GPQA Diamond

Name: GPQA Diamond — AI Model Benchmark Results
Creator: Neura Market

448 graduate-level science questions (biology, chemistry, physics) designed to be hard for non-experts.

Model Rankings (261)

#	Model	Score	Provider	Source
	GPT-6 Astra🇺🇸			verified
	GPT-5.6 Sol🇺🇸			verified
	Claude Mythos Preview🇺🇸			verified
	Gemini 3.1 Pro🇺🇸			verified
	Claude Opus 4.7🇺🇸			verified
	Claude Opus 4.8🇺🇸			verified
	GPT-5.5🇺🇸			verified
	M Kimi K3🇨🇳			verified
	GPT-5.2 Pro🇺🇸			verified
	X Grok 4.5🇺🇸			verified
	GPT-5.6 Terra🇺🇸			verified
	GPT-5.4🇺🇸			verified
	Q Qwen3.8 Max🇨🇳			verified
	Q Qwen3.7 Max🇨🇳			verified
	GPT-5.2🇺🇸			verified
	T Hy4 preview🇨🇳			verified
	GPT-5.6 Luna🇺🇸			verified
	Gemini 3 Pro🇺🇸			verified
	Q Qwen3.8 Flash🇨🇳			verified
	Q Qwen3.8-Flash-Next🇨🇳			verified
	Claude Opus 4.6🇺🇸			verified
	Z GLM-5.2🇨🇳			verified
	M Kimi K2.6🇨🇳			verified
	Gemini 3 Flash🇺🇸			verified
	Q Qwen3.6 Plus🇨🇳			verified
	T Hy3🇨🇳			verified
	Q Qwen3.7-Plus🇨🇳			verified
	DeepSeek-V4-Pro-Max🇨🇳			verified
	Claude Sonnet 4.6🇺🇸			verified
	M Muse Spark🇺🇸			verified
	T Inkling-Small🇺🇸			verified
	Q Qwen3.8-27B🇨🇳			verified
	U Solar Pro 4🇰🇷			verified
	B Seed 2.0 Pro🇨🇳			verified
	Q Qwen3.5-397B-A17B🇨🇳			verified
	X Grok-4 Heavy🇺🇸			verified
	GPT-5.1 High🇺🇸			verified
	GPT-5.1 Thinking🇺🇸			verified
	GPT-5.1 Instant🇺🇸			verified
	GPT-5.1🇺🇸			verified
	DeepSeek-V4-Flash-Max🇨🇳			verified
	GPT-5 Medium🇺🇸			verified
	GPT-5.4 mini🇺🇸			verified
	Q Qwen3.6-27B🇨🇳			verified
	M Kimi K2.5🇨🇳			verified
	X Grok-4🇺🇸			verified
	DeepSeek-V4-Flash-0423🇨🇳			verified
	GPT-5 High🇺🇸			verified
	Claude Opus 4.5🇺🇸			verified
	Nemotron 3 Ultra (550B A55B)🇺🇸			verified
	Gemini 3.1 Flash-Lite🇺🇸			verified
	Q Qwen3.5-122B-A10B🇨🇳			verified
	Gemini 2.5 Pro Preview 06-05🇺🇸			verified
	Z GLM-5.1🇨🇳			verified
	Q Qwen3.6-35B-A3B🇨🇳			verified
	Z GLM-4.7🇨🇳			verified
	X Grok 4 Fast🇺🇸			verified
	GPT-5🇺🇸			verified
	GPT-5.5 Instant🇺🇸			verified
	Q Qwen3.5-27B🇨🇳			verified
	B Seed 2.0 Lite🇨🇳			verified
	ERNIE 5.0🇨🇳			verified
	Claude 3.7 Sonnet🇺🇸			verified
	MAI-Code-1-Flash🇺🇸			verified
	X Grok-3🇺🇸			verified
	M Kimi K2-Thinking-0905🇨🇳			verified
