Benchmarks
Blueprint Bench 2
Models scored
17
Best score
0.39
Metric
Score
Blueprint Bench 2 is an AI evaluation tracked by Epoch AI, with 17 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 October 2025 to July 2026. The best score recorded is 0.39, measured as Score. Models come from Anthropic, OpenAI, Google, xAI, Google DeepMind, Moonshot.
Full record
- Score metric
- Score
- Models scored
- 17
- Best score recorded
- 0.39
- Earliest model scored
- Oct 15, 2025
- Most recent model scored
- Jul 9, 2026
- Third-party reported
- Yes
Leaderboard
| 01 | claude-fable-5_unknown | Anthropic | 0.39 |
| 02 | gpt-5.5_unknown | OpenAI | 0.36 |
| 03 | gemini-3.5-flash_unknown | 0.34 | |
| 04 | gpt-5.6-sol_unknown | OpenAI | 0.34 |
| 05 | gpt-5.6-terra_unknown | OpenAI | 0.31 |
| 06 | grok-4.5_unknown | xAI | 0.27 |
| 07 | gpt-5.4-2026-03-05_unknown | OpenAI | 0.27 |
| 08 | gemini-3.1-pro-preview | Google DeepMind | 0.26 |
| 09 | claude-opus-4-7_unknown | Anthropic | 0.25 |
| 10 | gpt-5.6-luna_unknown | OpenAI | 0.23 |
| 11 | claude-opus-4-8_unknown | Anthropic | 0.15 |
| 12 | claude-sonnet-4-6_unknown | Anthropic | 0.07 |
| 13 | kimi-k2.6 | Moonshot | 0.04 |
| 14 | claude-haiku-4-5-20251001_unknown | Anthropic | 0 |
| 15 | grok-4-3 | xAI | 0 |
| 16 | grok-4-20 | xAI | 0 |
| 17 | gemini-3-flash-preview | Google DeepMind | 0 |
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