Benchmark

LiveCodeBench

Coding

Categories
coding
Openness
unknown
Source
artificial_analysis
Reported scores
343

Reported scores

artificial_analysis

ModelOrganizationReported valueReportedEvidence
Apriel-v1.5-15B-ThinkerServiceNow0.7280423280423282025-09-30evidence
Apriel-v1.6-15B-ThinkerServiceNow0.8074074074074072025-11-25evidence
Claude 2.0Anthropic0.1714285714285712023-07-11evidence
Claude 2.1Anthropic0.1947089947089952023-11-21evidence
Claude 3 HaikuAnthropic0.1544973544973542024-03-04evidence
Claude 3 OpusAnthropic0.2793650793650792024-03-04evidence
Claude 3 SonnetAnthropic0.1746031746031752024-03-04evidence
Claude 3.5 HaikuAnthropic0.3142857142857142024-10-22evidence
Claude 3.5 Sonnet (Oct '24)Anthropic0.3809523809523812024-10-22evidence
Claude 3.7 Sonnet (Non-reasoning)Anthropic0.3936507936507942025-02-24evidence
Claude 3.7 Sonnet (Reasoning)Anthropic0.4730158730158732025-02-24evidence
Claude 4 Opus (Non-reasoning)Anthropic0.5417989417989422025-05-22evidence
Claude 4 Opus (Reasoning)Anthropic0.6359788359788362025-05-22evidence
Claude 4 Sonnet (Non-reasoning)Anthropic0.4486772486772492025-05-22evidence
Claude 4 Sonnet (Reasoning)Anthropic0.6550264550264552025-05-22evidence
Claude 4.1 Opus (Reasoning)Anthropic0.65354482762025-08-05evidence
Claude 4.5 Haiku (Non-reasoning)Anthropic0.5111111111111112025-10-15evidence
Claude 4.5 Haiku (Reasoning)Anthropic0.6148148148148152025-10-15evidence
Claude 4.5 Sonnet (Non-reasoning)Anthropic0.590476190476192025-09-29evidence
Claude 4.5 Sonnet (Reasoning)Anthropic0.7142857142857142025-09-29evidence
Claude InstantAnthropic0.1089947089947092023-03-14evidence
Claude Opus 4.5 (Non-reasoning)Anthropic0.7375661375661382025-11-24evidence
Claude Opus 4.5 (Reasoning)Anthropic0.8708994708994712025-11-24evidence
Cogito v2.1 (Reasoning)Deep Cogito0.6878306878306882025-11-18evidence
Command ACohere0.2867724867724872025-03-13evidence
Command-R (Mar '24)Cohere0.04761904761904762024-03-12evidence
Command-R+ (Apr '24)Cohere0.1216931216931222024-04-04evidence
DBRX InstructDatabricks0.09312169312169312024-03-27evidence
DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)Nous Research0.08465608465608472025-02-13evidence
DeepHermes 3 - Mistral 24B Preview (Non-reasoning)Nous Research0.1947089947089952025-03-13evidence
DeepSeek Coder V2 Lite InstructDeepSeek0.1576719576719582024-06-17evidence
DeepSeek R1 (Jan '25)DeepSeek0.6169312169312172025-01-20evidence
DeepSeek R1 0528 (May '25)DeepSeek0.770370370370372025-05-28evidence
DeepSeek R1 0528 Qwen3 8BDeepSeek0.5132275132275132025-05-29evidence
DeepSeek R1 Distill Llama 70BDeepSeek0.2656084656084662025-01-20evidence
DeepSeek R1 Distill Llama 8BDeepSeek0.2328042328042332025-01-20evidence
DeepSeek R1 Distill Qwen 1.5BDeepSeek0.06984126984126982025-01-20evidence
DeepSeek R1 Distill Qwen 14BDeepSeek0.3756613756613762025-01-20evidence
