Project APE CRED: leaderboard
Models detect a planted error in a supplied solution. Detection recall uses 200 trials for each API or agent configuration, with agent harnesses and versions retained separately.
Metric: Detection recall (%). Source: ape.socialcatalystlab.org. 24 models tracked.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-6 Astra | (Low) (APE CRED run: harness=Codex CLI, version=0.153.4, native=codex6astra_low) | 99.5 | #8 |
| 2 | GPT-5.6 Sol | (High) (APE CRED run: harness=Codex CLI, version=0.144.4, native=codex56sol_high) | 99 | #33 |
| 3 | GPT-5.6 Luna | xHigh | 97.5 | #130 |
| 4 | GPT-5.6 Terra | (High) (APE CRED run: harness=Codex CLI, version=0.144.4, native=codex56terra_high) | 97 | #68 |
| 5 | GPT-5.5 | (High) (APE CRED run: harness=Codex CLI, version=0.142.5, native=codex_high) | 96.5 | #50 |
| 6 | Claude Fable 5 | (High) (APE CRED run: harness=Claude Code, version=2.1.215, native=fable5_high) | 96.5 | #28 |
| 7 | GPT-5.6 Pro Luna | 91 | #98 | |
| 8 | GLM-5.3 Flash | xHigh | 90 | #136 |
| 9 | GLM-5.2 | High | 89.5 | #152 |
| 10 | GPT-6 Luna | (High) (APE CRED run: harness=Codex CLI, version=0.156.1, native=codex6luna_high) | 87.5 | #105 |
| 11 | Claude Opus 4.8 | (Medium) (APE CRED run: harness=Claude Code, version=2.1.118, native=opus48_med) | 85 | #62 |
| 12 | DeepSeek V4 Pro | xHigh | 83.5 | #198 |
| 13 | Claude Sonnet 4.6 | (High) (APE CRED run: harness=Claude Code, version=2.1.107, native=sonnet_high) | 83.5 | #173 |
| 14 | DeepSeek V4 Flash | xHigh | 80.5 | #265 |
| 15 | Gemini 3.8 Flash | High | 79.5 | #39 |
No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=project-ape-cred · How It Works · Data refreshed daily, snapshot 2026-11-17.