Benchmarks
GDPval
Models scored
11
Best score
0.5
Metric
Win Rate (%)
GDPval is an AI evaluation tracked by Epoch AI, with 11 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 November 2024 to December 2025. The best score recorded is 0.5, measured as Win Rate (%). Models come from OpenAI, Anthropic, Google DeepMind, xAI.
Full record
- Score metric
- Win Rate (%)
- Models scored
- 11
- Best score recorded
- 0.5
- Earliest model scored
- Nov 20, 2024
- Most recent model scored
- Dec 11, 2025
- Third-party reported
- Yes
Leaderboard
| 01 | gpt-5.2-2025-12-11_none | OpenAI | 0.5 |
| 02 | claude-opus-4-5-20251101 | Anthropic | 0.46 |
| 03 | claude-opus-4-1-20250805 | Anthropic | 0.44 |
| 04 | claude-sonnet-4-5-20250929 | Anthropic | 0.42 |
| 05 | gemini-3-pro-preview | Google DeepMind | 0.4 |
| 06 | gpt-5-2025-08-07_medium | OpenAI | 0.35 |
| 07 | o3-2025-04-16_medium | OpenAI | 0.31 |
| 08 | o4-mini-2025-04-16_high | OpenAI | 0.25 |
| 09 | gemini-2.5-pro | Google DeepMind | 0.23 |
| 10 | grok-4-0709_high | xAI | 0.21 |
| 11 | gpt-4o-2024-11-20 | OpenAI | 0.1 |
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