Epoch AI - Algotune — leaderboard
Metric: Score. Source: epoch.ai. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 (Medium) | 2.05 |
| 2 | Gemini 3.1 Pro (Preview) | 2.02 |
| 3 | GPT-5.4 (High) | 1.85 |
| 4 | Gemini 3 Pro (Preview) | 1.83 |
| 5 | Claude Opus 4.5 (20251101) (Unknown) | 1.77 |
| 6 | O4 Mini (2025-04-16) (High) | 1.72 |
| 7 | DeepSeek R1 | 1.7 |
| 8 | GPT-5 (High) | 1.67 |
| 9 | GLM-4.5 (Thinking) | 1.52 |
| 10 | Claude Sonnet 4.5 (Unknown) | 1.52 |
| 11 | Gemini 2.5 Pro | 1.51 |
| 12 | Claude Opus 4.6 (High) | 1.47 |
| 13 | Qwen 3 Coder 480B A35B Instruct | 1.44 |
| 14 | GPT-OSS-120B (High) | 1.41 |
| 15 | GPT-5 Mini (High) | 1.38 |
Interactive version: theaggregate.ai/benchmark?slug=epoch-ai-algotune · How the rankings work · Data refreshed daily, snapshot 2026-07-22.