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
1351GPT OSS 20bofficial model card Table 3 · reasoning medium · with tools; Table 3 does not name the exact tool · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.67.1%
1352Gemma 4 31B ITOpenRouter harness, google/gemma-4-31b-it-20260402, Venice, public 90-day aggregate· OpenRouter benchmark exports67%
1353Llama 4 Maverick· Epoch AI Benchmarking Hub data67%
1354GPT OSS 20bOpenRouter harness, openai/gpt-oss-20b, Amazon Bedrock, public 90-day aggregate· OpenRouter benchmark exports67%
1355GPT 4.1· Epoch AI Benchmarking Hub data66.9%
1356DeepSeek ChatOpenRouter harness, deepseek/deepseek-chat-v3, StreamLake, public 90-day aggregate· OpenRouter benchmark exports66.9%
1357GLM 4.6vOpenRouter harness, z-ai/glm-4.6-20251208, auto-routing, public 90-day aggregate· OpenRouter benchmark exports66.8%
1358qwen3-vl-30bOpenRouter harness, qwen/qwen3-vl-30b-a3b-instruct, Alibaba, public 90-day aggregate· OpenRouter benchmark exports66.8%
1359Claude Sonnet 4· Epoch AI Benchmarking Hub data66.7%
1360Gemini 2.5 Pro Preview 05-06· Epoch AI Benchmarking Hub data66.7%
1361GPT 5.1none· Epoch AI Benchmarking Hub data66.7%
1362GPT OSS 20bOpenRouter harness, openai/gpt-oss-20b, Phala, public 90-day aggregate· OpenRouter benchmark exports66.5%
1363GLM 4.6vOpenRouter harness, z-ai/glm-4.6-20251208, Novita, public 90-day aggregate· OpenRouter benchmark exports66.3%
1364Claude Sonnet 3.7· Epoch AI Benchmarking Hub data66%
1365GPT OSS 20bofficial model card Table 3 · reasoning medium · no tools · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.66%
1366GLM 4.6vOpenRouter harness, z-ai/glm-4.6-20251208, Z.AI, public 90-day aggregate· OpenRouter benchmark exports66%
1367Llama 4 MaverickOpenRouter harness, meta-llama/llama-4-maverick-17b-128e-instruct, DeepInfra, public 90-day aggregate· OpenRouter benchmark exports66%
1368Llama 4 MaverickOpenRouter harness, meta-llama/llama-4-maverick-17b-128e-instruct, DigitalOcean, public 90-day aggregate· OpenRouter benchmark exports66%
1369Qwen3 235B A22B Instruct 2507OpenRouter harness, qwen/qwen3-235b-a22b-07-25, GMICloud, public 90-day aggregate· OpenRouter benchmark exports66%
1370GPT 4.1OpenRouter harness, openai/gpt-4.1-2025-04-14, OpenAI, public 90-day aggregate· OpenRouter benchmark exports66%
1371GPT-4.1 mini· Epoch AI Benchmarking Hub data65.8%
1372Llama 4 MaverickOpenRouter harness, meta-llama/llama-4-maverick-17b-128e-instruct, auto-routing, public 90-day aggregate· OpenRouter benchmark exports65.8%
1373qwen3-vl-30bOpenRouter harness, qwen/qwen3-vl-30b-a3b-instruct, PrimeIntellect, public 90-day aggregate· OpenRouter benchmark exports65.8%
1374Qwen3-4B-Thinking-2507· OpenEvals Leaderboard data· Reported by the model's developer. The source relaying it did not verify it.65.8%
1375Qwen3 32B· Epoch AI Benchmarking Hub data65.7%
1376gemini-2.0-pro-exp-02-05· Epoch AI Benchmarking Hub data65.7%
1377GPT OSS 20bOpenRouter harness, openai/gpt-oss-20b, auto-routing, public 90-day aggregate· OpenRouter benchmark exports65.6%
1378QwQ Plus· Epoch AI Benchmarking Hub data65.4%
1379QwQ 32B· Epoch AI Benchmarking Hub data65.3%
1380GPT-4.1 miniOpenRouter harness, openai/gpt-4.1-mini-2025-04-14, auto-routing, public 90-day aggregate· OpenRouter benchmark exports65.2%
1381Qwen3 30B A3B InstructOpenRouter harness, qwen/qwen3-30b-a3b-instruct-2507, auto-routing, public 90-day aggregate· OpenRouter benchmark exports65.2%
1382Qwen3 30B A3B InstructOpenRouter harness, qwen/qwen3-30b-a3b-instruct-2507, Alibaba, public 90-day aggregate· OpenRouter benchmark exports65.2%
1383DeepSeek R1OpenRouter harness, deepseek/deepseek-r1-0528, Novita, public 90-day aggregate· OpenRouter benchmark exports65.2%
1384Nemotron 3.5 LightningOpenRouter harness, nvidia/nemotron-3.5-lightning-20260807, Darkbloom, public 90-day aggregate· OpenRouter benchmark exports65.1%
1385Qwen3 32BOpenRouter harness, qwen/qwen3-32b-04-28, Groq, public 90-day aggregate· OpenRouter benchmark exports65%
1386GPT-4.1 miniOpenRouter harness, openai/gpt-4.1-mini-2025-04-14, OpenAI, public 90-day aggregate· OpenRouter benchmark exports64.9%
1387qwen3-vl-30bOpenRouter harness, qwen/qwen3-vl-30b-a3b-instruct, Novita, public 90-day aggregate· OpenRouter benchmark exports64.9%
1388Llama 4 MaverickOpenRouter harness, meta-llama/llama-4-maverick-17b-128e-instruct, Novita, public 90-day aggregate· OpenRouter benchmark exports64.5%
1389GPT OSS 20bOpenRouter harness, openai/gpt-oss-20b, Darkbloom, public 90-day aggregate· OpenRouter benchmark exports64.5%
1390qwen3-vl-30bOpenRouter harness, qwen/qwen3-vl-30b-a3b-instruct, auto-routing, public 90-day aggregate· OpenRouter benchmark exports64.4%
1391DeepSeek R1 Distill Qwen 32B· Epoch AI Benchmarking Hub data64.1%
1392Gemini 2.0 Flash· Epoch AI Benchmarking Hub data64.1%
1393GPT-5.4 mininone· Epoch AI Benchmarking Hub data64.1%
1394Llama 4 MaverickOpenRouter harness, meta-llama/llama-4-maverick-17b-128e-instruct, Parasail, public 90-day aggregate· OpenRouter benchmark exports64.1%
1395Qwen3 30B A3B InstructOpenRouter harness, qwen/qwen3-30b-a3b-instruct-2507, Ambient, public 90-day aggregate· OpenRouter benchmark exports64.1%
1396GPT-4.1 miniOpenRouter harness, openai/gpt-4.1-mini-2025-04-14, Azure, public 90-day aggregate· OpenRouter benchmark exports64%
1397Qwen3 14B· Epoch AI Benchmarking Hub data63.8%
1398GPT 4.1OpenRouter harness, openai/gpt-4.1-2025-04-14, auto-routing, public 90-day aggregate· OpenRouter benchmark exports63.7%
1399Qwen3 VL 235BOpenRouter harness, qwen/qwen3-vl-235b-a22b-instruct, Venice, public 90-day aggregate· OpenRouter benchmark exports63.7%
1400GPT 4.1OpenRouter harness, openai/gpt-4.1-2025-04-14, Azure, public 90-day aggregate· OpenRouter benchmark exports63.7%

Showing 1,351–1,400 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)