-rose-70b | paid
minimax/minimax-m1 | paid
minimax/minimax-m1:extended | paid
minimax/minimax-01 | paid
mistralai/mistral-large | paid
mistralai/mistral-large-2407 | paid
mistralai/mistral-large-2411 | paid
mistralai/mistral-medium | paid
nothingiisreal/mn-celeste-12b | paid
mistralai/mistral-small | paid
mistralai/mistral-tiny | paid
mistralai/codestral-2501 | paid
mistralai/devstral-small | paid
mistralai/devstral-small:free | free
mistralai/magistral-medium-2506 | paid
mistralai/magistral-medium-2506:thinking | paid
mistralai/magistral-small-2506 | paid
mistralai/ministral-3b | paid
mistralai/ministral-8b | paid
mistralai/mistral-7b-instruct | paid
@ -214,13 +214,15 @@ export interface IKBotOptions {
mistralai/mistral-small-24b-instruct-2501:free | free
mistralai/mistral-small-3.1-24b-instruct | paid
mistralai/mistral-small-3.1-24b-instruct:free | free
mistralai/mistral-small-3.2-24b-instruct | paid
mistralai/mistral-small-3.2-24b-instruct:free | free
mistralai/mixtral-8x22b-instruct | paid
mistralai/mixtral-8x7b-instruct | paid
mistralai/pixtral-12b | paid
mistralai/pixtral-large-2411 | paid
mistralai/mistral-saba | paid
moonshotai/kimi-vl-a3b-thinking:free | free
moonshotai/moonlight-16b-a3b-instruct:free | free
morph/morph-v2 | paid
gryphe/mythomax-l2-13b | paid
neversleep/llama-3-lumimaid-70b | paid
neversleep/llama-3-lumimaid-8b | paid
@ -228,7 +230,6 @@ export interface IKBotOptions {
neversleep/llama-3.1-lumimaid-8b | paid
neversleep/noromaid-20b | paid
nousresearch/deephermes-3-llama-3-8b-preview:free | free
nousresearch/deephermes-3-mistral-24b-preview:free | free
nousresearch/nous-hermes-2-mixtral-8x7b-dpo | paid
nousresearch/hermes-3-llama-3.1-405b | paid
nousresearch/hermes-3-llama-3.1-70b | paid
@ -238,19 +239,13 @@ export interface IKBotOptions {
nvidia/llama-3.1-nemotron-ultra-253b-v1:free | free
nvidia/llama-3.3-nemotron-super-49b-v1 | paid
nvidia/llama-3.3-nemotron-super-49b-v1:free | free
open-r1/olympiccoder-32b:free | free
openai/chatgpt-4o-latest | paid
openai/codex-mini | paid
openai/gpt-3.5-turbo | paid
openai/gpt-3.5-turbo-0613 | paid
openai/gpt-3.5-turbo-16k | paid
openai/gpt-3.5-turbo-0125 | paid
openai/gpt-3.5-turbo-1106 | paid
openai/gpt-3.5-turbo-instruct | paid
openai/gpt-4 | paid
openai/gpt-4-0314 | paid
openai/gpt-4-32k | paid
openai/gpt-4-32k-0314 | paid
openai/gpt-4-turbo | paid
openai/gpt-4-1106-preview | paid
openai/gpt-4-turbo-preview | paid
@ -276,10 +271,11 @@ export interface IKBotOptions {
openai/o3 | paid
openai/o3-mini | paid
openai/o3-mini-high | paid
openai/o3-pro | paid
openai/o4-mini | paid
openai/o4-mini-high | paid
opengvlab/internvl3-14b:free | free
opengvlab/internvl3-2b:free | free
opengvlab/internvl3-14b | paid
opengvlab/internvl3-2b | paid
all-hands/openhands-lm-32b-v0.1 | paid
perplexity/llama-3.1-sonar-large-128k-online | paid
perplexity/llama-3.1-sonar-small-128k-online | paid
@ -298,11 +294,9 @@ export interface IKBotOptions {
qwen/qwen-turbo | paid
qwen/qwen2.5-vl-32b-instruct | paid
qwen/qwen2.5-vl-32b-instruct:free | free
qwen/qwen2.5-vl-3b-instruct:free | free
qwen/qwen2.5-vl-72b-instruct | paid
qwen/qwen2.5-vl-72b-instruct:free | free
qwen/qwen-2.5-vl-7b-instruct | paid
qwen/qwen-2.5-vl-7b-instruct:free | free
qwen/qwen3-14b | paid
qwen/qwen3-14b:free | free
qwen/qwen3-235b-a22b | paid
@ -319,7 +313,6 @@ export interface IKBotOptions {
qwen/qwen-2.5-72b-instruct | paid
qwen/qwen-2.5-72b-instruct:free | free
qwen/qwen-2.5-7b-instruct | paid
qwen/qwen-2.5-7b-instruct:free | free
qwen/qwen-2.5-coder-32b-instruct | paid
qwen/qwen-2.5-coder-32b-instruct:free | free
featherless/qwerky-72b:free | free
@ -329,8 +322,8 @@ export interface IKBotOptions {
sao10k/l3-euryale-70b | paid
sao10k/l3.1-euryale-70b | paid
sao10k/l3.3-euryale-70b | paid
sarvamai/sarvam-m | paid
sarvamai/sarvam-m:free | free
sentientagi/dobby-mini-unhinged-plus-llama-3.1-8b | paid
shisa-ai/shisa-v2-llama3.3-70b:free | free
raifle/sorcererlm-8x22b | paid
thedrummer/anubis-pro-105b-v1 | paid
@ -346,11 +339,12 @@ export interface IKBotOptions {
tngtech/deepseek-r1t-chimera:free | free
undi95/toppy-m-7b | paid
scb10x/llama3.1-typhoon2-70b-instruct | paid
scb10x/llama3.1-typhoon2-8b-instruct | paid
microsoft/wizardlm-2-8x22b | paid
x-ai/grok-2-1212 | paid
x-ai/grok-2-vision-1212 | paid
x-ai/grok-3 | paid
x-ai/grok-3-beta | paid
x-ai/grok-3-mini | paid
x-ai/grok-3-mini-beta | paid
x-ai/grok-beta | paid
x-ai/grok-vision-beta | paid
@ -422,6 +416,8 @@ export interface IKBotOptions {
o3-mini-2025-01-31
o4-mini
o4-mini-2025-04-16
o4-mini-deep-research
o4-mini-deep-research-2025-06-26
omni-moderation-2024-09-26
omni-moderation-latest
text-embedding-3-large

523
packages/kbot/tests/unit/reports/all.json
View File

@ -5081,6 +5081,473 @@
"passed": true,
"duration": 1336,
"category": "language"
},
{
"test": "synonyms",
"prompt": "Provide a synonym for \"happy\". Return only the synonym, no explanation.",
"result": [
"Joyful"
],
"expected": "joyful",
"model": "openai/gpt-4o-mini",
"router": "openai/gpt-4o-mini",
"timestamp": "2025-06-05T22:54:17.429Z",
"passed": true,
"duration": 561,
"category": "language"
},
{
"test": "synonyms",
"prompt": "Provide a synonym for \"happy\". Return only the synonym, no explanation.",
"result": [
"Joyful"
],
"expected": "joyful",
"model": "deepseek/deepseek-r1:free",
"router": "deepseek/deepseek-r1:free",
"timestamp": "2025-06-05T22:54:21.005Z",
"passed": true,
"duration": 3571,
"category": "language"
},
{
"test": "addition",
"prompt": "add 5 and 3. Return only the number, no explanation.",
"result": [
"8"
],
"expected": "8",
"model": "anthropic/claude-sonnet-4",
"router": "anthropic/claude-sonnet-4",
"timestamp": "2025-06-05T22:54:48.966Z",
"passed": true,
"duration": 1522,
"category": "basic"
},
{
"test": "addition",
"prompt": "add 5 and 3. Return only the number, no explanation.",
"result": [
"8"
],
"expected": "8",
"model": "openai/gpt-4o-mini",
"router": "openai/gpt-4o-mini",
"timestamp": "2025-06-05T22:54:49.606Z",
"passed": true,
"duration": 634,
"category": "basic"
},
{
"test": "addition",
"prompt": "add 5 and 3. Return only the number, no explanation.",
"result": [
"8"
],
"expected": "8",
"model": "deepseek/deepseek-r1:free",
"router": "deepseek/deepseek-r1:free",
"timestamp": "2025-06-05T22:54:53.004Z",
"passed": true,
"duration": 3394,
"category": "basic"
},
{
"test": "multiplication",
"prompt": "multiply 8 and 3. Return only the number, no explanation.",
"result": [
"24"
],
"expected": "24",
"model": "anthropic/claude-sonnet-4",
"router": "anthropic/claude-sonnet-4",
"timestamp": "2025-06-05T22:54:53.710Z",
"passed": true,
"duration": 702,
"category": "basic"
},
{
"test": "multiplication",
"prompt": "multiply 8 and 3. Return only the number, no explanation.",
"result": [
"24"
],
"expected": "24",
"model": "openai/gpt-4o-mini",
"router": "openai/gpt-4o-mini",
"timestamp": "2025-06-05T22:54:56.480Z",
"passed": true,
"duration": 2765,
"category": "basic"
},
{
"test": "multiplication",
"prompt": "multiply 8 and 3. Return only the number, no explanation.",
"result": [
"The result of multiplying 8 and 3 is \\boxed{24}."
