Mistral Large 4 Release - Surge Code Human Preference vs Mistral Large 4: leaderboard
Mistral Large 4 open-weight release post (2026-10-29): Surge Code blind side-by-side human preference on code. Each opponent was compared with the released Mistral Large 4 and no ties were reported; scores are the share of prompts where graders preferred the opponent's answer (100 minus Mistral's published win share). Preferred over Mistral Large 4 (%).
Metric: Preferred over Mistral Large 4 (%). Source: mistral.ai. Saturation forecast: Around February 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5.5 | 78 | #3 |
| 2 | Kimi K3 | 36 | #35 |
| 3 | GLM-5.3 | 36 | #44 |
No result here: #6 GPT-6 Astra, #7 GPT-6.1 Sol, #9 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=mistral-large-4-release-surge-code-human-preference-vs-mistral-large-4 · How It Works · Data refreshed daily, snapshot 2026-11-05.