Skip to content

Benchmark

GPQA Diamond

Science benchmarks measure how well models answer science questions. Scores are percentages. Higher is better.

Models and systems measured
282
Scores recorded
1623
Sources
4
IQ weight
1.72

Score distribution

79.3%
Mean
84.5%
Median
15.7%
Std dev
56.8%
10th percentile
92.2%
90th percentile
0.168%
Min
0.168%96.8%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.72 for chat models, measured over 272 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#Model or system
1GPT-6.2 Astramax· Epoch AI Benchmarking Hub data96.8%
2Gemini 4 Hydrogenxhigh· Epoch AI Benchmarking Hub data96.8%
3Gemini 4 Carbonhigh· Epoch AI Benchmarking Hub data96.5%
4Gemini 4 ArgonOpenRouter harness, google/gemini-4-argon-20261013, Google, public 90-day aggregate· OpenRouter benchmark exports96.5%
5Gemini 4 Argonhigh· Epoch AI Benchmarking Hub data96.4%
6Gemini 4 Neonxhigh· Epoch AI Benchmarking Hub data96.3%
7GPT-6 Astrahighest effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.96%
8GPT-6 Astramax· Epoch AI Benchmarking Hub data95.8%
9Gemini 3.8 FlashOpenRouter harness, google/gemini-3.8-flash-20260902, auto-routing, public 90-day aggregate· OpenRouter benchmark exports95.6%
10Claude Sonnet 5.5max· Epoch AI Benchmarking Hub data95.6%
11Fugu UltraFugu official headline evaluation· Reported by Sakana AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.95.5%
12GPT-6 AstraOpenRouter harness, openai/gpt-6-astra-pro-20260903, auto-routing, public 90-day aggregate, pro· OpenRouter benchmark exports95.5%
13Gemini 3.8 Flashhigh· Epoch AI Benchmarking Hub data95.4%
14GPT-6.1 Solmax· Epoch AI Benchmarking Hub data95.4%
15Gemini 3.8 FlashOpenAI launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.95.3%
16Gemini 3.8 FlashOpenRouter harness, google/gemini-3.8-flash-20260902, Google AI Studio, public 90-day aggregate· OpenRouter benchmark exports95.3%
17Gemini 3.1 Pro PreviewOpenRouter harness, google/gemini-3.1-pro-preview-20260219, Google, public 90-day aggregate· OpenRouter benchmark exports95.2%
18GPT-6 AstraOpenRouter harness, openai/gpt-6-astra-pro-20260903, OpenAI, public 90-day aggregate, pro· OpenRouter benchmark exports95.1%
19Claude Fable 5.2OpenRouter harness, anthropic/claude-fable-5.2-20261109, Anthropic, public 90-day aggregate· OpenRouter benchmark exports95.1%
20Gemini 3.1 Pro PreviewOpenRouter harness, google/gemini-3.1-pro-preview-20260219, Google AI Studio, public 90-day aggregate· OpenRouter benchmark exports95.1%
21Claude Fable 5.2OpenRouter harness, anthropic/claude-fable-5.2-20261109, Azure, public 90-day aggregate· OpenRouter benchmark exports94.9%
22GPT-6 AstraOpenRouter harness, openai/gpt-6-astra-pro-20260903, Azure, public 90-day aggregate, pro· OpenRouter benchmark exports94.9%
23GPT-6 Astralower-cost setting· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.94.9%
24Gemini 3.8 FlashOpenRouter harness, google/gemini-3.8-flash-20260902, Google, public 90-day aggregate· OpenRouter benchmark exports94.8%
25Gemini 3.7 Flashhigh· Epoch AI Benchmarking Hub data94.8%
26Ling 3.1 FlashOpenRouter harness, inclusionai/ling-3.1-flash-20261002, DeepInfra, public 90-day aggregate· OpenRouter benchmark exports94.8%
27GPT-6.1 SolOpenRouter harness, openai/gpt-6.1-sol-20260929, Amazon Bedrock, public 90-day aggregate· OpenRouter benchmark exports94.8%
28GPT-6 AstraOpenRouter harness, openai/gpt-6-astra-20260903, OpenAI, public 90-day aggregate· OpenRouter benchmark exports94.7%
29Claude Fable 5.2OpenRouter harness, anthropic/claude-fable-5.2-20261109, Google, public 90-day aggregate· OpenRouter benchmark exports94.6%
30GPT-6 AstraOpenRouter harness, openai/gpt-6-astra-20260903, Amazon Bedrock, public 90-day aggregate· OpenRouter benchmark exports94.6%
31GPT-5.4 Proxhigh· Epoch AI Benchmarking Hub data94.6%
32GPT-5.6 SolOpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.94.6%
33GPT-5.6 SolOpenAI launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.94.6%
34Gemini 3.1 Pro PreviewOpenRouter harness, google/gemini-3.1-pro-preview-20260219, auto-routing, public 90-day aggregate· OpenRouter benchmark exports94.5%
35Gemini 3.7 FlashOpenRouter harness, google/gemini-3.7-flash-20260813, Google, public 90-day aggregate· OpenRouter benchmark exports94.5%
36Gemini 3.1 Pro Previewhigh· Epoch AI Benchmarking Hub data94.4%
37GPT-6 AstraOpenRouter harness, openai/gpt-6-astra-20260903, auto-routing, public 90-day aggregate· OpenRouter benchmark exports94.4%
38GPT-6.1 SolOpenRouter harness, openai/gpt-6.1-sol-20260929, auto-routing, public 90-day aggregate· OpenRouter benchmark exports94.4%
39GPT-6.1 SolOpenRouter harness, openai/gpt-6.1-sol-20260929, OpenAI, public 90-day aggregate· OpenRouter benchmark exports94.4%
40GPT-5.4 ProOpenAI GPT-5.4 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.94.4%
41GPT-6 Solmax· Epoch AI Benchmarking Hub data94.3%
42GPT-6.1 Terramax· Epoch AI Benchmarking Hub data94.3%
43GPT-6 AstraOpenRouter harness, openai/gpt-6-astra-20260903, Azure, public 90-day aggregate· OpenRouter benchmark exports94.3%
44Gemini 3.1 Pro Previewno tools· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.94.3%
45Gemini 3.1 Pro PreviewOpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.94.3%
46Gemini 3.1 Pro PreviewOpus 4.8 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.94.3%
47Claude Opus 4.7198 questions · adaptive thinking · max effort · avg@10· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.94.2%
48Claude Opus 4.7Opus 4.8 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.94.2%
49Gemini 3.6 Flashhigh· Epoch AI Benchmarking Hub data94.1%
50Gemini 3.7 FlashOpenRouter harness, google/gemini-3.7-flash-20260813, Google AI Studio, public 90-day aggregate· OpenRouter benchmark exports94.1%

Showing 1–50 of 1,621 results.

Not ranked

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or system
MiMo V2 Flash Baseofficial Base table · 5-shot· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.55.1%
Qwen3.8-2.4T-A95Blifecycle-page core-benchmark claim· Reported by Alibaba Cloud Model Studio· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.92.6%

Tokens the model generated per task, as measured by the source. Comparable within this benchmark only.

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · OpenEvals/leaderboard-data, MIT (licence)