],
"expected": "24",
"model": "deepseek/deepseek-r1:free",
"router": "deepseek/deepseek-r1:free",
"timestamp": "2025-06-05T22:54:59.909Z",
"passed": false,
"duration": 3425,
"reason": "Expected 24, but got The result of multiplying 8 and 3 is \\boxed{24}.",
"category": "basic"
},
{
"test": "division",
"prompt": "divide 15 by 3. Return only the number, no explanation.",
"result": [
"5"
],
"expected": "5",
"model": "anthropic/claude-sonnet-4",
"router": "anthropic/claude-sonnet-4",
"timestamp": "2025-06-05T22:55:01.169Z",
"passed": true,
"duration": 1252,
"category": "basic"
},
{
"test": "division",
"prompt": "divide 15 by 3. Return only the number, no explanation.",
"result": [
"5"
],
"expected": "5",
"model": "openai/gpt-4o-mini",
"router": "openai/gpt-4o-mini",
"timestamp": "2025-06-05T22:55:01.737Z",
"passed": true,
"duration": 564,
"category": "basic"
},
{
"test": "division",
"prompt": "divide 15 by 3. Return only the number, no explanation.",
"result": [
"5"
],
"expected": "5",
"model": "deepseek/deepseek-r1:free",
"router": "deepseek/deepseek-r1:free",
"timestamp": "2025-06-05T22:55:06.362Z",
"passed": true,
"duration": 4619,
"category": "basic"
},
{
"test": "web_content",
"prompt": "Check if the content contains a section about Human prehistory. Reply with \"yes\" if it does, \"no\" if it does not.",
"result": [
"Looking through the table of contents in the Wikipedia article on Kenya, I can see that there is indeed a section titled \"Prehistory\" under the History section.\n\nyes"
],
"expected": "yes",
"model": "anthropic/claude-sonnet-4",
"router": "anthropic/claude-sonnet-4",
"timestamp": "2025-06-05T22:55:12.528Z",
"passed": false,
"duration": 6161,
"reason": "Expected yes, but got Looking through the table of contents in the Wikipedia article on Kenya, I can see that there is indeed a section titled \"Prehistory\" under the History section.\n\nyes",
"category": "basic"
},
{
"test": "web_content",
"prompt": "Check if the content contains a section about Human prehistory. Reply with \"yes\" if it does, \"no\" if it does not.",
"result": [
"yes"
],
"expected": "yes",
"model": "openai/gpt-4o-mini",
"router": "openai/gpt-4o-mini",
"timestamp": "2025-06-05T22:55:18.757Z",
"passed": true,
"duration": 6225,
"category": "basic"
},
{
"test": "web_content",
"prompt": "Check if the content contains a section about Human prehistory. Reply with \"yes\" if it does, \"no\" if it does not.",
"result": [],
"expected": "yes",
"model": "deepseek/deepseek-r1:free",
"router": "deepseek/deepseek-r1:free",
"timestamp": "2025-06-05T22:55:25.642Z",
"passed": false,
"duration": 6879,
"reason": "Model returned empty response",
"category": "basic"
},
{
"test": "file-inclusion",
"prompt": "What animals are shown in these images?",
"result": [
"{\"animals\":[\"cat\",\"fox\"]}"
],
"expected": "[\"cat\",\"fox\"]",
"model": "openai/gpt-4o",
"router": "openai/gpt-4o",
"timestamp": "2025-06-05T22:55:45.624Z",
"passed": true,
"duration": 5694,
"category": "files"
},
{
"test": "file-inclusion",
"prompt": "What is the name of the algorithm implemented in these files? Return only the name.",
"result": [
"bubbleSort"
],
"expected": "bubble sort",
"model": "openai/gpt-4o",
"router": "openai/gpt-4o",
"timestamp": "2025-06-05T22:55:46.325Z",
"passed": false,
"duration": 694,
"reason": "Expected bubble sort, but got bubbleSort",
"category": "files"
},
{
"test": "file-inclusion",
"prompt": "List all algorithms implemented in these files, as JSON array.",
"result": [
"{\"algorithms\":[\"factorial\",\"bubbleSort\"]}"
],
"expected": "[\"bubble sort\",\"factorial\"]",
"model": "openai/gpt-4o",
"router": "openai/gpt-4o",
"timestamp": "2025-06-05T22:55:47.088Z",
"passed": true,
"duration": 758,
"category": "files"
},
{
"test": "file-inclusion",
"prompt": "What is the title of the product in data.json? Return only the title.",
"result": [
"Injection Barrel"
],
"expected": "Injection Barrel",
"model": "openai/gpt-4o",
"router": "openai/gpt-4o",
"timestamp": "2025-06-05T22:55:47.875Z",
"passed": true,
"duration": 782,
"category": "files"
},
{
"test": "summarization",
"prompt": "Summarize: \"The quick brown fox jumps over the dog\". Return only the summary, compact, no explanation.",
"result": [
"Fox jumps over dog."
],
"expected": "A fox jumps over a dog",
"model": "anthropic/claude-sonnet-4",
"router": "anthropic/claude-sonnet-4",
"timestamp": "2025-06-05T22:55:58.691Z",
"passed": true,
"duration": 1621,
"category": "language"
},
{
"test": "summarization",
"prompt": "Summarize: \"The quick brown fox jumps over the dog\". Return only the summary, compact, no explanation.",
"result": [
"A fox jumps over a dog."
],
"expected": "A fox jumps over a dog",
"model": "openai/gpt-4o-mini",
"router": "openai/gpt-4o-mini",
"timestamp": "2025-06-05T22:56:00.205Z",
"passed": true,
"duration": 1508,
"category": "language"
},
{
"test": "summarization",
"prompt": "Summarize: \"The quick brown fox jumps over the dog\". Return only the summary, compact, no explanation.",
"result": [
"A quick brown fox leaps over a dog."