DeepSeek R1 Distill Qwen 32BDeepSeek0.269841269841272025-01-20evidence
DeepSeek V3 (Dec '24)DeepSeek0.3587301587301592024-12-26evidence
DeepSeek V3 0324DeepSeek0.4052910052910052025-03-25evidence
DeepSeek V3.1 (Non-reasoning)DeepSeek0.5767195767195772025-08-21evidence
DeepSeek V3.1 (Reasoning)DeepSeek0.7841269841269842025-08-21evidence
DeepSeek V3.1 Terminus (Non-reasoning)DeepSeek0.5291005291005292025-09-22evidence
DeepSeek V3.1 Terminus (Reasoning)DeepSeek0.7978835978835982025-09-22evidence
DeepSeek V3.2 (Non-reasoning)DeepSeek0.5925925925925932025-12-01evidence
DeepSeek V3.2 (Reasoning)DeepSeek0.8624338624338622025-12-01evidence
DeepSeek V3.2 Exp (Non-reasoning)DeepSeek0.5544973544973542025-09-29evidence
DeepSeek V3.2 Exp (Reasoning)DeepSeek0.7894179894179892025-09-29evidence
DeepSeek V3.2 SpecialeDeepSeek0.8962962962962962025-12-01evidence
Devstral 2Mistral0.4476190476190482025-12-09evidence
Devstral MediumMistral0.3365079365079372025-07-10evidence
Devstral Small (Jul '25)Mistral0.2539682539682542025-07-10evidence
Devstral Small (May '25)Mistral0.2582010582010582025-05-21evidence
Devstral Small 2Mistral0.3481481481481482025-12-09evidence
Doubao Seed CodeByteDance Seed0.7661375661375662025-11-11evidence
ERNIE 4.5 300B A47BBaidu0.4666666666666672025-06-30evidence
ERNIE 5.0 Thinking PreviewBaidu0.8116402116402112025-11-13evidence
Exaone 4.0 1.2B (Non-reasoning)LG AI Research0.2931216931216932025-07-15evidence
Exaone 4.0 1.2B (Reasoning)LG AI Research0.5164021164021162025-07-15evidence
EXAONE 4.0 32B (Non-reasoning)LG AI Research0.4719576719576722025-07-15evidence
EXAONE 4.0 32B (Reasoning)LG AI Research0.7470899470899472025-07-15evidence
Falcon-H1R-7BTII UAE0.7238095238095242026-01-04evidence
Gemini 1.0 ProGoogle0.1164021164021162023-12-06evidence
Gemini 1.5 Flash (May '24)Google0.1957671957671962024-05-14evidence
Gemini 1.5 Flash (Sep '24)Google0.2730158730158732024-09-24evidence
Gemini 1.5 Flash-8BGoogle0.2169312169312172024-10-03evidence
Gemini 1.5 Pro (May '24)Google0.2444444444444442024-05-15evidence
Gemini 1.5 Pro (Sep '24)Google0.3164021164021162024-09-24evidence
Gemini 2.0 Flash (experimental)Google0.209523809523812024-12-11evidence
Gemini 2.0 Flash (Feb '25)Google0.3343915343915342025-02-05evidence
Gemini 2.0 Flash Thinking Experimental (Jan '25)Google0.3206349206349212025-01-21evidence
Gemini 2.0 Flash-Lite (Feb '25)Google0.1851851851851852025-02-25evidence
Gemini 2.0 Flash-Lite (Preview)Google0.1788359788359792025-02-05evidence
Gemini 2.0 Pro Experimental (Feb '25)Google0.3470899470899472025-02-05evidence
Gemini 2.5 Flash (Non-reasoning)Google0.4952380952380952025-05-20evidence
Gemini 2.5 Flash (Reasoning)Google0.6952380952380952025-05-20evidence
Gemini 2.5 Flash Preview (Non-reasoning)Google0.4063492063492062025-04-17evidence
Gemini 2.5 Flash Preview (Reasoning)Google0.5047619047619052025-04-17evidence
Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)Google0.6253968253968252025-09-25evidence
Gemini 2.5 Flash Preview (Sep '25) (Reasoning)Google0.7132275132275132025-09-25evidence
Gemini 2.5 Flash-Lite (Non-reasoning)Google0.42025-06-17evidence
Gemini 2.5 Flash-Lite (Reasoning)Google0.5925925925925932025-06-17evidence
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)Google0.6412698412698412025-09-25evidence
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)Google0.6878306878306882025-09-08evidence
Gemini 2.5 ProGoogle0.8010582010582012025-06-05evidence
Gemini 2.5 Pro Preview (Mar' 25)Google0.7777777777777782025-03-25evidence
Gemini 2.5 Pro Preview (May' 25)Google0.770370370370372025-05-06evidence
Gemini 3 Flash Preview (Non-reasoning)Google0.7968253968253972025-12-17evidence
Gemini 3 Flash Preview (Reasoning)Google0.9079365079365082025-12-17evidence
Gemini 3 Pro Preview (high)Google0.9174603174603172025-11-18evidence
Gemini 3 Pro Preview (low)Google0.8571428571428572025-11-18evidence
Gemma 3 12B InstructGoogle0.1365079365079362025-03-12evidence
Gemma 3 1B InstructGoogle0.01693121693121692025-03-13evidence
Gemma 3 270MGoogle0.003174603174603172025-08-14evidence
Gemma 3 27B InstructGoogle0.1365079365079362025-03-12evidence
Gemma 3 4B InstructGoogle0.1121693121693122025-03-12evidence
Gemma 3n E2B InstructGoogle0.09523809523809522025-06-26evidence
Gemma 3n E4B InstructGoogle0.1460317460317462025-06-26evidence
Gemma 3n E4B Instruct Preview (May '25)Google0.1375661375661382025-05-20evidence
GLM-4.5 (Reasoning)Z.ai0.7375661375661382025-07-28evidence
GLM-4.5-AirZ.ai0.6835978835978842025-07-28evidence
GLM-4.5V (Non-reasoning)Z.ai0.3523809523809522025-08-11evidence
GLM-4.5V (Reasoning)Z.ai0.6042328042328042025-08-11evidence
GLM-4.6 (Non-reasoning)Z.ai0.5608465608465612025-09-30evidence
GLM-4.6 (Reasoning)Z.ai0.6952380952380952025-09-30evidence
GLM-4.6V (Non-reasoning)Z.ai0.4105820105820112025-12-08evidence
GLM-4.6V (Reasoning)Z.ai0.159788359788362025-12-08evidence
GLM-4.7 (Non-reasoning)Z.ai0.5619047619047622025-12-22evidence
GLM-4.7 (Reasoning)Z.ai0.8941798941798942025-12-22evidence
GPT-4 TurboOpenAI0.2910052910052912023-11-06evidence
GPT-4.1OpenAI0.4571428571428572025-04-14evidence
GPT-4.1 miniOpenAI0.4825396825396832025-04-14evidence
GPT-4.1 nanoOpenAI0.3259259259259262025-04-14evidence
GPT-4o (Aug '24)OpenAI0.3174603174603172024-08-06evidence
GPT-4o (March 2025, chatgpt-4o-latest)OpenAI0.4253968253968252025-03-27evidence
GPT-4o (May '24)OpenAI0.3343915343915342024-05-13evidence
GPT-4o (Nov '24)OpenAI0.3089947089947092024-11-20evidence
GPT-4o miniOpenAI0.2338624338624342024-07-18evidence
GPT-5 (ChatGPT)OpenAI0.5428571428571432025-08-07evidence
GPT-5 (high)OpenAI0.8455026455026462025-08-07evidence
GPT-5 (low)OpenAI0.7629629629629632025-08-07evidence
