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
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 | |
|---|---|---|
| 1251 | Claude Sonnet 4.5· Epoch AI Benchmarking Hub data | 73.7% |
| 1252 | Gemini 3.1 Flash Liteminimal· Epoch AI Benchmarking Hub data | 73.7% |
| 1253 | Claude Sonnet 4.6OpenRouter harness, anthropic/claude-4.6-sonnet-20260217, Google, public 90-day aggregate· OpenRouter benchmark exports | 73.7% |
| 1254 | Qwen3 235B A22B Instruct 2507OpenRouter harness, qwen/qwen3-235b-a22b-07-25, Parasail, public 90-day aggregate· OpenRouter benchmark exports | 73.7% |
| 1255 | Qwen3 235B A22B Instruct 2507OpenRouter harness, qwen/qwen3-235b-a22b-07-25, Google, public 90-day aggregate· OpenRouter benchmark exports | 73.6% |
| 1256 | Kimi K2.6OpenRouter harness, moonshotai/kimi-k2.6-20260420, DeepInfra, public 90-day aggregate· OpenRouter benchmark exports | 73.5% |
| 1257 | GPT OSS 120Bofficial 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. | 73.5% |
| 1258 | Claude Sonnet 4.6OpenRouter harness, anthropic/claude-4.6-sonnet-20260217, Claude Platform on AWS, public 90-day aggregate· OpenRouter benchmark exports | 73.5% |
| 1259 | Claude Sonnet 4.6OpenRouter harness, anthropic/claude-4.6-sonnet-20260217, Anthropic, public 90-day aggregate· OpenRouter benchmark exports | 73.5% |
| 1260 | Qwen3.6 35B A3BOpenRouter harness, qwen/qwen3.6-35b-a3b-20260415, Darkbloom, public 90-day aggregate· OpenRouter benchmark exports | 73.4% |
| 1261 | Nemotron 3.5 LightningOpenRouter harness, nvidia/nemotron-3.5-lightning-20260807, CoreWeave, public 90-day aggregate· OpenRouter benchmark exports | 73.3% |
| 1262 | Qwen3 235B A22B Instruct 2507OpenRouter harness, qwen/qwen3-235b-a22b-07-25, Venice, public 90-day aggregate· OpenRouter benchmark exports | 73.3% |
| 1263 | Qwen3 235B A22B Instruct 2507OpenRouter harness, qwen/qwen3-235b-a22b-07-25, Novita, public 90-day aggregate· OpenRouter benchmark exports | 73.3% |
| 1264 | MiMo V2.6 FlashOpenRouter harness, xiaomi/mimo-v2.6-flash-20260921, Relace, public 90-day aggregate· OpenRouter benchmark exports | 73.2% |
| 1265 | Claude Opus 4.1· Epoch AI Benchmarking Hub data | 73.2% |
| 1266 | DeepSeek V4 Pronone· Epoch AI Benchmarking Hub data | 73.2% |
| 1267 | Gemma 4 26B A4Bminimal· Epoch AI Benchmarking Hub data | 73.2% |
| 1268 | GPT 5.2none· Epoch AI Benchmarking Hub data | 73.2% |
| 1269 | MiMo V2.6 FlashOpenRouter harness, xiaomi/mimo-v2.6-flash-20260921, auto-routing, public 90-day aggregate· OpenRouter benchmark exports | 73.2% |
| 1270 | Claude Haiku 4.5OpenRouter harness, anthropic/claude-4.5-haiku-20251001, auto-routing, public 90-day aggregate· OpenRouter benchmark exports | 73.2% |
| 1271 | GPT OSS 120Bofficial 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. | 73.1% |
| 1272 | Claude Haiku 4.5launch-page setting· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 73% |
| 1273 | Claude Haiku 4.5OpenRouter harness, anthropic/claude-4.5-haiku-20251001, Amazon Bedrock, public 90-day aggregate· OpenRouter benchmark exports | 72.9% |
| 1274 | DeepSeek V3.1OpenRouter harness, deepseek/deepseek-chat-v3.1, Mara, public 90-day aggregate· OpenRouter benchmark exports | 72.9% |
| 1275 | Kimi K2.7 CodeOpenRouter harness, moonshotai/kimi-k2.7-code-20260612, DeepInfra, public 90-day aggregate· OpenRouter benchmark exports | 72.8% |