],
"expected": "A fox jumps over a dog",
"model": "deepseek/deepseek-r1:free",
"router": "deepseek/deepseek-r1:free",
"timestamp": "2025-06-05T22:56:06.210Z",
"passed": true,
"duration": 6000,
"category": "language"
},
{
"test": "translation",
"prompt": "Translate \"Hello, world!\" to Spanish. Return only the translation, no explanation.",
"result": [
"¡Hola, mundo!"
],
"expected": "¡Hola, mundo!",
"model": "anthropic/claude-sonnet-4",
"router": "anthropic/claude-sonnet-4",
"timestamp": "2025-06-05T22:56:07.465Z",
"passed": true,
"duration": 1250,
"category": "language"
},
{
"test": "translation",
"prompt": "Translate \"Hello, world!\" to Spanish. Return only the translation, no explanation.",
"result": [
"¡Hola, mundo!"
],
"expected": "¡Hola, mundo!",
"model": "openai/gpt-4o-mini",
"router": "openai/gpt-4o-mini",
"timestamp": "2025-06-05T22:56:07.992Z",
"passed": true,
"duration": 521,
"category": "language"
},
{
"test": "translation",
"prompt": "Translate \"Hello, world!\" to Spanish. Return only the translation, no explanation.",
"result": [
"¡Hola, mundo!"
],
"expected": "¡Hola, mundo!",
"model": "deepseek/deepseek-r1:free",
"router": "deepseek/deepseek-r1:free",
"timestamp": "2025-06-05T22:56:10.966Z",
"passed": true,
"duration": 2969,
"category": "language"
},
{
"test": "grammar",
"prompt": "Correct the grammar in: \"I goes to the store yesterday\". Return only the corrected sentence, no explanation.",
"result": [
"I went to the store yesterday."
],
"expected": "I went to the store yesterday",
"model": "anthropic/claude-sonnet-4",
"router": "anthropic/claude-sonnet-4",
"timestamp": "2025-06-05T22:56:12.216Z",
"passed": false,
"duration": 1246,
"reason": "Expected I went to the store yesterday, but got I went to the store yesterday.",
"category": "language"
},
{
"test": "grammar",
"prompt": "Correct the grammar in: \"I goes to the store yesterday\". Return only the corrected sentence, no explanation.",
"result": [
"\"I went to the store yesterday.\""
],
"expected": "I went to the store yesterday",
"model": "openai/gpt-4o-mini",
"router": "openai/gpt-4o-mini",
"timestamp": "2025-06-05T22:56:12.844Z",
"passed": false,
"duration": 623,
"reason": "Expected I went to the store yesterday, but got \"I went to the store yesterday.\"",
"category": "language"
},
{
"test": "grammar",
"prompt": "Correct the grammar in: \"I goes to the store yesterday\". Return only the corrected sentence, no explanation.",
"result": [
"I went to the store yesterday."
],
"expected": "I went to the store yesterday",
"model": "deepseek/deepseek-r1:free",
"router": "deepseek/deepseek-r1:free",
"timestamp": "2025-06-05T22:56:17.444Z",
"passed": false,
"duration": 4594,
"reason": "Expected I went to the store yesterday, but got I went to the store yesterday.",
"category": "language"
},
{
"test": "language_detection",
"prompt": "Identify the language of: \"Bonjour, comment allez-vous?\". Return only the language name, no explanation.",
"result": [
"French"
],
"expected": "French",
"model": "anthropic/claude-sonnet-4",
"router": "anthropic/claude-sonnet-4",
"timestamp": "2025-06-05T22:56:18.557Z",
"passed": true,
"duration": 1107,
"category": "language"
},
{
"test": "language_detection",
"prompt": "Identify the language of: \"Bonjour, comment allez-vous?\". Return only the language name, no explanation.",
"result": [
"French"
],
"expected": "French",
"model": "openai/gpt-4o-mini",
"router": "openai/gpt-4o-mini",
"timestamp": "2025-06-05T22:56:19.252Z",
"passed": true,
"duration": 689,
"category": "language"
},
{
"test": "language_detection",
"prompt": "Identify the language of: \"Bonjour, comment allez-vous?\". Return only the language name, no explanation.",
"result": [
"French"
],
"expected": "French",
"model": "deepseek/deepseek-r1:free",
"router": "deepseek/deepseek-r1:free",
"timestamp": "2025-06-05T22:56:23.475Z",
"passed": true,
"duration": 4218,
"category": "language"
},
{
"test": "synonyms",
"prompt": "Provide a synonym for \"happy\". Return only the synonym, no explanation.",
"result": [
"Joyful"
],
"expected": "joyful",
"model": "anthropic/claude-sonnet-4",
"router": "anthropic/claude-sonnet-4",
"timestamp": "2025-06-05T22:56:25.120Z",
"passed": true,
"duration": 1639,
"category": "language"
},
{
"test": "synonyms",
"prompt": "Provide a synonym for \"happy\". Return only the synonym, no explanation.",
"result": [
"Joyful"
],
"expected": "joyful",
"model": "openai/gpt-4o-mini",
"router": "openai/gpt-4o-mini",
"timestamp": "2025-06-05T22:56:25.785Z",
"passed": true,
"duration": 661,
"category": "language"
},
{
"test": "synonyms",
"prompt": "Provide a synonym for \"happy\". Return only the synonym, no explanation.",
"result": [
"Joyful"
],
"expected": "joyful",
"model": "deepseek/deepseek-r1:free",
"router": "deepseek/deepseek-r1:free",
"timestamp": "2025-06-05T22:56:29.261Z",
"passed": true,
"duration": 3471,
"category": "language"
}
],
"highscores": [
@ -5224,8 +5691,8 @@
"rankings": [
{
"model": "openai/gpt-4o-mini",
"duration": 639,
"duration_secs": 0.639
"duration": 521,
"duration_secs": 0.521
},
{
"model": "openai/gpt-3.5-turbo",
@ -5244,8 +5711,8 @@
},
{
"model": "openai/gpt-4o-mini",
"duration": 641,
"duration_secs": 0.641
"duration": 623,
"duration_secs": 0.623
}
]
},
@ -5259,8 +5726,8 @@
},
{
"model": "openai/gpt-4o-mini",
"duration": 8548,
"duration_secs": 8.548
"duration": 1508,
"duration_secs": 1.508
}
]
},
@ -5269,8 +5736,8 @@
"rankings": [
{
"model": "openai/gpt-4o-mini",
"duration": 657,
"duration_secs": 0.657
"duration": 689,
"duration_secs": 0.689
},
{
"model": "openai/gpt-3.5-turbo",
@ -5289,8 +5756,8 @@
},
{
"model": "openai/gpt-4o-mini",
"duration": 622,
"duration_secs": 0.622
"duration": 661,
"duration_secs": 0.661
}
]
},
@ -5299,8 +5766,8 @@
"rankings": [
{
"model": "openai/gpt-4o",
"duration": 614,
"duration_secs": 0.614
"duration": 782,
"duration_secs": 0.782
},
{
"model": "google/gemini-2.0-flash-exp:free",
@ -5339,8 +5806,8 @@
"rankings": [
{
"model": "openai/gpt-4o-mini",
"duration": 641,
"duration_secs": 0.641
"duration": 634,
"duration_secs": 0.634
},
{
