Benchmarks
Algotune
Models scored
18
Best score
2.05
Metric
Score
Algotune is an AI evaluation tracked by Epoch AI, with 18 scored model versions on record. The scores here are reported by third parties rather than produced by Epoch AI running the evaluation itself.
Scored models span January 2025 to March 2026. The best score recorded is 2.05, measured as Score. Models come from OpenAI, Google DeepMind, Anthropic, DeepSeek, Z.ai (Zhipu AI),Tsinghua University, Alibaba.
Full record
- Score metric
- Score
- Models scored
- 18
- Best score recorded
- 2.05
- Earliest model scored
- Jan 20, 2025
- Most recent model scored
- Mar 5, 2026
- Third-party reported
- Yes
Leaderboard
| 01 | gpt-5.2-2025-12-11_medium | OpenAI | 2.05 |
| 02 | gemini-3.1-pro-preview | Google DeepMind | 2.02 |
| 03 | gpt-5.4-2026-03-05_high | OpenAI | 1.85 |
| 04 | gemini-3-pro-preview | Google DeepMind | 1.83 |
| 05 | claude-opus-4-5-20251101_unknown | Anthropic | 1.77 |
| 06 | o4-mini-2025-04-16_high | OpenAI | 1.72 |
| 07 | DeepSeek-R1 | DeepSeek | 1.7 |
| 08 | gpt-5-2025-08-07_high | OpenAI | 1.67 |
| 09 | glm-4.5_thinking | Z.ai (Zhipu AI),Tsinghua University | 1.52 |
| 10 | claude-sonnet-4-5-20250929_unknown | Anthropic | 1.52 |
| 11 | gemini-2.5-pro | Google DeepMind | 1.51 |
| 12 | claude-opus-4-6_high | Anthropic | 1.47 |
| 13 | Qwen3-Coder-480B-A35B-Instruct | Alibaba | 1.44 |
| 14 | openai/gpt-oss-120b_high | OpenAI | 1.41 |
| 15 | gpt-5-mini-2025-08-07_high | OpenAI | 1.38 |
| 16 | claude-opus-4-1-20250805_unknown | Anthropic | 1.34 |
| 17 | claude-opus-4-20250514_unknown | Anthropic | 1.33 |
| 18 | gpt-5-pro-2025-10-06_medium | OpenAI | 1.31 |
More benchmarks
SourceEpoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/benchmarks. Licensed under CC BY 4.0.
← All benchmarks