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
1601Llama 3.1 8B InstructOpenRouter harness, meta-llama/llama-3.1-8b-instruct, DeepInfra, public 90-day aggregate· OpenRouter benchmark exports26.1%
1602Llama 3 8B Instruct· Epoch AI Benchmarking Hub data26.1%
1603Llama 3.1 8B InstructOpenRouter harness, meta-llama/llama-3.1-8b-instruct, Novita, public 90-day aggregate· OpenRouter benchmark exports25.9%
1604Ministral 3B· Epoch AI Benchmarking Hub data25.3%
1605DeepSeek LLM 67B Chat· Epoch AI Benchmarking Hub data24.6%
1606Llama 3.2 1B Instruct· Epoch AI Benchmarking Hub data23.9%
1607Gemma 3 4B IT· Epoch AI Benchmarking Hub data23.2%
1608Gemini Nano Banana 2.1OpenRouter harness, google/gemini-nano-banana-2.1-20261006, Google, public 90-day aggregate· OpenRouter benchmark exports21.4%
1609Gemma 3 1b it· Epoch AI Benchmarking Hub data19.9%
1610Ling 3.0 Flash FinOpenRouter harness, inclusionai/ling-3.0-flash-fin-20260827, DeepInfra, public 90-day aggregate· OpenRouter benchmark exports17.2%
1611Mistral (7B) Instruct v0.3· Epoch AI Benchmarking Hub data15.2%
1612Yi 34B Chat· Epoch AI Benchmarking Hub data14.7%
1613open-mistral-7b· Epoch AI Benchmarking Hub data13.2%
1614Qwen3.5 0.8B· OpenEvals Leaderboard data· Reported by the model's developer. The source relaying it did not verify it.11.9%
1615Gemini 3.1 Flash-Lite ImageOpenRouter harness, google/gemini-3.1-flash-lite-image-20260630, Google AI Studio, public 90-day aggregate· OpenRouter benchmark exports11.6%
1616Gemini 3.1 Flash-Lite ImageOpenRouter harness, google/gemini-3.1-flash-lite-image-20260630, Google, public 90-day aggregate· OpenRouter benchmark exports11.3%
1617Gemini 3.1 Flash-Lite ImageOpenRouter harness, google/gemini-3.1-flash-lite-image-20260630, auto-routing, public 90-day aggregate· OpenRouter benchmark exports10.3%
1618DeepSeek R1 0528 Qwen3 8B· Epoch AI Benchmarking Hub data9.3%
1619DeepSeek V3OpenRouter harness, deepseek/deepseek-chat-v3-0324, Novita, public 90-day aggregate· OpenRouter benchmark exports8.8%
1620DeepSeek V3.1OpenRouter harness, deepseek/deepseek-chat-v3.1, SiliconFlow, public 90-day aggregate· OpenRouter benchmark exports0.168%
1621Llama 3.1 8B InstructOpenRouter harness, meta-llama/llama-3.1-8b-instruct, Cloudflare, public 90-day aggregate· OpenRouter benchmark exports0.168%

Showing 1,601–1,621 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)