| 1276 | Qwen3 Next 80B A3B InstructOpenRouter harness, qwen/qwen3-next-80b-a3b-instruct-2509, Parasail, public 90-day aggregate· OpenRouter benchmark exports | 72.8% |
| 1277 | Gemini 2.5 FlashOpenRouter harness, google/gemini-2.5-flash, auto-routing, public 90-day aggregate· OpenRouter benchmark exports | 72.8% |
| 1278 | Claude Haiku 4.5OpenRouter harness, anthropic/claude-4.5-haiku-20251001, Azure, public 90-day aggregate· OpenRouter benchmark exports | 72.8% |
| 1279 | Nemotron 3.5 LightningOpenRouter harness, nvidia/nemotron-3.5-lightning-20260807, Phala, public 90-day aggregate· OpenRouter benchmark exports | 72.7% |
| 1280 | Claude Haiku 4.5OpenRouter harness, anthropic/claude-4.5-haiku-20251001, Anthropic, public 90-day aggregate· OpenRouter benchmark exports | 72.7% |
| 1281 | MiMo V2.6 FlashOpenRouter harness, xiaomi/mimo-v2.6-flash-20260921, Cohere, public 90-day aggregate· OpenRouter benchmark exports | 72.7% |
| 1282 | Kimi K2.7 CodeOpenRouter harness, moonshotai/kimi-k2.7-code-20260612, Tenstorrent, public 90-day aggregate· OpenRouter benchmark exports | 72.6% |
| 1283 | Qwen3 Max· Epoch AI Benchmarking Hub data | 72.6% |
| 1284 | Qwen3 235B A22B Instruct 2507OpenRouter harness, qwen/qwen3-235b-a22b-07-25, auto-routing, public 90-day aggregate· OpenRouter benchmark exports | 72.6% |
| 1285 | DeepSeek V4.1 FlashOpenRouter harness, deepseek/deepseek-v4.1-flash-20260910, Krea, public 90-day aggregate· OpenRouter benchmark exports | 72.3% |
| 1286 | GLM 5OpenRouter harness, z-ai/glm-5-20260211, Novita, public 90-day aggregate· OpenRouter benchmark exports | 72.3% |
| 1287 | GLM 5OpenRouter harness, z-ai/glm-5-20260211, Z.AI, public 90-day aggregate· OpenRouter benchmark exports | 72.3% |
| 1288 | GPT 5.4 Nanolow· Epoch AI Benchmarking Hub data | 72.2% |
| 1289 | Claude Haiku 4.5OpenRouter harness, anthropic/claude-4.5-haiku-20251001, Google, public 90-day aggregate· OpenRouter benchmark exports | 72.1% |
| 1290 | Qwen3 235B A22B Instruct 2507OpenRouter harness, qwen/qwen3-235b-a22b-07-25, DeepInfra, public 90-day aggregate· OpenRouter benchmark exports | 72.1% |
| 1291 | Qwen3 Next 80B A3B InstructOpenRouter harness, qwen/qwen3-next-80b-a3b-instruct-2509, Google, public 90-day aggregate· OpenRouter benchmark exports | 72.1% |
| 1292 | Qwen3 Next 80B A3B InstructOpenRouter harness, qwen/qwen3-next-80b-a3b-instruct-2509, auto-routing, public 90-day aggregate· OpenRouter benchmark exports | 72% |
| 1293 | MiMo V2.6 FlashOpenRouter harness, xiaomi/mimo-v2.6-flash-20260921, Makora, public 90-day aggregate· OpenRouter benchmark exports | 71.8% |
| 1294 | GPT 5minimal· Epoch AI Benchmarking Hub data | 71.7% |
| 1295 | GPT-5 miniminimal· Epoch AI Benchmarking Hub data | 71.7% |
| 1296 | Qwen3 Next 80B A3B InstructOpenRouter harness, qwen/qwen3-next-80b-a3b-instruct-2509, Alibaba, public 90-day aggregate· OpenRouter benchmark exports | 71.7% |
| 1297 | GPT-5 minimedium· Epoch AI Benchmarking Hub data | 71.7% |
| 1298 | Seed OSS 36B Instruct· Epoch AI Benchmarking Hub data | 71.5% |
| 1299 | GPT OSS 20bofficial model card Table 3 · reasoning high · no tools · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 71.5% |
| 1300 | Qwen3 VL 235BOpenRouter harness, qwen/qwen3-vl-235b-a22b-instruct, Parasail, public 90-day aggregate· OpenRouter benchmark exports | 71.4% |
Showing 1,251–1,300 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)