GPT-5 (medium)OpenAI0.7026455026455032025-08-07evidence
GPT-5 (minimal)OpenAI0.5576719576719582025-08-07evidence
GPT-5 Codex (high)OpenAI0.840211640211642025-09-23evidence
GPT-5 mini (high)OpenAI0.8380952380952382025-08-07evidence
GPT-5 mini (medium)OpenAI0.6920634920634922025-08-07evidence
GPT-5 mini (minimal)OpenAI0.5449735449735452025-08-07evidence
GPT-5 nano (high)OpenAI0.7894179894179892025-08-07evidence
GPT-5 nano (medium)OpenAI0.7629629629629632025-08-07evidence
GPT-5 nano (minimal)OpenAI0.469841269841272025-08-07evidence
GPT-5.1 (high)OpenAI0.8677248677248682025-11-13evidence
GPT-5.1 (Non-reasoning)OpenAI0.4941798941798942025-11-13evidence
GPT-5.1 Codex (high)OpenAI0.8486772486772492025-11-13evidence
GPT-5.1 Codex mini (high)OpenAI0.8359788359788362025-11-13evidence
GPT-5.2 (medium)OpenAI0.8941798941798942025-12-11evidence
GPT-5.2 (Non-reasoning)OpenAI0.6687830687830692025-12-11evidence
GPT-5.2 (xhigh)OpenAI0.8888888888888892025-12-11evidence
gpt-oss-120b (high)OpenAI0.8783068783068782025-08-05evidence
gpt-oss-120b (low)OpenAI0.7068783068783072025-08-05evidence
gpt-oss-20b (high)OpenAI0.7767195767195772025-08-05evidence
gpt-oss-20b (low)OpenAI0.6518518518518522025-08-05evidence
Granite 3.3 8B (Non-reasoning)IBM0.1269841269841272025-04-16evidence
Granite 4.0 1BIBM0.04656084656084662025-10-28evidence
Granite 4.0 350MIBM0.02433862433862432025-10-28evidence
Granite 4.0 H 1BIBM0.1153439153439152025-10-28evidence
Granite 4.0 H 350MIBM0.0190476190476192025-10-28evidence
Granite 4.0 H SmallIBM0.2507936507936512025-09-22evidence
Granite 4.0 MicroIBM0.179894179894182025-09-22evidence
Grok 2 (Dec '24)xAI0.2666666666666672024-12-12evidence
Grok 3xAI0.4253968253968252025-02-19evidence
Grok 3 mini Reasoning (high)xAI0.6962962962962962025-02-19evidence
Grok 4xAI0.8190476190476192025-07-10evidence
Grok 4 Fast (Non-reasoning)xAI0.4010582010582012025-09-19evidence
Grok 4 Fast (Reasoning)xAI0.8317460317460322025-09-19evidence
Grok 4.1 Fast (Non-reasoning)xAI0.3989417989417992025-11-19evidence
Grok 4.1 Fast (Reasoning)xAI0.8222222222222222025-11-19evidence
Grok BetaxAI0.2412698412698412024-08-13evidence
Grok Code Fast 1xAI0.6571428571428572025-08-28evidence
Hermes 3 - Llama-3.1 70BNous Research0.1883597883597882024-08-15evidence
Hermes 4 - Llama-3.1 405B (Non-reasoning)Nous Research0.5460317460317462025-08-27evidence
Hermes 4 - Llama-3.1 405B (Reasoning)Nous Research0.6857142857142862025-08-27evidence
Hermes 4 - Llama-3.1 70B (Non-reasoning)Nous Research0.2687830687830692025-08-27evidence
Hermes 4 - Llama-3.1 70B (Reasoning)Nous Research0.6529100529100532025-08-27evidence
HyperCLOVA X SEED Think (32B)Naver0.6285714285714292025-12-26evidence
INTELLECT-3Prime Intellect0.7767195767195772025-11-27evidence
Jamba 1.5 LargeAI21 Labs0.1428571428571432024-08-22evidence
Jamba 1.5 MiniAI21 Labs0.06243386243386242024-08-22evidence
