AI EVALUATION, IN CONTEXT.BY EQUALITY MACHINE

LLM Stats

GPQA

A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.

评测信息与证据

来源
LLM Stats
发布者
Anthropic
评测发布日期
2023-11-20
采集日期
2026-08-17
模态
text

本站保留来源报告的结果,不代表独立复测。请先核对任务版本、评测协议、分数单位和报告日期;不同运行条件不能直接合并为统一排名。

原始资料

报告成绩 239

按来源中的观察顺序展示,顺序不代表排名。日期保留原始精度。

模型数值单位协议报告日期与口径来源
GPT-5.6 Sol0.946未收录未收录2026-07-09 · model_announcementLLM Stats
Claude Mythos Preview0.946未收录未收录2026-04-07 · model_announcementLLM Stats
Gemini 3.1 Pro0.943未收录未收录2026-02-19 · model_announcementLLM Stats
Claude Opus 4.70.942未收录未收录2026-04-16 · model_announcementLLM Stats
Claude Opus 4.80.936未收录未收录2026-05-28 · model_announcementLLM Stats
GPT-5.50.936未收录未收录2026-04-23 · model_announcementLLM Stats
Kimi K30.935未收录未收录2026-07-16 · model_announcementLLM Stats
GPT-5.2 Pro0.932未收录未收录2025-12-11 · model_announcementLLM Stats
Grok 4.50.93未收录未收录2026-07-16 · model_announcementLLM Stats
GPT-5.6 Terra0.929未收录未收录2026-07-09 · model_announcementLLM Stats
GPT-5.40.928未收录未收录2026-03-05 · model_announcementLLM Stats
Qwen3.8 Max0.926未收录未收录2026-08-02 · model_announcementLLM Stats
Qwen3.7 Max0.924未收录未收录2026-05-19 · model_announcementLLM Stats
GPT-5.20.924未收录未收录2025-12-11 · model_announcementLLM Stats
GPT-5.6 Luna0.923未收录未收录2026-07-09 · model_announcementLLM Stats
Gemini 3 Pro0.919未收录未收录2025-11-18 · model_announcementLLM Stats
Claude Opus 4.60.913未收录未收录2026-02-05 · model_announcementLLM Stats
GLM-5.20.912未收录未收录2026-06-16 · model_announcementLLM Stats
Kimi K2.60.905未收录未收录2026-04-20 · model_announcementLLM Stats
Hy30.904未收录未收录2026-07-06 · model_announcementLLM Stats
Qwen3.6 Plus0.904未收录未收录2026-04-02 · model_announcementLLM Stats
Gemini 3 Flash0.904未收录未收录2025-12-17 · model_announcementLLM Stats
Qwen3.7-Plus0.903未收录未收录2026-05-31 · model_announcementLLM Stats
DeepSeek-V4-Pro-Max0.901未收录未收录2026-04-23 · model_announcementLLM Stats
Claude Sonnet 4.60.899未收录未收录2026-02-17 · model_announcementLLM Stats
Inkling-Small0.895未收录未收录2026-07-30 · model_announcementLLM Stats
Muse Spark0.895未收录未收录2026-04-08 · model_announcementLLM Stats
Qwen3.8-27B0.892未收录未收录2026-08-14 · model_announcementLLM Stats
Solar Pro 40.89未收录未收录2026-08-06 · model_announcementLLM Stats
Seed 2.0 Pro0.889未收录未收录2026-02-14 · model_announcementLLM Stats
Qwen3.5-397B-A17B0.884未收录未收录2026-02-16 · model_announcementLLM Stats
Grok-4 Heavy0.884未收录未收录2025-07-09 · model_announcementLLM Stats
DeepSeek-V4-Flash-Max0.881未收录未收录2026-04-23 · model_announcementLLM Stats
GPT-5.10.881未收录未收录2025-11-13 · model_announcementLLM Stats
GPT-5.1 Thinking0.881未收录未收录2025-11-12 · model_announcementLLM Stats
GPT-5.1 High0.881未收录未收录2025-11-12 · model_announcementLLM Stats
GPT-5.1 Instant0.881未收录未收录2025-11-12 · model_announcementLLM Stats
GPT-5 Medium0.881未收录未收录2025-08-07 · model_announcementLLM Stats
