Benchmarks
Btf3
Models scored
8
Best score
0.15
Metric
Pooled score
Btf3 is an AI evaluation tracked by Epoch AI, with 8 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 April 2026 to July 2026. The best score recorded is 0.15, measured as Pooled score. Models come from Anthropic, OpenAI.
Full record
- Score metric
- Pooled score
- Models scored
- 8
- Best score recorded
- 0.15
- Earliest model scored
- Apr 23, 2026
- Most recent model scored
- Jul 9, 2026
- Third-party reported
- Yes
Leaderboard
| 01 | claude-sonnet-5_xhigh | Anthropic | 0.15 |
| 02 | gpt-5.5_high | OpenAI | 0.14 |
| 03 | claude-opus-4-8_high | Anthropic | 0.14 |
| 04 | gpt-5.6-sol_high | OpenAI | 0.14 |
| 05 | claude-fable-5_high | Anthropic | 0.13 |
| 06 | claude-opus-4-8_xhigh | Anthropic | 0.13 |
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