MiniMax M2.1
- Made by
- MiniMax
- Released
- Announced in
- MiniMax M2.1: Significantly Enhanced Multi-Language Programming, Built for Real-World Complex Tasksminimax.io
- Event
- MiniMax M2.1
- API record
- /api/v1/models/minimax-m2-1
Benchmark results
| Benchmark | Score | Source check |
|---|---|---|
| Humanity's Last ExamNo tools · in-house run with Artificial Analysis Intelligence Index methods · reported later, in MiniMax M2.5: Built for Real-World Productivity. | 22.2% | CorroboratedThe same number is printed in 1 other lab document: 1 |
| SWE-bench Verified | 74.0% | CheckedA person checked this number against its source on 19 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.CorroboratedThe same number is printed in 1 other lab document: 1 |
| Droid (Factory AI) harness | 71.3% | CheckedA person checked this number against its source on 19 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. |
| mini-swe-agent harness | 67.0% | CheckedA person checked this number against its source on 19 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. |
| SWE-bench ProClaude Code harness; average of 4 runs · reported later, in MiniMax M2.5: Built for Real-World Productivity. · The source doesn't say whether this is the public or the commercial set | 49.7% | CheckedA person checked this number against its source on 20 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. |
| GPQA Diamondin-house run with Artificial Analysis Intelligence Index methods · reported later, in MiniMax M2.5: Built for Real-World Productivity. | 83.0% | CorroboratedThe same number is printed in 1 other lab document: 1 |
| BrowseCompwithout context management | 47.4% | CheckedA person checked this number against its source on 19 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. |
| with context management | 62.0% | CheckedA person checked this number against its source on 19 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.CorroboratedThe same number is printed in 1 other lab document: 1 |
| Terminal-Bench 2.0 | 47.9% | CheckedA person checked this number against its source on 19 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.CorroboratedThe same number is printed in 1 other lab document: 1 |
Sources
Reported by MiniMax
