xbench-ScienceQA: leaderboard
xbench's science question board (xbench.org): graduate-level science questions answered with search turned off and graded by a gemini-3.5-flash judge; the score is the average over five runs. The publisher keeps runs of older model versions and records the reasoning effort of each run; GPT-6 Astra (API modelId openai/gpt-6-astra-pro) and Deepseek-V4-Flash (API release and evaluation dates point to the 0731 checkpoint while modelId and link point to the bare April repo) are held because their checkpoint identities are ambiguous.
Metric: Average score (%). Source: xbench.org. Saturation forecast: Around September 2027. 28 models tracked. Updated 19 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 4.8 | 76.4 | #64 | |
| 2 | Claude Opus 5.5 | 76.4 | #9 | |
| 3 | Qwen 3.8 Max | 73.4 | #66 | |
| 4 | Claude Fable 5 | 73.4 | #32 | |
| 5 | Claude Opus 4.7 | 73 | #85 | |
| 6 | GPT-5.5 Pro | High | 73 | #40 |
| 7 | DeepSeek V4.1 Flash | Max | 72.6 | #69 |
| 8 | Gemini 3.8 Flash | High | 72.4 | #43 |
| 9 | Grok 4.5 | 72.4 | #90 | |
| 10 | GPT-5.4 Pro | xHigh | 72.2 | #95 |
| 11 | Gemini 3 Pro (Preview) | 71.6 | #120 | |
| 12 | Kimi K3 | 71.2 | #61 | |
| 13 | Seed 2.1 Pro | 71 | #148 | |
| 14 | GPT-5.6 Pro Sol | 71 | #31 | |
| 15 | GPT-5.4 | 70.8 | #138 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=xbench-scienceqa · How It Works · Data refreshed daily, snapshot 2026-11-20.