"model": "openai/gpt-3.5-turbo",
@ -5362,15 +5829,15 @@
{
"test": "multiplication",
"rankings": [
{
"model": "openai/gpt-4o-mini",
"duration": 585,
"duration_secs": 0.585
},
{
"model": "openai/gpt-3.5-turbo",
"duration": 624,
"duration_secs": 0.624
},
{
"model": "anthropic/claude-sonnet-4",
"duration": 702,
"duration_secs": 0.702
}
]
},
@ -5402,15 +5869,15 @@
{
"test": "division",
"rankings": [
{
"model": "openai/gpt-4o-mini",
"duration": 481,
"duration_secs": 0.481
},
{
"model": "openai/gpt-3.5-turbo",
"duration": 513,
"duration_secs": 0.513
},
{
"model": "openai/gpt-4o-mini",
"duration": 564,
"duration_secs": 0.564
}
]
},
@ -5438,9 +5905,9 @@
"duration_secs": 0.22
},
{
"model": "openai/gpt-4o-mini",
"duration": 4917,
"duration_secs": 4.917
"model": "anthropic/claude-sonnet-4",
"duration": 6161,
"duration_secs": 6.161
}
]
},
@ -5495,5 +5962,5 @@
]
}
],
"lastUpdated": "2025-06-05T22:53:48.765Z"
"lastUpdated": "2025-06-05T22:56:29.265Z"
}

201
packages/kbot/tests/unit/reports/basic.json
View File

@ -347,6 +347,175 @@
"duration": 5147,
"reason": "Model returned empty response",
"category": "basic"
},
{
"test": "addition",
"prompt": "add 5 and 3. Return only the number, no explanation.",
"result": [
"8"
],
"expected": "8",
"model": "anthropic/claude-sonnet-4",
"router": "anthropic/claude-sonnet-4",
"timestamp": "2025-06-05T22:54:48.966Z",
"passed": true,
"duration": 1522,
"category": "basic"
},
{
"test": "addition",
"prompt": "add 5 and 3. Return only the number, no explanation.",
"result": [
"8"
],
"expected": "8",
"model": "openai/gpt-4o-mini",
"router": "openai/gpt-4o-mini",
"timestamp": "2025-06-05T22:54:49.606Z",
"passed": true,
"duration": 634,
"category": "basic"
},
{
"test": "addition",
"prompt": "add 5 and 3. Return only the number, no explanation.",
"result": [
"8"
],
"expected": "8",
"model": "deepseek/deepseek-r1:free",
"router": "deepseek/deepseek-r1:free",
"timestamp": "2025-06-05T22:54:53.004Z",
"passed": true,
"duration": 3394,
"category": "basic"
},
{
"test": "multiplication",
"prompt": "multiply 8 and 3. Return only the number, no explanation.",
"result": [
"24"
],
"expected": "24",
"model": "anthropic/claude-sonnet-4",
"router": "anthropic/claude-sonnet-4",
"timestamp": "2025-06-05T22:54:53.710Z",
"passed": true,
"duration": 702,
"category": "basic"
},
{
"test": "multiplication",
"prompt": "multiply 8 and 3. Return only the number, no explanation.",
"result": [
"24"
],
"expected": "24",
"model": "openai/gpt-4o-mini",
"router": "openai/gpt-4o-mini",
"timestamp": "2025-06-05T22:54:56.480Z",
"passed": true,
"duration": 2765,
"category": "basic"
},
{
"test": "multiplication",
"prompt": "multiply 8 and 3. Return only the number, no explanation.",
"result": [
"The result of multiplying 8 and 3 is \\boxed{24}."
],
"expected": "24",
"model": "deepseek/deepseek-r1:free",
"router": "deepseek/deepseek-r1:free",
"timestamp": "2025-06-05T22:54:59.909Z",
"passed": false,
"duration": 3425,
"reason": "Expected 24, but got The result of multiplying 8 and 3 is \\boxed{24}.",
"category": "basic"
},
{
"test": "division",
"prompt": "divide 15 by 3. Return only the number, no explanation.",
"result": [
"5"
],
"expected": "5",
"model": "anthropic/claude-sonnet-4",
"router": "anthropic/claude-sonnet-4",
"timestamp": "2025-06-05T22:55:01.169Z",
"passed": true,
"duration": 1252,
"category": "basic"
},
{
"test": "division",
"prompt": "divide 15 by 3. Return only the number, no explanation.",
"result": [
"5"
],
"expected": "5",
"model": "openai/gpt-4o-mini",
"router": "openai/gpt-4o-mini",
"timestamp": "2025-06-05T22:55:01.737Z",
"passed": true,
"duration": 564,
"category": "basic"
},
{
"test": "division",
"prompt": "divide 15 by 3. Return only the number, no explanation.",
"result": [
"5"
],
"expected": "5",
"model": "deepseek/deepseek-r1:free",
"router": "deepseek/deepseek-r1:free",
"timestamp": "2025-06-05T22:55:06.362Z",
"passed": true,
"duration": 4619,
"category": "basic"
},
{
"test": "web_content",
"prompt": "Check if the content contains a section about Human prehistory. Reply with \"yes\" if it does, \"no\" if it does not.",
"result": [
"Looking through the table of contents in the Wikipedia article on Kenya, I can see that there is indeed a section titled \"Prehistory\" under the History section.\n\nyes"
],
"expected": "yes",
"model": "anthropic/claude-sonnet-4",
"router": "anthropic/claude-sonnet-4",
"timestamp": "2025-06-05T22:55:12.528Z",
"passed": false,
"duration": 6161,
"reason": "Expected yes, but got Looking through the table of contents in the Wikipedia article on Kenya, I can see that there is indeed a section titled \"Prehistory\" under the History section.\n\nyes",
"category": "basic"
},
{
"test": "web_content",
"prompt": "Check if the content contains a section about Human prehistory. Reply with \"yes\" if it does, \"no\" if it does not.",
"result": [
"yes"
],
"expected": "yes",
"model": "openai/gpt-4o-mini",
"router": "openai/gpt-4o-mini",
"timestamp": "2025-06-05T22:55:18.757Z",
"passed": true,
"duration": 6225,
"category": "basic"
},
{
"test": "web_content",
"prompt": "Check if the content contains a section about Human prehistory. Reply with \"yes\" if it does, \"no\" if it does not.",
"result": [],
"expected": "yes",
"model": "deepseek/deepseek-r1:free",
"router": "deepseek/deepseek-r1:free",
"timestamp": "2025-06-05T22:55:25.642Z",
"passed": false,
"duration": 6879,
"reason": "Model returned empty response",
"category": "basic"
}
],
"highscores": [
@ -355,8 +524,8 @@
"rankings": [
{
"model": "openai/gpt-4o-mini",
"duration": 641,
"duration_secs": 0.641
"duration": 634,
"duration_secs": 0.634
},
{
"model": "openai/gpt-3.5-turbo",
@ -368,30 +537,30 @@
{
"test": "multiplication",
"rankings": [
{
"model": "openai/gpt-4o-mini",
"duration": 585,
"duration_secs": 0.585
},
{
"model": "openai/gpt-3.5-turbo",
"duration": 624,
"duration_secs": 0.624
},
{
"model": "anthropic/claude-sonnet-4",
"duration": 702,
"duration_secs": 0.702
}
]
},
{
"test": "division",
"rankings": [
{
"model": "openai/gpt-4o-mini",
"duration": 481,
"duration_secs": 0.481
},
{