Jamba 1.6 LargeAI21 Labs0.1724867724867722025-03-06evidence
Jamba 1.6 MiniAI21 Labs0.07089947089947092025-03-06evidence
Jamba 1.7 LargeAI21 Labs0.1809523809523812025-07-07evidence
Jamba 1.7 MiniAI21 Labs0.06137566137566142025-07-07evidence
Jamba Reasoning 3BAI21 Labs0.209523809523812025-10-08evidence
K-EXAONE (Reasoning)LG AI Research0.7682539682539682025-12-31evidence
K2-V2 (high)MBZUAI Institute of Foundation Models0.6941798941798942025-12-05evidence
K2-V2 (low)MBZUAI Institute of Foundation Models0.3925925925925932025-12-05evidence
K2-V2 (medium)MBZUAI Institute of Foundation Models0.5407407407407412025-12-05evidence
KAT-Coder-Pro V1KwaiKAT0.7470899470899472025-11-11evidence
Kimi K2Moonshot AI0.5555555555555562025-07-11evidence
Kimi K2 0905Moonshot AI0.609523809523812025-09-05evidence
Kimi K2 ThinkingMoonshot AI0.8529100529100532025-11-06evidence
Kimi Linear 48B A3B InstructMoonshot AI0.3777777777777782025-10-30evidence
LFM 40BLiquid AI0.09629629629629632024-09-30evidence
LFM2 1.2BLiquid AI0.02010582010582012025-07-10evidence
LFM2 2.6BLiquid AI0.08148148148148152025-09-23evidence
LFM2 8B A1BLiquid AI0.1513227513227512025-10-07evidence
Ling-1TInclusionAI0.6772486772486772025-10-08evidence
Ling-flash-2.0InclusionAI0.589417989417992025-09-17evidence
Ling-mini-2.0InclusionAI0.4285714285714292025-09-09evidence
Llama 2 Chat 13BMeta0.09841269841269842023-07-18evidence
Llama 2 Chat 70BMeta0.09841269841269842023-07-18evidence
Llama 2 Chat 7BMeta0.002116402116402122023-07-18evidence
Llama 3 Instruct 70BMeta0.1978835978835982024-04-18evidence
Llama 3 Instruct 8BMeta0.09629629629629632024-04-18evidence
Llama 3.1 Instruct 405BMeta0.3047619047619052024-07-23evidence
Llama 3.1 Instruct 70BMeta0.2317460317460322024-07-23evidence
Llama 3.1 Instruct 8BMeta0.1164021164021162024-07-23evidence
Llama 3.1 Nemotron Instruct 70BNVIDIA0.1693121693121692024-10-15evidence
Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)NVIDIA0.4931216931216932025-05-20evidence
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)NVIDIA0.6412698412698412025-04-07evidence
Llama 3.1 Tulu3 405BAllen Institute for AI0.2910052910052912025-01-30evidence
Llama 3.2 Instruct 11B (Vision)Meta0.110052910052912024-09-25evidence
Llama 3.2 Instruct 1BMeta0.0190476190476192024-09-25evidence
Llama 3.2 Instruct 3BMeta0.08253968253968252024-09-25evidence
Llama 3.2 Instruct 90B (Vision)Meta0.2137566137566142024-09-25evidence
Llama 3.3 Instruct 70BMeta0.2878306878306882024-12-06evidence
Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)NVIDIA0.280423280423282025-03-18evidence
Llama 3.3 Nemotron Super 49B v1 (Reasoning)NVIDIA0.2772486772486772025-03-18evidence
Llama 4 MaverickMeta0.3968253968253972025-04-05evidence
Llama 4 ScoutMeta0.2994708994708992025-04-05evidence
Llama Nemotron Super 49B v1.5 (Non-reasoning)NVIDIA0.289947089947092025-07-25evidence
