Up to four models
GPT-5.4 vs MiniMax-M2.5
On the index (GPT-4 = 100), GPT-5.4 scores 166 and MiniMax-M2.5 144. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
GPT-5.4
166150–182
WeightsClosed
ReleasedMar 2026
Price in / out$2.5 / $15
Context1.05M
Core tests taken7 of 9
144128–160
WeightsOpen
ReleasedFeb 2026
Price in / out$0.29 / $1.2
Context198K
Core tests taken1 of 9
GPT-5.4 leads MiniMax-M2.5 by 22 points, ahead on 1 of 1 shared core tests, at 11× the price.
Test by testthird-party results
GPT-5.4
MiniMax-M2.5
Every result as a table
| Test | GPT-5.4 | MiniMax-M2.5 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Vals AI) | 91.7% | 82.1% |
| MMLU Pro | 87.5% | 80.1% |
| CL-bench | 27.9% | 11.4% |
| Coding | ||
| LiveCodeBench | 84.1% | 79.2% |
| SWE-bench | 78.2% | 74.2% |
| Vibe Code Bench v1.1 | 67.4% | 14.8% |
| Professional work | ||
| CorpFin v2 | 65.3% | 59.6% |
| LegalBench | 86.0% | 80.0% |
| TaxEval v2 | 74.0% | 68.2% |
| Novel problems | ||
| ARC-AGI-2 | 74.0% | 4.9% |
| ARC-AGI-1 | 93.7% | 63.7% |
Task length · METR45 sec
Tests at least two of these models have taken. Bold rows are the core tests.