MiniMax M3 (High): benchmark results
Provider: MiniMax. Released 2026-06-01. Access: Open.
Unified ELO 1707 ± 24, rank #349 of 2055 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SceneActBench - Articulated | 58.4 | Task score (0-100): 100 S2O articulated objects: rig a close | 60 |
| SceneActBench - Reconstruction | 9.6 | Task score (0-100): 100 3D-FRONT rooms from about 11 calibra | 60 |
| SceneActBench - Camera | 25.6 | Task score (0-100): 100 furnished 3D-FRONT scenes: recover t | 40 |
| MazeBench | 0 | Gems collected (gems) | 37.5 |
| GameLogicBench - Repo | 13.04 | Solve rate (%; the 23 Repo tasks (a mechanic inside a real o | 29.2 |
| CWE-Bench | 22.7 | Pass@1 (%) | 21.4 |
| GameLogicBench | 19.44 | Solve rate (%; all 72 tasks; one sample per model-scaffold c | 16.7 |
| GameLogicBench - Combo | 17.86 | Solve rate (%; the 28 Combo tasks (several interacting mecha | 16.7 |
| AI Coding Daily (OpenCode) - React-TS Code Quality | 15 | React-TS Code Quality (max 20) points, LLM-judged rubric sco | 15.2 |
| SceneActBench - Layout | 58.1 | Task score (0-100): 100 3D-FRONT rooms from one view: place | 10 |
| AI Coding Daily (OpenCode) - Laravel Code Quality | 15.3 | Laravel Code Quality (max 20) points, LLM-judged rubric scor | 8.7 |
| GameLogicBench - Atom | 28.57 | Solve rate (%; the 21 Atom tasks (one mechanic in a minimal | 8.3 |
Interactive version: theaggregate.ai/model?slug=minimax-m3-high · How It Works · Data refreshed daily, snapshot 2026-09-29.