Llama Nemotron Super 49B v1.5 (Reasoning)NVIDIA0.7365079365079372025-07-25evidence
Magistral Medium 1Mistral0.5269841269841272025-06-10evidence
Magistral Medium 1.2Mistral0.750264550264552025-09-18evidence
Magistral Small 1Mistral0.5142857142857142025-06-10evidence
Magistral Small 1.2Mistral0.7227513227513232025-09-17evidence
Mi:dm K 2.5 ProKorea Telecom0.6560846560846562025-12-11evidence
Mi:dm K 2.5 Pro PreviewKorea Telecom0.5756613756613762025-12-11evidence
MiMo-V2-Flash (Non-reasoning)Xiaomi0.4021164021164022025-12-16evidence
MiMo-V2-Flash (Reasoning)Xiaomi0.8677248677248682025-12-16evidence
MiniMax M1 40kMiniMax0.6571428571428572025-06-17evidence
MiniMax M1 80kMiniMax0.7111111111111112025-06-17evidence
MiniMax-M2MiniMax0.8264550264550272025-10-26evidence
MiniMax-M2.1MiniMax0.809523809523812025-12-23evidence
Ministral 3 14BMistral0.3513227513227512025-12-02evidence
Ministral 3 3BMistral0.2465608465608472025-12-02evidence
Ministral 3 8BMistral0.3026455026455032025-12-02evidence
Mistral 7B InstructMistral0.04550264550264552023-09-27evidence
Mistral Large (Feb '24)Mistral0.1777777777777782024-02-26evidence
Mistral Large 2 (Jul '24)Mistral0.2666666666666672024-07-24evidence
Mistral Large 2 (Nov '24)Mistral0.2931216931216932024-11-18evidence
Mistral Large 3Mistral0.4645502645502642025-12-02evidence
Mistral MediumMistral0.09947089947089952023-12-11evidence
Mistral Medium 3Mistral0.42025-05-07evidence
Mistral Medium 3.1Mistral0.4063492063492062025-08-12evidence
Mistral Small (Feb '24)Mistral0.1111111111111112024-02-26evidence
Mistral Small (Sep '24)Mistral0.1407407407407412024-09-17evidence
Mistral Small 3Mistral0.2518518518518522025-01-30evidence
Mistral Small 3.1Mistral0.2116402116402122025-03-17evidence
Mistral Small 3.2Mistral0.2751322751322752025-06-20evidence
Mixtral 8x22B InstructMistral0.1481481481481482024-04-17evidence
Mixtral 8x7B InstructMistral0.06560846560846562023-12-11evidence
Molmo 7B-DAllen Institute for AI0.03915343915343912024-09-25evidence
Motif-2-12.7B-ReasoningMotif Technologies0.6507936507936512025-12-04evidence
Nova 2.0 Lite (high)Amazon0.7111111111111112025-10-29evidence
Nova 2.0 Lite (low)Amazon0.4687830687830692025-10-29evidence
Nova 2.0 Lite (medium)Amazon0.6634920634920632025-10-29evidence
Nova 2.0 Lite (Non-reasoning)Amazon0.3460317460317462025-10-29evidence
Nova 2.0 Omni (low)Amazon0.5915343915343912025-11-26evidence
Nova 2.0 Omni (medium)Amazon0.660317460317462025-11-26evidence
Nova 2.0 Omni (Non-reasoning)Amazon0.3047619047619052025-11-26evidence
Nova 2.0 Pro Preview (low)Amazon0.6380952380952382025-11-27evidence
Nova 2.0 Pro Preview (medium)Amazon0.730158730158732025-11-27evidence
Nova 2.0 Pro Preview (Non-reasoning)Amazon0.4730158730158732025-11-27evidence
Nova LiteAmazon0.1671957671957672024-12-03evidence
Nova MicroAmazon0.139682539682542024-12-03evidence