GPT-5.4 mini0.88未收录未收录2026-03-17 · model_announcementLLM Stats
Qwen3.6-27B0.878未收录未收录2026-04-21 · model_announcementLLM Stats
Kimi K2.50.876未收录未收录2026-01-27 · model_announcementLLM Stats
Grok-40.875未收录未收录2025-07-09 · model_announcementLLM Stats
DeepSeek-V4-Flash-04230.874未收录未收录2026-04-23 · model_announcementLLM Stats
GPT-5 High0.873未收录未收录2025-08-07 · model_announcementLLM Stats
Nemotron 3 Ultra (550B A55B)0.87未收录未收录2026-06-04 · model_announcementLLM Stats
Claude Opus 4.50.87未收录未收录2025-11-24 · model_announcementLLM Stats
Gemini 3.1 Flash-Lite0.869未收录未收录2026-03-03 · model_announcementLLM Stats
Qwen3.5-122B-A10B0.866未收录未收录2026-02-24 · model_announcementLLM Stats
Gemini 2.5 Pro Preview 06-050.864未收录未收录2025-06-05 · model_announcementLLM Stats
GLM-5.10.862未收录未收录2026-04-07 · model_announcementLLM Stats
Qwen3.6-35B-A3B0.86未收录未收录2026-04-16 · model_announcementLLM Stats
GLM-4.70.857未收录未收录2025-12-22 · model_announcementLLM Stats
Grok 4 Fast0.857未收录未收录2025-08-28 · model_announcementLLM Stats
GPT-50.857未收录未收录2025-08-07 · model_announcementLLM Stats
GPT-5.5 Instant0.856未收录未收录2026-05-05 · model_announcementLLM Stats
Qwen3.5-27B0.855未收录未收录2026-02-24 · model_announcementLLM Stats
Seed 2.0 Lite0.851未收录未收录2026-02-14 · model_announcementLLM Stats
ERNIE 5.00.85未收录未收录2026-01-22 · model_announcementLLM Stats
Claude 3.7 Sonnet0.848未收录未收录2025-02-24 · model_announcementLLM Stats
MAI-Code-1-Flash0.846未收录未收录2026-06-02 · model_announcementLLM Stats
Grok-30.846未收录未收录2025-02-17 · model_announcementLLM Stats
Kimi K2-Thinking-09050.845未收录未收录2025-09-05 · model_announcementLLM Stats
Gemma 4 31B0.843未收录未收录2026-04-02 · model_announcementLLM Stats
MAI-Thinking-10.842未收录未收录2026-06-02 · model_announcementLLM Stats
Qwen3.5-35B-A3B0.842未收录未收录2026-02-24 · model_announcementLLM Stats
Grok-3 Mini0.84未收录未收录2025-02-17 · model_announcementLLM Stats
ChatGPT-4o Latest0.84未收录未收录2024-05-13 · model_announcementLLM Stats
MiMo-V2-Flash0.837未收录未收录2025-12-16 · model_announcementLLM Stats
Muse Glimmer-30B0.835未收录未收录2026-08-10 · model_announcementLLM Stats
Claude Sonnet 4.50.834未收录未收录2025-09-29 · model_announcementLLM Stats
o30.833未收录未收录2025-04-16 · model_announcementLLM Stats
Gemini 2.5 Pro0.83未收录未收录2025-05-20 · model_announcementLLM Stats
GPT-5.4 nano0.828未收录未收录2026-03-17 · model_announcementLLM Stats
Gemini 2.5 Flash0.828未收录未收录2025-05-20 · model_announcementLLM Stats
Nemotron 3 Super (120B A12B)0.827未收录未收录2026-03-11 · model_announcementLLM Stats
DeepSeek-V3.2 (Thinking)0.824未收录未收录2025-12-01 · model_announcementLLM Stats
DeepSeek-V3.20.824未收录未收录2025-12-01 · model_announcementLLM Stats
Gemma 4 26B-A4B0.823未收录未收录2026-04-02 · model_announcementLLM Stats
GPT-5 mini0.823未收录未收录2025-08-07 · model_announcementLLM Stats
Qwen3.5-9B0.817未收录未收录2026-03-02 · model_announcementLLM Stats