"model": "openai/gpt-3.5-turbo",
"duration": 513,
"duration_secs": 0.513
},
{
"model": "openai/gpt-4o-mini",
"duration": 564,
"duration_secs": 0.564
}
]
},
@ -404,12 +573,12 @@
"duration_secs": 0.22
},
{
"model": "openai/gpt-4o-mini",
"duration": 4917,
"duration_secs": 4.917
"model": "anthropic/claude-sonnet-4",
"duration": 6161,
"duration_secs": 6.161
}
]
}
],
"lastUpdated": "2025-06-05T21:19:47.545Z"
"lastUpdated": "2025-06-05T22:55:25.642Z"
}

110
packages/kbot/tests/unit/reports/basic.md
View File

@ -6,37 +6,59 @@
| Test | Model | Duration (ms) | Duration (s) |
|------|-------|--------------|--------------|
| addition | openai/gpt-4o-mini | 641 | 0.64 |
| addition | anthropic/claude-sonnet-4 | 2024 | 2.02 |
| addition | deepseek/deepseek-r1:free | 3798 | 3.80 |
| multiplication | openai/gpt-4o-mini | 585 | 0.58 |
| multiplication | anthropic/claude-sonnet-4 | 1752 | 1.75 |
| multiplication | deepseek/deepseek-r1:free | 3272 | 3.27 |
| division | openai/gpt-4o-mini | 481 | 0.48 |
| division | anthropic/claude-sonnet-4 | 1775 | 1.77 |
| division | deepseek/deepseek-r1:free | 3406 | 3.41 |
| web_content | openai/gpt-4o-mini | 4917 | 4.92 |
| web_content | deepseek/deepseek-r1:free | 5147 | 5.15 |
| web_content | anthropic/claude-sonnet-4 | 6020 | 6.02 |
| addition | openai/gpt-4o-mini | 634 | 0.63 |
| addition | anthropic/claude-sonnet-4 | 1522 | 1.52 |
| addition | deepseek/deepseek-r1:free | 3394 | 3.39 |
| multiplication | anthropic/claude-sonnet-4 | 702 | 0.70 |
| multiplication | openai/gpt-4o-mini | 2765 | 2.77 |
| multiplication | deepseek/deepseek-r1:free | 3425 | 3.42 |
| division | openai/gpt-4o-mini | 564 | 0.56 |
| division | anthropic/claude-sonnet-4 | 1252 | 1.25 |
| division | deepseek/deepseek-r1:free | 4619 | 4.62 |
| web_content | anthropic/claude-sonnet-4 | 6161 | 6.16 |
| web_content | openai/gpt-4o-mini | 6225 | 6.22 |
| web_content | deepseek/deepseek-r1:free | 6879 | 6.88 |
## Summary
- Total Tests: 12
- Passed: 11
- Failed: 1
- Success Rate: 91.67%
- Average Duration: 2818ms (2.82s)
- Passed: 9
- Failed: 3
- Success Rate: 75.00%
- Average Duration: 3179ms (3.18s)
## Failed Tests
### multiplication - deepseek/deepseek-r1:free
- Prompt: `multiply 8 and 3. Return only the number, no explanation.`
- Expected: `24`
- Actual: `The result of multiplying 8 and 3 is \boxed{24}.`
- Duration: 3425ms (3.42s)
- Reason: Expected 24, but got The result of multiplying 8 and 3 is \boxed{24}.
- Timestamp: 6/6/2025, 12:54:59 AM
### web_content - anthropic/claude-sonnet-4
- Prompt: `Check if the content contains a section about Human prehistory. Reply with "yes" if it does, "no" if it does not.`
- Expected: `yes`
- Actual: `Looking through the table of contents in the Wikipedia article on Kenya, I can see that there is indeed a section titled "Prehistory" under the History section.
yes`
- Duration: 6161ms (6.16s)
- Reason: Expected yes, but got Looking through the table of contents in the Wikipedia article on Kenya, I can see that there is indeed a section titled "Prehistory" under the History section.
yes
- Timestamp: 6/6/2025, 12:55:12 AM
### web_content - deepseek/deepseek-r1:free
- Prompt: `Check if the content contains a section about Human prehistory. Reply with "yes" if it does, "no" if it does not.`
- Expected: `yes`
- Actual: ``
- Duration: 5147ms (5.15s)
- Duration: 6879ms (6.88s)
- Reason: Model returned empty response
- Timestamp: 6/5/2025, 11:19:47 PM
- Timestamp: 6/6/2025, 12:55:25 AM
## Passed Tests
@ -45,86 +67,70 @@
- Prompt: `add 5 and 3. Return only the number, no explanation.`
- Expected: `8`
- Actual: `8`
- Duration: 2024ms (2.02s)
- Timestamp: 6/5/2025, 11:19:15 PM
- Duration: 1522ms (1.52s)
- Timestamp: 6/6/2025, 12:54:48 AM
### addition - openai/gpt-4o-mini
- Prompt: `add 5 and 3. Return only the number, no explanation.`
- Expected: `8`
- Actual: `8`
- Duration: 641ms (0.64s)
- Timestamp: 6/5/2025, 11:19:16 PM
- Duration: 634ms (0.63s)
- Timestamp: 6/6/2025, 12:54:49 AM
### addition - deepseek/deepseek-r1:free
- Prompt: `add 5 and 3. Return only the number, no explanation.`
- Expected: `8`
- Actual: `8`
- Duration: 3798ms (3.80s)
- Timestamp: 6/5/2025, 11:19:20 PM
- Duration: 3394ms (3.39s)
- Timestamp: 6/6/2025, 12:54:53 AM
### multiplication - anthropic/claude-sonnet-4
- Prompt: `multiply 8 and 3. Return only the number, no explanation.`
- Expected: `24`
- Actual: `24`
- Duration: 1752ms (1.75s)
- Timestamp: 6/5/2025, 11:19:21 PM
- Duration: 702ms (0.70s)
- Timestamp: 6/6/2025, 12:54:53 AM
### multiplication - openai/gpt-4o-mini
- Prompt: `multiply 8 and 3. Return only the number, no explanation.`
- Expected: `24`
- Actual: `24`
- Duration: 585ms (0.58s)
- Timestamp: 6/5/2025, 11:19:22 PM
### multiplication - deepseek/deepseek-r1:free
- Prompt: `multiply 8 and 3. Return only the number, no explanation.`
- Expected: `24`
- Actual: `24`
- Duration: 3272ms (3.27s)
- Timestamp: 6/5/2025, 11:19:25 PM
- Duration: 2765ms (2.77s)
- Timestamp: 6/6/2025, 12:54:56 AM
### division - anthropic/claude-sonnet-4
- Prompt: `divide 15 by 3. Return only the number, no explanation.`
- Expected: `5`
- Actual: `5`
- Duration: 1775ms (1.77s)
- Timestamp: 6/5/2025, 11:19:27 PM
- Duration: 1252ms (1.25s)
- Timestamp: 6/6/2025, 12:55:01 AM
### division - openai/gpt-4o-mini
- Prompt: `divide 15 by 3. Return only the number, no explanation.`
- Expected: `5`
- Actual: `5`
- Duration: 481ms (0.48s)
- Timestamp: 6/5/2025, 11:19:28 PM
- Duration: 564ms (0.56s)
- Timestamp: 6/6/2025, 12:55:01 AM
### division - deepseek/deepseek-r1:free
- Prompt: `divide 15 by 3. Return only the number, no explanation.`
- Expected: `5`
- Actual: `5`
- Duration: 3406ms (3.41s)
- Timestamp: 6/5/2025, 11:19:31 PM
### web_content - anthropic/claude-sonnet-4
- Prompt: `Check if the content contains a section about Human prehistory. Reply with "yes" if it does, "no" if it does not.`
- Expected: `yes`
- Actual: `yes`
- Duration: 6020ms (6.02s)
- Timestamp: 6/5/2025, 11:19:37 PM
- Duration: 4619ms (4.62s)
- Timestamp: 6/6/2025, 12:55:06 AM
