CRED v0.92 - Execution
Science · 2026-07-20
The CRED v0.92 execution chapter measures detection recall on failures recorded in the deterministic Replication and Build Defects diagnosis supplied to every verifier.
Top models (higher is better)
| Model | Score |
|---|---|
| Sonnet 4.6 | 100.0 |
| Sonnet 5 | 100.0 |
| GPT-5.5 | 100.0 |
| GPT-5.6 Luna | 100.0 |
| GPT-5.6 Sol | 100.0 |
| Claude Fable 5 | 100.0 |
| GPT-5.6 Terra | 100.0 |
| GPT-6 Astra | 100.0 |
| GPT-6 Luna | 100.0 |
| Opus 4.8 | 100.0 |
| DeepSeek-V4-Flash | 100.0 |
| DeepSeek-V4-Pro | 100.0 |
| GLM-5.2 | 100.0 |
| Gemini 3 Flash Preview | 100.0 |
| Gemini 3.5 Flash | 100.0 |
| Mistral Small 3.2 24B Instruct 2506 | 100.0 |
| Mistral Large 3 675B Instruct 2512 | 100.0 |
| Hy3 preview | 100.0 |
| GPT-4.1 | 100.0 |
| GPT-4o (source unspecified) | 100.0 |
| GPT-5.6 Luna Pro | 100.0 |
| GLM-5.3 Flash | 100.0 |
| Gemini 3.7 Flash | 100.0 |
| Gemini 3.8 Flash | 100.0 |
| DeepSeek-V3-0324 | 100.0 |
| DeepSeek-R1 | 100.0 |
| DeepSeek-R1-0528 | 100.0 |
| DeepSeek-V3.1 | 100.0 |
| DeepSeek-V3.2 | 100.0 |
| GLM-4.5 | 100.0 |
| GLM 4.6 | 100.0 |
| GLM-4.7 | 100.0 |
| GLM-5 | 100.0 |
| Qwen3-235B-A22B | 100.0 |
| Qwen3 235B A22B Instruct 2507 | 100.0 |
| Llama 3.3 70B Instruct | 100.0 |
| Llama 4 Maverick Instruct | 100.0 |
| Kimi K2 Instruct | 100.0 |
| Kimi K2 Thinking | 100.0 |
| Kimi K2.5 | 100.0 |