GPQA-D leaderboard

A display-only GPQA Diamond reference from provider comparison charts.

Models ranked by their published GPQA Diamond value

Rank	Model	Provider	Multiple choice questions
1	GPT-6 Astra	OpenAI	96.0
2	SASakana Fugu	Sakana AI	95.5
2	SASakana Fugu-Ultra	Sakana AI	95.5
4	GPT-5.6 Sol	OpenAI	94.6
5	Gemini 3.1 Pro	Google	94.3
6	Claude Opus 4.7 (Adaptive)	Anthropic	94.2
7	Claude Opus 4.8	Anthropic	93.6
7	GPT-5.5	OpenAI	93.6
9	Kimi K3	Moonshot AI	93.5
10	GPT-5.6 Terra	OpenAI	92.9
11	GPT-5.4	OpenAI	92.8
11	OAOrnith-1.5-397B	Ornith AI	92.8
13	Gemini 3.5 Flash	Google	92.7
14	Qwen3.8 Max	Alibaba	92.6
15	Qwen3.7 Max	Alibaba	92.4
16	GPT-5.6 Luna	OpenAI	92.3
16	Hy4 preview	Tencent	92.3
18	Qwen3.8-Flash-Next	Alibaba	91.7
19	GLM-5.2	Z.AI	91.2
20	Qwen3.8-Omni-Flash	Alibaba	91.0
21	DeepSeek V4.1 Flash	DeepSeek	90.9
22	Kimi K2.6	Moonshot AI	90.5
23	Qwen3.7 Plus	Alibaba	90.3
24	DeepSeek V4 Pro 0813	DeepSeek	90.1
25	INInterfaze Beta	Interfaze	89.9
26	TMInkling-Small	Thinking Machines Lab	89.5
26	Muse Spark	Meta	89.5
28	Claude Opus 4.6	Anthropic	89.2
28	OAOrnith-1.5-35B-A3B	Ornith AI	89.2
28	Qwen3.8-27B	Alibaba	89.2
31	Solar Pro 4	Upstage	89.0
32	Grok 4.20	xAI	88.5
33	DeepSeek V4 Flash 0731	DeepSeek	88.1
34	TMInkling	Thinking Machines Lab	87.9
35	Kimi K2.5	Moonshot AI	87.6
36	Hy3 Preview	Tencent	87.2
37	MiniMax M2.7	MiniMax	87.0
37	Nemotron 3 Ultra	NVIDIA	87.0
39	OAOrnith-1.5-9B	Ornith AI	86.4
40	Solar Open 2	Upstage	86.3
41	GLM-5.1	Z.AI	86.2
42	GLM-5	Z.AI	86.0
43	PMTernary Bonsai 2 27B	Prism ML	85.8
44	STA.X K2	SK Telecom	85.6
45	Ling 3.0 Flash	InclusionAI	85.0
46	MAI-Thinking-1	Microsoft	84.2
47	Ling 3.0 Flash FP8	InclusionAI	84.0
48	K-EXAONE 2.0	LG AI Research	82.2
49	Mercury 2.5	Inception	79.0
50	Gemma 4 12B	Google	78.8
51	Trinity-Large-Thinking	Arcee AI	76.3
52	Nemotron 3.5 Lightning 30B A3B NVFP4	NVIDIA	75.6
53	Nemotron 3 Nano Omni 30B A3B	NVIDIA	72.2
54	ZYZAYA1-8B	Zyphra	71.0
55	OPMiniCPM5-2B	OpenBMB	70.2
56	LongCat-Flash-Lite-Sparse	Meituan	69.5
57	Trinity-Large-Preview	Arcee AI	63.3
58	JEMellum2-12B-A2.5B-Thinking	JetBrains	57.6
59	ZYZAYA1-74B-Preview	Zyphra	57.3
60	LLaDA2.2-mini	InclusionAI	44.4
61	SPSoofi S 30B-A3B	Soofi Project	43.4
62	JEMellum2-12B-A2.5B-Instruct	JetBrains	40.9
63	OPMiniCPM5-1B	OpenBMB	26.3
64	LFM2.5-230M	LiquidAI	25.4

Evidence key: Observed

Rows are ordered by the value Trinity-Large-Thinking: Scaling an Open Source Frontier Agent published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.