Up to four models
MiniMax-M2.5 vs MiniMax-M2.1
On the index (GPT-4 = 100), MiniMax-M2.5 scores 144 and MiniMax-M2.1 135. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
144128–160
WeightsOpen
ReleasedFeb 2026
Price in / out$0.29 / $1.2
Context198K
Core tests taken1 of 9
MiniMax-M2.5 and MiniMax-M2.1 are too close to call (8 points apart, within the uncertainty).
Test by testthird-party results
Every result as a table
| Test | MiniMax-M2.5 | MiniMax-M2.1 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Vals AI) | 82.1% | 78.5% |
| MMLU Pro | 80.1% | 87.1% |
| Coding | ||
| Terminal-Bench 2.0 (Terminus 2 runs) | 42.3% | 29.2% |
| LiveCodeBench | 79.2% | 81.8% |
| SWE-bench | 74.2% | 74.8% |
| Professional work | ||
| CorpFin v2 | 59.6% | 58.9% |
| LegalBench | 80.0% | 75.4% |
| TaxEval v2 | 68.2% | 66.3% |
Tests at least two of these models have taken. Bold rows are the core tests.