LongCat-Flash-Thinking0.815未收录未收录2025-09-22 · model_announcementLLM Stats
Nova 2 Pro0.814未收录未收录2025-12-02 · model_announcementLLM Stats
o4-mini0.814未收录未收录2025-04-16 · model_announcementLLM Stats
Qwen3-235B-A22B-Thinking-25070.811未收录未收录2025-07-25 · model_announcementLLM Stats
MiniMax M2.10.81未收录未收录2025-12-23 · model_announcementLLM Stats
GLM-4.60.81未收录未收录2025-09-30 · model_announcementLLM Stats
DeepSeek-R1-05280.81未收录未收录2025-05-28 · model_announcementLLM Stats
Claude Opus 4.10.809未收录未收录2025-08-05 · model_announcementLLM Stats
GPT OSS 120B High0.809未收录未收录2025-08-05 · model_announcementLLM Stats
LongCat-Flash-Thinking-26010.805未收录未收录2026-01-14 · model_announcementLLM Stats
GPT OSS 120B0.801未收录未收录2025-08-05 · model_announcementLLM Stats
DeepSeek-V3.2-Exp0.799未收录未收录2025-09-29 · model_announcementLLM Stats
Nova 2 Lite0.796未收录未收录2025-12-02 · model_announcementLLM Stats
Claude Opus 40.796未收录未收录2025-05-22 · model_announcementLLM Stats
GLM-4.50.791未收录未收录2025-07-28 · model_announcementLLM Stats
o1-pro0.79未收录未收录2024-12-17 · model_announcementLLM Stats
Gemma 4 12B0.788未收录未收录2026-05-23 · model_announcementLLM Stats
Sarvam-105B0.787未收录未收录2026-03-06 · model_announcementLLM Stats
MiniMax M20.78未收录未收录2025-10-27 · model_announcementLLM Stats
o10.78未收录未收录2024-12-17 · model_announcementLLM Stats
Qwen3-235B-A22B-Instruct-25070.775未收录未收录2025-07-22 · model_announcementLLM Stats
Qwen3-Next-80B-A3B-Thinking0.772未收录未收录2025-09-10 · model_announcementLLM Stats
o3-mini0.772未收录未收录2025-01-30 · model_announcementLLM Stats
Qwen3.5-4B0.762未收录未收录2026-03-02 · model_announcementLLM Stats
Llama 3.1 Nemotron Ultra 253B v10.7601未收录未收录2025-04-07 · model_announcementLLM Stats
Kimi K2 09050.758未收录未收录2025-09-05 · model_announcementLLM Stats
Nemotron 3.5 Lightning (30B A3B)0.7544未收录未收录2026-08-11 · model_announcementLLM Stats
Claude Sonnet 40.754未收录未收录2025-05-22 · model_announcementLLM Stats
GLM-4.7-Flash0.752未收录未收录2026-01-19 · model_announcementLLM Stats
Kimi K2-Instruct-09050.751未收录未收录2025-09-05 · model_announcementLLM Stats
Kimi K2 Instruct0.751未收录未收录2025-07-11 · model_announcementLLM Stats
Nemotron 3 Nano (30B A3B)0.75未收录未收录2025-12-15 · model_announcementLLM Stats
GLM-4.5-Air0.75未收录未收录2025-07-28 · model_announcementLLM Stats
DeepSeek-V3.10.749未收录未收录2025-01-10 · model_announcementLLM Stats
Qwen3 VL 30B A3B Thinking0.744未收录未收录2025-09-22 · model_announcementLLM Stats
GPT OSS 20B High0.742未收录未收录2025-08-05 · model_announcementLLM Stats
Gemini 2.0 Flash Thinking0.742未收录未收录2025-01-21 · model_announcementLLM Stats
Mercury 20.74未收录未收录2026-02-24 · model_announcementLLM Stats
ERNIE 4.50.74未收录未收录2025-06-25 · model_announcementLLM Stats
DeepSeek R1 Zero0.733未收录未收录2025-01-20 · model_announcementLLM Stats
o1-preview0.733未收录未收录2024-09-12 · model_announcementLLM Stats