### web_content - openai/gpt-4o-mini
- Prompt: `Check if the content contains a section about Human prehistory. Reply with "yes" if it does, "no" if it does not.`
- Expected: `yes`
- Actual: `yes`
- Duration: 4917ms (4.92s)
- Timestamp: 6/5/2025, 11:19:42 PM
- Duration: 6225ms (6.22s)
- Timestamp: 6/6/2025, 12:55:18 AM

63
packages/kbot/tests/unit/reports/files.json
View File

@ -1996,6 +1996,63 @@
"passed": true,
"duration": 614,
"category": "files"
},
{
"test": "file-inclusion",
"prompt": "What animals are shown in these images?",
"result": [
"{\"animals\":[\"cat\",\"fox\"]}"
],
"expected": "[\"cat\",\"fox\"]",
"model": "openai/gpt-4o",
"router": "openai/gpt-4o",
"timestamp": "2025-06-05T22:55:45.624Z",
"passed": true,
"duration": 5694,
"category": "files"
},
{
"test": "file-inclusion",
"prompt": "What is the name of the algorithm implemented in these files? Return only the name.",
"result": [
"bubbleSort"
],
"expected": "bubble sort",
"model": "openai/gpt-4o",
"router": "openai/gpt-4o",
"timestamp": "2025-06-05T22:55:46.325Z",
"passed": false,
"duration": 694,
"reason": "Expected bubble sort, but got bubbleSort",
"category": "files"
},
{
"test": "file-inclusion",
"prompt": "List all algorithms implemented in these files, as JSON array.",
"result": [
"{\"algorithms\":[\"factorial\",\"bubbleSort\"]}"
],
"expected": "[\"bubble sort\",\"factorial\"]",
"model": "openai/gpt-4o",
"router": "openai/gpt-4o",
"timestamp": "2025-06-05T22:55:47.088Z",
"passed": true,
"duration": 758,
"category": "files"
},
{
"test": "file-inclusion",
"prompt": "What is the title of the product in data.json? Return only the title.",
"result": [
"Injection Barrel"
],
"expected": "Injection Barrel",
"model": "openai/gpt-4o",
"router": "openai/gpt-4o",
"timestamp": "2025-06-05T22:55:47.875Z",
"passed": true,
"duration": 782,
"category": "files"
}
],
"highscores": [
@ -2004,8 +2061,8 @@
"rankings": [
{
"model": "openai/gpt-4o",
"duration": 614,
"duration_secs": 0.614
"duration": 782,
"duration_secs": 0.782
},
{
"model": "google/gemini-2.0-flash-exp:free",
@ -2015,5 +2072,5 @@
]
}
],
"lastUpdated": "2025-06-05T22:29:46.852Z"
"lastUpdated": "2025-06-05T22:55:47.876Z"
}

8
packages/kbot/tests/unit/reports/files.md
View File

@ -6,7 +6,7 @@
| Test | Model | Duration (ms) | Duration (s) |
|------|-------|--------------|--------------|
| file-inclusion | openai/gpt-4o | 614 | 0.61 |
| file-inclusion | openai/gpt-4o | 782 | 0.78 |
## Summary
@ -14,7 +14,7 @@
- Passed: 3
- Failed: 1
- Success Rate: 75.00%
- Average Duration: 1380ms (1.38s)
- Average Duration: 1982ms (1.98s)
## Failed Tests
@ -27,6 +27,6 @@
- Prompt: `What is the title of the product in data.json? Return only the title.`
- Expected: `Injection Barrel`
- Actual: `Injection Barrel`
- Duration: 614ms (0.61s)
- Timestamp: 6/6/2025, 12:29:46 AM
- Duration: 782ms (0.78s)
- Timestamp: 6/6/2025, 12:55:47 AM

263
packages/kbot/tests/unit/reports/language.json
View File

@ -1991,6 +1991,247 @@
"passed": true,
"duration": 1336,
"category": "language"
},
{
"test": "synonyms",
"prompt": "Provide a synonym for \"happy\". Return only the synonym, no explanation.",
"result": [
"Joyful"
],
"expected": "joyful",
"model": "openai/gpt-4o-mini",
"router": "openai/gpt-4o-mini",
"timestamp": "2025-06-05T22:54:17.429Z",
"passed": true,
"duration": 561,
"category": "language"
},
{
"test": "synonyms",
"prompt": "Provide a synonym for \"happy\". Return only the synonym, no explanation.",
"result": [
"Joyful"
],
"expected": "joyful",
"model": "deepseek/deepseek-r1:free",
"router": "deepseek/deepseek-r1:free",
"timestamp": "2025-06-05T22:54:21.005Z",
"passed": true,
"duration": 3571,
"category": "language"
},
{
"test": "summarization",
"prompt": "Summarize: \"The quick brown fox jumps over the dog\". Return only the summary, compact, no explanation.",
"result": [
"Fox jumps over dog."
],
"expected": "A fox jumps over a dog",
"model": "anthropic/claude-sonnet-4",
"router": "anthropic/claude-sonnet-4",
"timestamp": "2025-06-05T22:55:58.691Z",
"passed": true,
"duration": 1621,
"category": "language"
},
{
"test": "summarization",
"prompt": "Summarize: \"The quick brown fox jumps over the dog\". Return only the summary, compact, no explanation.",
"result": [
"A fox jumps over a dog."
],
"expected": "A fox jumps over a dog",
"model": "openai/gpt-4o-mini",
"router": "openai/gpt-4o-mini",
"timestamp": "2025-06-05T22:56:00.205Z",
"passed": true,
"duration": 1508,
"category": "language"
},
{
"test": "summarization",
"prompt": "Summarize: \"The quick brown fox jumps over the dog\". Return only the summary, compact, no explanation.",
"result": [
"A quick brown fox leaps over a dog."
],
"expected": "A fox jumps over a dog",
"model": "deepseek/deepseek-r1:free",
"router": "deepseek/deepseek-r1:free",
"timestamp": "2025-06-05T22:56:06.210Z",
"passed": true,
"duration": 6000,
"category": "language"
},
{
"test": "translation",
"prompt": "Translate \"Hello, world!\" to Spanish. Return only the translation, no explanation.",
"result": [
"¡Hola, mundo!"
],
"expected": "¡Hola, mundo!",
"model": "anthropic/claude-sonnet-4",
"router": "anthropic/claude-sonnet-4",
"timestamp": "2025-06-05T22:56:07.465Z",
"passed": true,
"duration": 1250,
"category": "language"
},
{
"test": "translation",
"prompt": "Translate \"Hello, world!\" to Spanish. Return only the translation, no explanation.",
"result": [
"¡Hola, mundo!"
],
"expected": "¡Hola, mundo!",
"model": "openai/gpt-4o-mini",
"router": "openai/gpt-4o-mini",
"timestamp": "2025-06-05T22:56:07.992Z",
"passed": true,
"duration": 521,
"category": "language"
},
{
"test": "translation",
"prompt": "Translate \"Hello, world!\" to Spanish. Return only the translation, no explanation.",
"result": [
"¡Hola, mundo!"
],
"expected": "¡Hola, mundo!",
"model": "deepseek/deepseek-r1:free",
"router": "deepseek/deepseek-r1:free",
"timestamp": "2025-06-05T22:56:10.966Z",
"passed": true,
"duration": 2969,
"category": "language"
},
{
"test": "grammar",
"prompt": "Correct the grammar in: \"I goes to the store yesterday\". Return only the corrected sentence, no explanation.",
"result": [
"I went to the store yesterday."