Nova PremierAmazon0.3174603174603172025-04-30evidence
Nova ProAmazon0.2328042328042332024-12-03evidence
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)NVIDIA0.359788359788362025-12-15evidence
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)NVIDIA0.7407407407407412025-12-15evidence
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)NVIDIA0.3449735449735452025-10-28evidence
NVIDIA Nemotron Nano 12B v2 VL (Reasoning)NVIDIA0.6941798941798942025-10-28evidence
NVIDIA Nemotron Nano 9B V2 (Non-reasoning)NVIDIA0.7005291005291012025-08-18evidence
NVIDIA Nemotron Nano 9B V2 (Reasoning)NVIDIA0.7238095238095242025-08-18evidence
o1OpenAI0.6793650793650792024-12-05evidence
o1-miniOpenAI0.5756613756613762024-09-12evidence
o3OpenAI0.8084656084656082025-04-16evidence
o3-miniOpenAI0.7174603174603172025-01-31evidence
o3-mini (high)OpenAI0.7343915343915342025-01-31evidence
o4-mini (high)OpenAI0.8592592592592592025-04-16evidence
OLMo 2 32BAllen Institute for AI0.06772486772486772025-03-13evidence
OLMo 2 7BAllen Institute for AI0.04126984126984132024-11-26evidence
Olmo 3 32B ThinkAllen Institute for AI0.6719576719576722025-11-20evidence
Olmo 3 7B InstructAllen Institute for AI0.2656084656084662025-11-20evidence
Olmo 3 7B ThinkAllen Institute for AI0.6169312169312172025-11-20evidence
Olmo 3.1 32B ThinkAllen Institute for AI0.6952380952380952025-12-12evidence
OpenChat 3.5 (1210)OpenChat0.1153439153439152023-12-18evidence
Phi-3 Mini Instruct 3.8BMicrosoft0.1164021164021162024-04-23evidence
Phi-4Microsoft0.2306878306878312024-12-12evidence
Phi-4 Mini InstructMicrosoft0.1259259259259262024-02-26evidence
Phi-4 Multimodal InstructMicrosoft0.1312169312169312025-02-26evidence
Pixtral LargeMistral0.2613756613756612024-11-18evidence
Qwen2 Instruct 72BQwen0.1587301587301592024-06-07evidence
Qwen2.5 Coder Instruct 32BQwen0.2952380952380952024-11-11evidence
Qwen2.5 Coder Instruct 7BQwen0.1259259259259262024-09-19evidence
Qwen2.5 Instruct 32BQwen0.2476190476190482024-09-19evidence
Qwen2.5 Instruct 72BQwen0.2761904761904762024-09-19evidence
Qwen2.5 MaxQwen0.3587301587301592025-01-28evidence
Qwen2.5 TurboQwen0.1629629629629632024-11-18evidence
Qwen3 0.6B (Non-reasoning)Qwen0.0730158730158732025-04-28evidence
Qwen3 0.6B (Reasoning)Qwen0.1206349206349212025-04-28evidence
Qwen3 1.7B (Non-reasoning)Qwen0.1259259259259262025-04-28evidence
Qwen3 1.7B (Reasoning)Qwen0.3079365079365082025-04-28evidence
Qwen3 14B (Non-reasoning)Qwen0.280423280423282025-04-28evidence
Qwen3 14B (Reasoning)Qwen0.5227513227513232025-04-28evidence
Qwen3 235B A22B (Non-reasoning)Qwen0.3428571428571432025-04-28evidence
Qwen3 235B A22B (Reasoning)Qwen0.6222222222222222025-04-28evidence
Qwen3 235B A22B 2507 (Reasoning)Qwen0.7883597883597882025-07-25evidence
Qwen3 235B A22B 2507 InstructQwen0.5238095238095242025-07-21evidence