LongCat-Flash-Chat0.7323未收录未收录2025-08-29 · model_announcementLLM Stats
DiffusionGemma 26B-A4B0.732未收录未收录2026-06-10 · model_announcementLLM Stats
Qwen3 VL 32B Thinking0.731未收录未收录2025-09-22 · model_announcementLLM Stats
Claude Haiku 4.50.73未收录未收录2025-10-15 · model_announcementLLM Stats
Qwen3-Next-80B-A3B-Instruct0.729未收录未收录2025-09-10 · model_announcementLLM Stats
GPT OSS 20B0.715未收录未收录2025-08-05 · model_announcementLLM Stats
Mistral Small 40.712未收录未收录2026-03-16 · model_announcementLLM Stats
Ministral 3 (14B Reasoning 2512)0.712未收录未收录2025-12-04 · model_announcementLLM Stats
GPT-5 nano0.712未收录未收录2025-08-07 · model_announcementLLM Stats
Magistral Medium0.708未收录未收录2025-06-10 · model_announcementLLM Stats
Qwen3 VL 30B A3B Instruct0.704未收录未收录2025-09-22 · model_announcementLLM Stats
GPT-4o0.701未收录未收录2024-08-06 · model_announcementLLM Stats
MiniMax M1 80K0.7未收录未收录2025-06-16 · model_announcementLLM Stats
Qwen3 VL 8B Thinking0.699未收录未收录2025-09-22 · model_announcementLLM Stats
Llama 4 Maverick0.698未收录未收录2025-04-05 · model_announcementLLM Stats
GPT-4.50.695未收录未收录2025-02-27 · model_announcementLLM Stats
MiniMax M1 40K0.692未收录未收录2025-06-16 · model_announcementLLM Stats
Qwen3 VL 32B Instruct0.689未收录未收录2025-09-22 · model_announcementLLM Stats
Phi 4 Reasoning Plus0.689未收录未收录2025-04-30 · model_announcementLLM Stats
DeepSeek-V3 03240.684未收录未收录2025-03-25 · model_announcementLLM Stats
Magistral Small 25060.6818未收录未收录2025-06-10 · model_announcementLLM Stats
Claude 3.5 Sonnet0.672未收录未收录2024-10-22 · model_announcementLLM Stats
Ministral 3 (8B Reasoning 2512)0.668未收录未收录2025-12-04 · model_announcementLLM Stats
LongCat-Flash-Lite0.6678未收录未收录2026-02-05 · model_announcementLLM Stats
MiMo-V2.5-Pro0.667未收录未收录2026-04-27 · model_announcementLLM Stats
Llama-3.3 Nemotron Super 49B v10.6667未收录未收录2025-03-18 · model_announcementLLM Stats
Sarvam-30B0.665未收录未收录2026-03-06 · model_announcementLLM Stats
GPT-4.10.663未收录未收录2025-04-14 · model_announcementLLM Stats
Hermes 3 70B0.661未收录未收录2024-08-15 · model_announcementLLM Stats
Phi 4 Reasoning0.658未收录未收录2025-04-30 · model_announcementLLM Stats
Qwen3 30B A3B0.658未收录未收录2025-04-29 · model_announcementLLM Stats
QwQ-32B0.652未收录未收录2025-03-05 · model_announcementLLM Stats
DeepSeek R1 Distill Llama 70B0.652未收录未收录2025-01-20 · model_announcementLLM Stats
QwQ-32B-Preview0.652未收录未收录2024-11-28 · model_announcementLLM Stats
GPT-4.1 mini0.65未收录未收录2025-04-14 · model_announcementLLM Stats
Gemini 2.5 Flash-Lite0.646未收录未收录2025-06-17 · model_announcementLLM Stats
Qwen3 VL 4B Thinking0.641未收录未收录2025-09-22 · model_announcementLLM Stats
Nemotron Nano 9B v20.64未收录未收录2025-08-18 · model_announcementLLM Stats
DeepSeek R1 Distill Qwen 32B0.621未收录未收录2025-01-20 · model_announcementLLM Stats
Gemini 2.0 Flash0.621未收录未收录2024-12-01 · model_announcementLLM Stats
