Mistral Large 2512
Scorecard
Per-criterion scores not available for this model. It appears in the cross-part overview but is not part of the canonical Models 1–10 hand-graded set; only the headline composite is shown.
Per-part composites
| Part | Opus 4.7 (inline) | DeepSeek V4 Pro (judge) |
|---|---|---|
| Part A | 3.63 | 2.40 |
| Part B | 3.30 | 1.75 |
| Part C | 3.45 | 4.45 |
Notes from the evaluation
Mistral Large 2512 r1** | **12/12** | 13/15 | 8/10 | 6/8 | 3/5 | **3.63** | | **Mistral Large 2512 r2** | **12/12** | 13/15 | 8/10 | 6/8 | 3/5 | **3.65** | | **Mistral Large 2512 r3** | **12/12** | 13/15 | 8/10 | 6/8 | 3/5 | **3.68** | | **Qwen 3.5 397B r1** | 11/12 | 12/15 | 7/10 | 5/8 | 4/5 | **3.50** | | **Qwen 3.5 397B r2** | 11/12 | 13/15 | 8/10 | 5/8 | 4/5 | **3.55** | | **Qwen 3.5 397B r3**
Source files in the repo
Cross-judge composites: analysis/results_overview.md
Full report · PDF
Get the full report
All 111 questions, the complete rubric, per-model verdicts, and the methodology paper. Delivered as PDF within 60 seconds. CC-BY 4.0.