	Gemma 4 31B🇺🇸			verified
	Q Qwen3.5-35B-A3B🇨🇳			verified
	MAI-Thinking-1🇺🇸			verified
	ChatGPT-4o Latest🇺🇸			verified
	X Grok-3 Mini🇺🇸			verified
	X MiMo-V2-Flash🇨🇳			verified
	M Muse Glimmer-30B🇺🇸			verified
	Claude Sonnet 4.5🇺🇸			verified
	o3🇺🇸			verified
	Gemini 2.5 Pro🇺🇸			verified
	GPT-5.4 nano🇺🇸			verified
	Gemini 2.5 Flash🇺🇸			verified
	Nemotron 3 Super (120B A12B)🇺🇸			verified
	DeepSeek-V3.2🇨🇳			verified
	DeepSeek-V3.2 (Thinking)🇨🇳			verified
	Gemma 4 26B-A4B🇺🇸			verified
	GPT-5 mini🇺🇸			verified
	Q Qwen3.5-9B🇨🇳			verified
	M LongCat-Flash-Thinking🇨🇳			verified
	o4-mini🇺🇸			verified
	Nova 2 Pro🇺🇸			verified
	Q Qwen3-235B-A22B-Thinking-2507🇨🇳			verified
	Z GLM-4.6🇨🇳			verified
	MiniMax M2.1🇨🇳			verified
	DeepSeek-R1-0528🇨🇳			verified
	Claude Opus 4.1🇺🇸			verified
	GPT OSS 120B High🇺🇸			verified
	L EXAONE 4.5 33B🇰🇷			verified
	M LongCat-Flash-Thinking-2601🇨🇳			verified
	GPT OSS 120B🇺🇸			verified
	DeepSeek-V3.2-Exp🇨🇳			verified
	Claude Opus 4🇺🇸			verified
	Nova 2 Lite🇺🇸			verified
	Z GLM-4.5🇨🇳			verified
	o1-pro🇺🇸			verified
	Gemma 4 12B🇺🇸			verified
	S Sarvam-105B🇮🇳			verified
	MiniMax M2🇨🇳			verified
	o1🇺🇸			verified
	o1🇺🇸			aggregated
	Q Qwen3-235B-A22B-Instruct-2507🇨🇳			verified
	o3-mini🇺🇸			verified
	Q Qwen3-Next-80B-A3B-Thinking🇨🇳			verified
	Q Qwen3.5-4B🇨🇳			verified
	Llama 3.1 Nemotron Ultra 253B v1🇺🇸			verified
	M Kimi K2 0905🇨🇳			verified
	Nemotron 3.5 Lightning (30B A3B)🇺🇸			verified
	Claude Sonnet 4🇺🇸			verified
	Z GLM-4.7-Flash🇨🇳			verified
	M Kimi K2-Instruct-0905🇨🇳			verified
	M Kimi K2 Instruct🇨🇳			verified
	Z GLM-4.5-Air🇨🇳			verified
	Nemotron 3 Nano (30B A3B)🇺🇸			verified
	DeepSeek-V3.1🇨🇳			verified
	Claude Opus 4🇺🇸			aggregated
	Q Qwen3 VL 30B A3B Thinking🇨🇳			verified
	GPT OSS 20B High🇺🇸			verified
	Gemini 2.0 Flash Thinking🇺🇸			verified
	ERNIE 4.5🇨🇳			verified
	I Mercury 2🇺🇸			verified
	DeepSeek R1 Zero🇨🇳			verified
	o1-preview🇺🇸			verified
	M LongCat-Flash-Chat🇨🇳			verified
	DiffusionGemma 26B-A4B🇺🇸			verified
	Q Qwen3 VL 32B Thinking🇨🇳			verified
	Claude Haiku 4.5🇺🇸			verified
	Q Qwen3-Next-80B-A3B-Instruct🇨🇳			verified
	GPT OSS 20B🇺🇸			verified