Qwen3 Max0.62未收录未收录2025-12-15 · model_announcementLLM Stats
o1-mini0.6未收录未收录2024-09-12 · model_announcementLLM Stats
Claude 3.5 Sonnet0.594未收录未收录2024-06-21 · model_announcementLLM Stats
DeepSeek R1 Distill Qwen 14B0.591未收录未收录2025-01-20 · model_announcementLLM Stats
DeepSeek-V30.591未收录未收录2024-12-25 · model_announcementLLM Stats
Gemini 1.5 Pro0.591未收录未收录2024-05-01 · model_announcementLLM Stats
Gemma 4 E4B0.586未收录未收录2026-04-02 · model_announcementLLM Stats
Llama 4 Scout0.572未收录未收录2025-04-05 · model_announcementLLM Stats
Phi 40.561未收录未收录2024-12-12 · model_announcementLLM Stats
Grok-20.56未收录未收录2024-08-13 · model_announcementLLM Stats
Llama 3.1 Nemotron Nano 8B V10.541未收录未收录2025-03-18 · model_announcementLLM Stats
GPT-4o0.536未收录未收录2024-05-13 · model_announcementLLM Stats
Min istral 3 (3B Reasoning 2512)0.534未收录未收录2025-12-04 · model_announcementLLM Stats
Phi 4 Mini Reasoning0.52未收录未收录2025-04-30 · model_announcementLLM Stats
Qwen3.5-2B0.516未收录未收录2026-03-02 · model_announcementLLM Stats
Gemini 2.0 Flash-Lite0.515未收录未收录2025-02-05 · model_announcementLLM Stats
Grok-2 mini0.51未收录未收录2024-08-13 · model_announcementLLM Stats
Gemini 1.5 Flash0.51未收录未收录2024-05-01 · model_announcementLLM Stats
Llama 3.1 405B Instruct0.507未收录未收录2024-07-23 · model_announcementLLM Stats
Llama 3.3 70B Instruct0.505未收录未收录2024-12-06 · model_announcementLLM Stats
Claude 3 Opus0.504未收录未收录2024-02-29 · model_announcementLLM Stats
GPT-4.1 nano0.503未收录未收录2025-04-14 · model_announcementLLM Stats
Qwen2.5 32B Instruct0.495未收录未收录2024-09-19 · model_announcementLLM Stats
DeepSeek R1 Distill Qwen 7B0.491未收录未收录2025-01-20 · model_announcementLLM Stats
DeepSeek R1 Distill Llama 8B0.49未收录未收录2025-01-20 · model_announcementLLM Stats
Qwen2.5 72B Instruct0.49未收录未收录2024-09-19 · model_announcementLLM Stats
Kimi K2 Base0.481未收录未收录2025-07-11 · model_announcementLLM Stats
GPT-4 Turbo0.48未收录未收录2024-04-09 · model_announcementLLM Stats
Qwen3 235B A22B0.4747未收录未收录2025-04-29 · model_announcementLLM Stats
Nova Pro0.469未收录未收录2024-11-20 · model_announcementLLM Stats
Llama 3.2 90B Instruct0.467未收录未收录2024-09-25 · model_announcementLLM Stats
Mistral Small 3.2 24B Instruct0.4613未收录未收录2025-06-20 · model_announcementLLM Stats
Qwen2.5 VL 32B Instruct0.46未收录未收录2025-02-28 · model_announcementLLM Stats
Mistral Small 3.1 24B Instruct0.4596未收录未收录2025-03-17 · model_announcementLLM Stats
Qwen2.5 14B Instruct0.455未收录未收录2024-09-19 · model_announcementLLM Stats
Mistral Small 3 24B Instruct0.453未收录未收录2025-01-30 · model_announcementLLM Stats
Mistral Large 3 (675B Instruct 2512 NVFP4)0.439未收录未收录2025-12-04 · model_announcementLLM Stats
Mistral Large 3 (675B Instruct 2512)0.439未收录未收录2025-12-04 · model_announcementLLM Stats
Mistral Large 3 (675B Instruct 2512 Eagle)0.439未收录未收录2025-12-04 · model_announcementLLM Stats