Qwen3 30B A3B (Non-reasoning)Qwen0.3216931216931222025-04-28evidence
Qwen3 30B A3B (Reasoning)Qwen0.5058201058201062025-04-28evidence
Qwen3 30B A3B 2507 (Reasoning)Qwen0.7068783068783072025-07-30evidence
Qwen3 30B A3B 2507 InstructQwen0.5153439153439152025-07-29evidence
Qwen3 32B (Non-reasoning)Qwen0.2878306878306882025-04-28evidence
Qwen3 32B (Reasoning)Qwen0.5460317460317462025-04-28evidence
Qwen3 4B (Non-reasoning)Qwen0.2328042328042332025-04-28evidence
Qwen3 4B (Reasoning)Qwen0.4645502645502642025-04-28evidence
Qwen3 4B 2507 (Reasoning)Qwen0.6412698412698412025-08-06evidence
Qwen3 4B 2507 InstructQwen0.3767195767195772025-08-06evidence
Qwen3 8B (Non-reasoning)Qwen0.2021164021164022025-04-28evidence
Qwen3 8B (Reasoning)Qwen0.4063492063492062025-04-28evidence
Qwen3 Coder 30B A3B InstructQwen0.4031746031746032025-07-31evidence
Qwen3 Coder 480B A35B InstructQwen0.5851851851851852025-07-22evidence
Qwen3 MaxQwen0.7671957671957672025-09-23evidence
Qwen3 Max (Preview)Qwen0.6507936507936512025-09-05evidence
Qwen3 Max Thinking (Preview)Qwen0.5354497354497352025-11-03evidence
Qwen3 Next 80B A3B (Reasoning)Qwen0.7841269841269842025-09-11evidence
Qwen3 Next 80B A3B InstructQwen0.6835978835978842025-09-11evidence
Qwen3 Omni 30B A3B (Reasoning)Qwen0.6793650793650792025-09-22evidence
Qwen3 Omni 30B A3B InstructQwen0.4222222222222222025-09-22evidence
Qwen3 VL 235B A22B (Reasoning)Qwen0.6455026455026452025-09-23evidence
Qwen3 VL 235B A22B InstructQwen0.5936507936507942025-09-23evidence
Qwen3 VL 30B A3B (Reasoning)Qwen0.6973544973544972025-10-03evidence
Qwen3 VL 30B A3B InstructQwen0.4761904761904762025-10-03evidence
Qwen3 VL 32B (Reasoning)Qwen0.7375661375661382025-10-21evidence
Qwen3 VL 32B InstructQwen0.5142857142857142025-10-21evidence
Qwen3 VL 4B (Reasoning)Qwen0.319576719576722025-10-14evidence
Qwen3 VL 4B InstructQwen0.289947089947092025-10-14evidence
Qwen3 VL 8B (Reasoning)Qwen0.3534391534391532025-10-14evidence
Qwen3 VL 8B InstructQwen0.3322751322751322025-10-14evidence
QwQ 32BQwen0.6306878306878312025-03-05evidence
QwQ 32B-PreviewQwen0.3365079365079372024-11-27evidence
Reka Flash 3Reka AI0.4349206349206352025-03-10evidence
Ring-1TInclusionAI0.6433862433862432025-10-13evidence
Ring-flash-2.0InclusionAI0.6275132275132272025-09-19evidence
Sarvam M (Reasoning)Sarvam0.2952380952380952025-05-23evidence
Seed-OSS-36B-InstructByteDance Seed0.7650793650793652025-08-20evidence
Solar Pro 2 (Non-reasoning)Upstage0.4243386243386242025-07-09evidence
Solar Pro 2 (Preview) (Non-reasoning)Upstage0.3851851851851852025-05-20evidence
Solar Pro 2 (Preview) (Reasoning)Upstage0.4624338624338622025-05-20evidence
Solar Pro 2 (Reasoning)Upstage0.6158730158730162025-07-09evidence
SonarPerplexity0.2952380952380952025-01-21evidence
Sonar ProPerplexity0.2751322751322752025-01-21evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.