],
"expected": "I went to the store yesterday",
"model": "anthropic/claude-sonnet-4",
"router": "anthropic/claude-sonnet-4",
"timestamp": "2025-06-05T22:56:12.216Z",
"passed": false,
"duration": 1246,
"reason": "Expected I went to the store yesterday, but got I went to the store yesterday.",
"category": "language"
},
{
"test": "grammar",
"prompt": "Correct the grammar in: \"I goes to the store yesterday\". Return only the corrected sentence, no explanation.",
"result": [
"\"I went to the store yesterday.\""
],
"expected": "I went to the store yesterday",
"model": "openai/gpt-4o-mini",
"router": "openai/gpt-4o-mini",
"timestamp": "2025-06-05T22:56:12.844Z",
"passed": false,
"duration": 623,
"reason": "Expected I went to the store yesterday, but got \"I went to the store yesterday.\"",
"category": "language"
},
{
"test": "grammar",
"prompt": "Correct the grammar in: \"I goes to the store yesterday\". Return only the corrected sentence, no explanation.",
"result": [
"I went to the store yesterday."
],
"expected": "I went to the store yesterday",
"model": "deepseek/deepseek-r1:free",
"router": "deepseek/deepseek-r1:free",
"timestamp": "2025-06-05T22:56:17.444Z",
"passed": false,
"duration": 4594,
"reason": "Expected I went to the store yesterday, but got I went to the store yesterday.",
"category": "language"
},
{
"test": "language_detection",
"prompt": "Identify the language of: \"Bonjour, comment allez-vous?\". Return only the language name, no explanation.",
"result": [
"French"
],
"expected": "French",
"model": "anthropic/claude-sonnet-4",
"router": "anthropic/claude-sonnet-4",
"timestamp": "2025-06-05T22:56:18.557Z",
"passed": true,
"duration": 1107,
"category": "language"
},
{
"test": "language_detection",
"prompt": "Identify the language of: \"Bonjour, comment allez-vous?\". Return only the language name, no explanation.",
"result": [
"French"
],
"expected": "French",
"model": "openai/gpt-4o-mini",
"router": "openai/gpt-4o-mini",
"timestamp": "2025-06-05T22:56:19.252Z",
"passed": true,
"duration": 689,
"category": "language"
},
{
"test": "language_detection",
"prompt": "Identify the language of: \"Bonjour, comment allez-vous?\". Return only the language name, no explanation.",
"result": [
"French"
],
"expected": "French",
"model": "deepseek/deepseek-r1:free",
"router": "deepseek/deepseek-r1:free",
"timestamp": "2025-06-05T22:56:23.475Z",
"passed": true,
"duration": 4218,
"category": "language"
},
{
"test": "synonyms",
"prompt": "Provide a synonym for \"happy\". Return only the synonym, no explanation.",
"result": [
"Joyful"
],
"expected": "joyful",
"model": "anthropic/claude-sonnet-4",
"router": "anthropic/claude-sonnet-4",
"timestamp": "2025-06-05T22:56:25.120Z",
"passed": true,
"duration": 1639,
"category": "language"
},
{
"test": "synonyms",
"prompt": "Provide a synonym for \"happy\". Return only the synonym, no explanation.",
"result": [
"Joyful"
],
"expected": "joyful",
"model": "openai/gpt-4o-mini",
"router": "openai/gpt-4o-mini",
"timestamp": "2025-06-05T22:56:25.785Z",
"passed": true,
"duration": 661,
"category": "language"
},
{
"test": "synonyms",
"prompt": "Provide a synonym for \"happy\". Return only the synonym, no explanation.",
"result": [
"Joyful"
],
"expected": "joyful",
"model": "deepseek/deepseek-r1:free",
"router": "deepseek/deepseek-r1:free",
"timestamp": "2025-06-05T22:56:29.261Z",
"passed": true,
"duration": 3471,
"category": "language"
}
],
"highscores": [
@ -1999,8 +2240,8 @@
"rankings": [
{
"model": "openai/gpt-4o-mini",
"duration": 639,
"duration_secs": 0.639
"duration": 521,
"duration_secs": 0.521
},
{
"model": "openai/gpt-3.5-turbo",
@ -2019,8 +2260,8 @@
},
{
"model": "openai/gpt-4o-mini",
"duration": 641,
"duration_secs": 0.641
"duration": 623,
"duration_secs": 0.623
}
]
},
@ -2034,8 +2275,8 @@
},
{
"model": "openai/gpt-4o-mini",
"duration": 8548,
"duration_secs": 8.548
"duration": 1508,
"duration_secs": 1.508
}
]
},
@ -2044,8 +2285,8 @@
"rankings": [
{
"model": "openai/gpt-4o-mini",
"duration": 657,
"duration_secs": 0.657
"duration": 689,
"duration_secs": 0.689
},
{
"model": "openai/gpt-3.5-turbo",
@ -2064,11 +2305,11 @@
},
{
"model": "openai/gpt-4o-mini",
"duration": 622,
"duration_secs": 0.622
"duration": 661,
"duration_secs": 0.661
}
]
}
],
"lastUpdated": "2025-06-05T22:53:48.763Z"
"lastUpdated": "2025-06-05T22:56:29.262Z"
}

111
packages/kbot/tests/unit/reports/language.md
View File

@ -6,29 +6,29 @@
| Test | Model | Duration (ms) | Duration (s) |
|------|-------|--------------|--------------|
| translation | openai/gpt-4o-mini | 1451 | 1.45 |
| translation | anthropic/claude-sonnet-4 | 1560 | 1.56 |
| translation | deepseek/deepseek-r1:free | 5434 | 5.43 |
| grammar | openai/gpt-4o-mini | 695 | 0.69 |
| grammar | anthropic/claude-sonnet-4 | 1201 | 1.20 |
| grammar | deepseek/deepseek-r1:free | 3395 | 3.40 |
| summarization | openai/gpt-4o-mini | 692 | 0.69 |
| summarization | anthropic/claude-sonnet-4 | 1304 | 1.30 |
| summarization | deepseek/deepseek-r1:free | 14038 | 14.04 |
| language_detection | openai/gpt-4o-mini | 459 | 0.46 |
| language_detection | anthropic/claude-sonnet-4 | 1137 | 1.14 |
| language_detection | deepseek/deepseek-r1:free | 3924 | 3.92 |
| synonyms | openai/gpt-4o-mini | 622 | 0.62 |
| synonyms | anthropic/claude-sonnet-4 | 1251 | 1.25 |
| synonyms | deepseek/deepseek-r1:free | 3836 | 3.84 |
| summarization | openai/gpt-4o-mini | 1508 | 1.51 |
| summarization | anthropic/claude-sonnet-4 | 1621 | 1.62 |
| summarization | deepseek/deepseek-r1:free | 6000 | 6.00 |
| translation | openai/gpt-4o-mini | 521 | 0.52 |
| translation | anthropic/claude-sonnet-4 | 1250 | 1.25 |
| translation | deepseek/deepseek-r1:free | 2969 | 2.97 |
| grammar | openai/gpt-4o-mini | 623 | 0.62 |
| grammar | anthropic/claude-sonnet-4 | 1246 | 1.25 |
| grammar | deepseek/deepseek-r1:free | 4594 | 4.59 |
| language_detection | openai/gpt-4o-mini | 689 | 0.69 |
| language_detection | anthropic/claude-sonnet-4 | 1107 | 1.11 |
| language_detection | deepseek/deepseek-r1:free | 4218 | 4.22 |
| synonyms | openai/gpt-4o-mini | 661 | 0.66 |
| synonyms | anthropic/claude-sonnet-4 | 1639 | 1.64 |
| synonyms | deepseek/deepseek-r1:free | 3471 | 3.47 |
## Summary
- Total Tests: 15
- Passed: 9
- Failed: 6
- Success Rate: 60.00%
- Average Duration: 2733ms (2.73s)
- Passed: 12
- Failed: 3
- Success Rate: 80.00%
- Average Duration: 2141ms (2.14s)
## Failed Tests
@ -37,126 +37,123 @@
- Prompt: `Correct the grammar in: "I goes to the store yesterday". Return only the corrected sentence, no explanation.`
- Expected: `I went to the store yesterday`
- Actual: `I went to the store yesterday.`
- Duration: 1201ms (1.20s)
- Duration: 1246ms (1.25s)
- Reason: Expected I went to the store yesterday, but got I went to the store yesterday.