Mistral Large 3 (675B Base)0.439未收录未收录2025-12-04 · model_announcementLLM Stats
Gemma 4 E2B0.434未收录未收录2026-04-02 · model_announcementLLM Stats
Gemma 3 27B0.424未收录未收录2025-03-12 · model_announcementLLM Stats
Qwen2 72B Instruct0.424未收录未收录2024-07-23 · model_announcementLLM Stats
Nova Lite0.42未收录未收录2024-11-20 · model_announcementLLM Stats
Llama 3.1 70B Instruct0.417未收录未收录2024-07-23 · model_announcementLLM Stats
Claude 3.5 Haiku0.416未收录未收录2024-10-22 · model_announcementLLM Stats
Gemma 3 12B0.409未收录未收录2025-03-12 · model_announcementLLM Stats
Gemini Diffusion0.404未收录未收录2025-05-20 · model_announcementLLM Stats
Claude 3 Sonnet0.404未收录未收录2024-02-29 · model_announcementLLM Stats
GPT-4o mini0.402未收录未收录2024-07-18 · model_announcementLLM Stats
Nova Micro0.4未收录未收录2024-11-20 · model_announcementLLM Stats
Gemini 1.5 Flash 8B0.384未收录未收录2024-03-15 · model_announcementLLM Stats
Mistral Small 3.1 24B Base0.375未收录未收录2025-03-17 · model_announcementLLM Stats
Jamba 1.5 Large0.369未收录未收录2024-08-22 · model_announcementLLM Stats
Phi-3.5-MoE-instruct0.368未收录未收录2024-08-23 · model_announcementLLM Stats
Qwen2.5 7B Instruct0.364未收录未收录2024-09-19 · model_announcementLLM Stats
Grok-1.50.359未收录未收录2024-03-28 · model_announcementLLM Stats
GPT-40.357未收录未收录2023-06-13 · model_announcementLLM Stats
Mistral Small 3 24B Base0.3437未收录未收录2025-01-30 · model_announcementLLM Stats
DeepSeek R1 Distill Qwen 1.5B0.338未收录未收录2025-01-20 · model_announcementLLM Stats
Claude 3 Haiku0.333未收录未收录2024-03-13 · model_announcementLLM Stats
Llama 3.2 11B Instruct0.328未收录未收录2024-09-25 · model_announcementLLM Stats
Llama 3.2 3B Instruct0.328未收录未收录2024-09-25 · model_announcementLLM Stats
Jamba 1.5 Mini0.323未收录未收录2024-08-22 · model_announcementLLM Stats
Qwen2.5-Omni-7B0.308未收录未收录2025-03-27 · model_announcementLLM Stats
Gemma 3 4B0.308未收录未收录2025-03-12 · model_announcementLLM Stats
GPT-3.5 Turbo0.308未收录未收录2023-03-21 · model_announcementLLM Stats
Phi-3.5-mini-instruct0.304未收录未收录2024-08-23 · model_announcementLLM Stats
Llama 3.1 8B Instruct0.304未收录未收录2024-07-23 · model_announcementLLM Stats
Gemini 1.0 Pro0.279未收录未收录2024-02-15 · model_announcementLLM Stats
Qwen2 7B Instruct0.253未收录未收录2024-07-23 · model_announcementLLM Stats
Phi 4 Mini0.252未收录未收录2025-02-01 · model_announcementLLM Stats
Gemma 3n E2B Instructed0.248未收录未收录2025-06-26 · model_announcementLLM Stats
Gemma 3n E2B Instructed LiteRT (Preview)0.248未收录未收录2025-05-20 · model_announcementLLM Stats
Gemma 3n E4B Instructed0.237未收录未收录2025-06-26 · model_announcementLLM Stats
Gemma 3n E4B Instructed LiteRT Preview0.237未收录未收录2025-05-20 · model_announcementLLM Stats
Gemma 3 1B0.192未收录未收录2025-03-12 · model_announcementLLM Stats
Qwen3.5-0.8B0.119未收录未收录2026-03-02 · model_announcementLLM Stats

其他来源中的相关记录