General365: leaderboard
Metric: Accuracy (%) over all 1,460 problems (365 hand-written seeds and 1,095 expansions); numeric answers checked with math-verify, choice and text answers graded by GPT-4.1; temperature 1.0 for reasoning and 0.7 for chat models, highest available reasoning effort; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 26 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 62.8 |
| 2 | Gemini 3 Flash | 60.8 |
| 3 | GLM-5 (Thinking) | 59.9 |
| 4 | GPT-5 (High) | 58.6 |
| 5 | GPT-5.1 (High) | 58.2 |
| 6 | Qwen 3.5 397B A17B (Thinking) | 57.7 |
| 7 | DeepSeek V3.2 Speciale | 57.5 |
| 8 | GLM-4.7 (Thinking) | 57.4 |
| 9 | Qwen 3 Max (Thinking) | 57.2 |
| 10 | Kimi K2.5 (Thinking) | 56.4 |
| 11 | DeepSeek V3.2 (Thinking) | 54.9 |
| 12 | Grok 4.1 Fast (Reasoning) | 53.1 |
| 13 | Kimi K2 (Thinking) | 53 |
| 14 | GLM-4.6 (Thinking) | 52.9 |
| 15 | O4 Mini (High) | 51 |
Interactive version: theaggregate.ai/benchmark?slug=general365 · How It Works · Data refreshed daily, snapshot 2026-10-07.