- Timestamp: 6/6/2025, 12:30:29 AM
- Timestamp: 6/6/2025, 12:56:12 AM
### grammar - openai/gpt-4o-mini
- Prompt: `Correct the grammar in: "I goes to the store yesterday". Return only the corrected sentence, no explanation.`
- Expected: `I went to the store yesterday`
- Actual: `"I went to the store yesterday."`
- Duration: 695ms (0.69s)
- Duration: 623ms (0.62s)
- Reason: Expected I went to the store yesterday, but got "I went to the store yesterday."
- Timestamp: 6/6/2025, 12:30:30 AM
- Timestamp: 6/6/2025, 12:56:12 AM
### grammar - deepseek/deepseek-r1:free
- Prompt: `Correct the grammar in: "I goes to the store yesterday". Return only the corrected sentence, no explanation.`
- Expected: `I went to the store yesterday`
- Actual: `I went to the store yesterday.`
- Duration: 3395ms (3.40s)
- Duration: 4594ms (4.59s)
- Reason: Expected I went to the store yesterday, but got I went to the store yesterday.
- Timestamp: 6/6/2025, 12:30:33 AM
- Timestamp: 6/6/2025, 12:56:17 AM
## Passed Tests
### summarization - anthropic/claude-sonnet-4
- Prompt: `Summarize: "The quick brown fox jumps over the dog". Return only the summary, compact, no explanation.`
- Expected: `A fox jumps over a dog`
- Actual: `A brown fox leaps over a dog.`
- Duration: 1304ms (1.30s)
- Reason: Expected A fox jumps over a dog, but got A brown fox leaps over a dog.
- Timestamp: 6/6/2025, 12:30:34 AM
- Actual: `Fox jumps over dog.`
- Duration: 1621ms (1.62s)
- Timestamp: 6/6/2025, 12:55:58 AM
### summarization - openai/gpt-4o-mini
- Prompt: `Summarize: "The quick brown fox jumps over the dog". Return only the summary, compact, no explanation.`
- Expected: `A fox jumps over a dog`
- Actual: `A fox jumps over a dog.`
- Duration: 692ms (0.69s)
- Reason: Expected A fox jumps over a dog, but got A fox jumps over a dog.
- Timestamp: 6/6/2025, 12:30:35 AM
- Duration: 1508ms (1.51s)
- Timestamp: 6/6/2025, 12:56:00 AM
### summarization - deepseek/deepseek-r1:free
- Prompt: `Summarize: "The quick brown fox jumps over the dog". Return only the summary, compact, no explanation.`
- Expected: `A fox jumps over a dog`
- Actual: `"A quick brown fox leaps over a dog."`
- Duration: 14038ms (14.04s)
- Reason: Expected A fox jumps over a dog, but got "A quick brown fox leaps over a dog."
- Timestamp: 6/6/2025, 12:30:49 AM
## Passed Tests
- Actual: `A quick brown fox leaps over a dog.`
- Duration: 6000ms (6.00s)
- Timestamp: 6/6/2025, 12:56:06 AM
### translation - anthropic/claude-sonnet-4
- Prompt: `Translate "Hello, world!" to Spanish. Return only the translation, no explanation.`
- Expected: `¡Hola, mundo!`
- Actual: `¡Hola, mundo!`
- Duration: 1560ms (1.56s)
- Timestamp: 6/6/2025, 12:30:21 AM
- Duration: 1250ms (1.25s)
- Timestamp: 6/6/2025, 12:56:07 AM
### translation - openai/gpt-4o-mini
- Prompt: `Translate "Hello, world!" to Spanish. Return only the translation, no explanation.`
- Expected: `¡Hola, mundo!`
- Actual: `¡Hola, mundo!`
- Duration: 1451ms (1.45s)
- Timestamp: 6/6/2025, 12:30:22 AM
- Duration: 521ms (0.52s)
- Timestamp: 6/6/2025, 12:56:07 AM
### translation - deepseek/deepseek-r1:free
- Prompt: `Translate "Hello, world!" to Spanish. Return only the translation, no explanation.`
- Expected: `¡Hola, mundo!`
- Actual: `¡Hola, mundo!`
- Duration: 5434ms (5.43s)
- Timestamp: 6/6/2025, 12:30:28 AM
- Duration: 2969ms (2.97s)
- Timestamp: 6/6/2025, 12:56:10 AM
### language_detection - anthropic/claude-sonnet-4
- Prompt: `Identify the language of: "Bonjour, comment allez-vous?". Return only the language name, no explanation.`
- Expected: `French`
- Actual: `French`
- Duration: 1137ms (1.14s)
- Timestamp: 6/6/2025, 12:30:50 AM
- Duration: 1107ms (1.11s)
- Timestamp: 6/6/2025, 12:56:18 AM
### language_detection - openai/gpt-4o-mini
- Prompt: `Identify the language of: "Bonjour, comment allez-vous?". Return only the language name, no explanation.`
- Expected: `French`
- Actual: `French`
- Duration: 459ms (0.46s)
- Timestamp: 6/6/2025, 12:30:51 AM
- Duration: 689ms (0.69s)
- Timestamp: 6/6/2025, 12:56:19 AM
### language_detection - deepseek/deepseek-r1:free
- Prompt: `Identify the language of: "Bonjour, comment allez-vous?". Return only the language name, no explanation.`
- Expected: `French`
- Actual: `French`
- Duration: 3924ms (3.92s)
- Timestamp: 6/6/2025, 12:30:55 AM
- Duration: 4218ms (4.22s)
- Timestamp: 6/6/2025, 12:56:23 AM
### synonyms - anthropic/claude-sonnet-4
- Prompt: `Provide a synonym for "happy". Return only the synonym, no explanation.`
- Expected: `joyful`
- Actual: `Joyful`
- Duration: 1251ms (1.25s)
- Timestamp: 6/6/2025, 12:30:56 AM
- Duration: 1639ms (1.64s)
- Timestamp: 6/6/2025, 12:56:25 AM
### synonyms - openai/gpt-4o-mini
- Prompt: `Provide a synonym for "happy". Return only the synonym, no explanation.`
- Expected: `joyful`
- Actual: `Joyful`
- Duration: 622ms (0.62s)
- Timestamp: 6/6/2025, 12:30:57 AM
- Duration: 661ms (0.66s)
- Timestamp: 6/6/2025, 12:56:25 AM
### synonyms - deepseek/deepseek-r1:free
- Prompt: `Provide a synonym for "happy". Return only the synonym, no explanation.`
- Expected: `joyful`
- Actual: `joyful`
- Duration: 3836ms (3.84s)
- Timestamp: 6/6/2025, 12:31:00 AM
- Actual: `Joyful`
- Duration: 3471ms (3.47s)
- Timestamp: 6/6/2025, 12:56:29 AM