LiveK12Bench - Physics: leaderboard
Metric: Answer accuracy (%), pass@1 on the final answer, Physics questions, LiveK12Bench 2026-03 split of recent Chinese high-school exam papers, unified answer prompt, answers checked by a panel of three LLM judges that never grade their own model; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 86.2 |
| 2 | Gemini 3 Flash | 84.4 |
| 3 | Kimi K2.5 | 81.6 |
| 4 | Claude Opus 4.6 | 79.1 |
| 5 | Claude Sonnet 4.6 | 77.6 |
| 6 | Qwen 3 VL 235B A22B | 77.3 |
| 7 | GPT-5 | 70.9 |
| 8 | GLM-5 | 67.5 |
| 9 | GPT-5 Mini | 60.1 |
| 10 | GPT-4o | 29.1 |
Interactive version: theaggregate.ai/benchmark?slug=livek12bench-physics · How It Works · Data refreshed daily, snapshot 2026-10-07.