Benchmarks
Frontierswe
Models scored
12
Best score
0.9
Metric
Dominance
Frontierswe is an AI evaluation tracked by Epoch AI, with 12 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 2026 to June 2026. The best score recorded is 0.9, measured as Dominance. Models come from OpenAI, Anthropic, Google DeepMind, Moonshot, Z.ai (Zhipu AI), DeepSeek, Alibaba.
Full record
- Score metric
- Dominance
- Models scored
- 12
- Best score recorded
- 0.9
- Earliest model scored
- Jan 27, 2026
- Most recent model scored
- Jun 9, 2026
- Third-party reported
- Yes
Leaderboard
| 01 | claude-fable-5_unknown | Anthropic | 0.9 |
| 02 | claude-opus-4-8_unknown | Anthropic | 0.78 |
| 03 | gpt-5.5_unknown | OpenAI | 0.76 |
| 04 | claude-opus-4-7_unknown | Anthropic | 0.66 |
| 05 | claude-opus-4-6_unknown | Anthropic | 0.59 |
| 06 | gpt-5.4-2026-03-05_unknown | OpenAI | 0.56 |
| 07 | gemini-3.1-pro-preview | Google DeepMind | 0.41 |
| 08 | glm-5.1 | Z.ai (Zhipu AI) | 0.32 |
| 09 | deepseek-v4-pro_unknown | DeepSeek | 0.31 |
| 10 | kimi-k2.6 | Moonshot | 0.28 |
| 11 | kimi-k2.5 | Moonshot | 0.27 |
| 12 | qwen3.6-plus | Alibaba | 0.24 |
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