	Ministral 3 (14B Reasoning 2512)🇫🇷			verified
	GPT-5 nano🇺🇸			verified
	Mistral Small 4🇫🇷			verified
	Magistral Medium🇫🇷			verified
	Claude Sonnet 4🇺🇸			aggregated
	Q Qwen3 VL 30B A3B Instruct🇨🇳			verified
	GPT-4o🇺🇸			verified
	MiniMax M1 80K🇨🇳			verified
	Q Qwen3 VL 8B Thinking🇨🇳			verified
	M Llama 4 Maverick🇺🇸			verified
	GPT-4.5🇺🇸			verified
	MiniMax M1 40K🇨🇳			verified
	Phi 4 Reasoning Plus🇺🇸			verified
	Q Qwen3 VL 32B Instruct🇨🇳			verified
	DeepSeek-V3 0324🇨🇳			verified
	Magistral Small 2506🇫🇷			verified
	Claude 3.5 Sonnet🇺🇸			verified
	Ministral 3 (8B Reasoning 2512)🇫🇷			verified
	M LongCat-Flash-Lite🇨🇳			verified
	X MiMo-V2.5-Pro🇨🇳			verified
	Llama-3.3 Nemotron Super 49B v1🇺🇸			verified
	S Sarvam-30B🇮🇳			verified
	I IBM Granite 4.2 30B🇺🇸			verified
	GPT-4.1🇺🇸			verified
	N Hermes 3 70B🇺🇸			verified
	Phi 4 Reasoning🇺🇸			verified
	Q Qwen3 30B A3B🇨🇳			verified
	Q QwQ-32B🇨🇳			verified
	DeepSeek R1 Distill Llama 70B🇨🇳			verified
	Q QwQ-32B-Preview🇨🇳			verified
	Claude 3.5 Sonnet🇺🇸			aggregated
	GPT-4.1 mini🇺🇸			verified
	Gemini 2.5 Flash-Lite🇺🇸			verified
	I IBM Granite 4.2 8B🇺🇸			verified
	Q Qwen3 VL 4B Thinking🇨🇳			verified
	Nemotron Nano 9B v2🇺🇸			verified
	DeepSeek R1 Distill Qwen 32B🇨🇳			verified
	Gemini 2.0 Flash🇺🇸			verified
	Q Qwen3 Max🇨🇳			verified
	o1-mini🇺🇸			verified
	Claude 3.5 Sonnet🇺🇸			verified
	Gemini 1.5 Pro🇺🇸			verified
	DeepSeek R1 Distill Qwen 14B🇨🇳			verified
	DeepSeek-V3🇨🇳			verified
	Gemma 4 E4B🇺🇸			verified
	M Llama 4 Scout🇺🇸			verified
	Phi 4🇺🇸			verified
	X Grok-2🇺🇸			verified
	I IBM Granite 4.2 3B🇺🇸			verified
	Llama 3.1 Nemotron Nano 8B V1🇺🇸			verified
	GPT-4o🇺🇸			aggregated
	GPT-4o🇺🇸			verified
	Min istral 3 (3B Reasoning 2512)🇫🇷			verified
	Phi 4 Mini Reasoning🇺🇸			verified
	Q Qwen3.5-2B🇨🇳			verified
	Gemini 2.0 Flash-Lite🇺🇸			verified
	Llama 3.1 405B🇺🇸			aggregated
	X Grok-2 mini🇺🇸			verified
	Gemini 1.5 Flash🇺🇸			verified
	M Llama 3.1 405B Instruct🇺🇸			verified
	M Llama 3.3 70B Instruct🇺🇸			verified
	Claude 3 Opus🇺🇸			aggregated
	Claude 3 Opus🇺🇸			verified
	GPT-4.1 nano🇺🇸			verified
	Q Qwen2.5 32B Instruct🇨🇳			verified
	Llama 3.3 70B🇺🇸			aggregated
	GPT-4 Turbo🇺🇸			aggregated
	DeepSeek R1 Distill Qwen 7B🇨🇳			verified
	Q Qwen2.5 72B Instruct🇨🇳			verified
	DeepSeek R1 Distill Llama 8B🇨🇳			verified
	Qwen 2.5 72B🇨🇳			aggregated
	Mistral Large 2🇫🇷			aggregated
	M Kimi K2 Base🇨🇳			verified
	GPT-4 Turbo🇺🇸			verified
	Q Qwen3 235B A22B🇨🇳			verified
	Nova Pro🇺🇸			verified
	M Llama 3.2 90B Instruct🇺🇸			verified
	Llama 3.1 70B🇺🇸			aggregated
	Mistral Small 3.2 24B Instruct🇫🇷			verified
	Q Qwen2.5 VL 32B Instruct🇨🇳			verified
	Mistral Small 3.1 24B Instruct🇫🇷			verified
	Q Qwen2.5 14B Instruct🇨🇳			verified
	Mistral Small 3 24B Instruct🇫🇷			verified
	Mistral Large 3 (675B Instruct 2512 NVFP4)🇫🇷			verified
	Mistral Large 3 (675B Base)🇫🇷			verified
	Mistral Large 3 (675B Instruct 2512 Eagle)🇫🇷			verified
	Mistral Large 3 (675B Instruct 2512)🇫🇷			verified
	Gemma 4 E2B🇺🇸			verified
	Gemma 3 27B🇺🇸			verified
	Q Qwen2 72B Instruct🇨🇳			verified
	Nova Lite🇺🇸			verified
	M Llama 3.1 70B Instruct🇺🇸			verified
	Claude 3.5 Haiku🇺🇸			aggregated
	Claude 3.5 Haiku🇺🇸			verified
	Gemma 3 12B🇺🇸			verified
	Gemini Diffusion🇺🇸			verified
	Claude 3 Sonnet🇺🇸			verified
	GPT-4o mini🇺🇸			aggregated
	GPT-4o mini🇺🇸			verified
	Nova Micro🇺🇸			verified
	Gemini 1.5 Flash 8B🇺🇸			verified
	Mistral Small 3.1 24B Base🇫🇷			verified
	Jamba 1.5 Large🇮🇱			verified
	Phi-3.5-MoE-instruct🇺🇸			verified
	Q Qwen2.5 7B Instruct🇨🇳			verified
	X Grok-1.5🇺🇸			verified
	GPT-4🇺🇸			verified
	Mistral Small 3 24B Base🇫🇷			verified
	DeepSeek R1 Distill Qwen 1.5B🇨🇳			verified
	Claude 3 Haiku🇺🇸			verified
	M Llama 3.2 3B Instruct🇺🇸			verified
	M Llama 3.2 11B Instruct🇺🇸			verified
	Jamba 1.5 Mini🇮🇱			verified
	Gemma 3 4B🇺🇸			verified
	GPT-3.5 Turbo🇺🇸			verified
	Q Qwen2.5-Omni-7B🇨🇳			verified
	M Llama 3.1 8B Instruct🇺🇸			verified
	Phi-3.5-mini-instruct🇺🇸			verified
	Gemini 1.0 Pro🇺🇸			verified
	Q Qwen2 7B Instruct🇨🇳			verified
	Phi 4 Mini🇺🇸			verified
	Gemma 3n E2B Instructed LiteRT (Preview)🇺🇸			verified
	Gemma 3n E2B Instructed🇺🇸			verified
	Gemma 3n E4B Instructed🇺🇸			verified
	Gemma 3n E4B Instructed LiteRT Preview🇺🇸			verified
	Gemma 3 1B🇺🇸			verified
	Q Qwen3.5-0.8B🇨🇳			verified

AI Model Benchmarks

GPQA Diamond

Model Rankings (261)