Up to four models
GPT-5 vs MiniMax-M3
On the index (GPT-4 = 100), GPT-5 scores 149 and MiniMax-M3 147. 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
149133–164
WeightsClosed
ReleasedAug 2025
Price in / out$1.25 / $10
Context400K
Core tests taken6 of 9
147131–164
WeightsOpen
ReleasedJun 2026
Price in / out$0.30 / $1.2
Context1.05M
Core tests taken4 of 9
GPT-5 and MiniMax-M3 are too close to call (1 point apart, within the uncertainty), ahead on 0 of 1 shared core tests, at 6.5× the price.
Test by testthird-party results
GPT-5
MiniMax-M3
Every result as a table
| Test | GPT-5 | MiniMax-M3 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 86.2% | 90.9% |
| GPQA Diamond (Vals AI) | 85.6% | 92.7% |
| MMLU Pro | 86.5% | 84.2% |
| MMMU Pro | 81.5% | 81.2% |
| SimpleBench | 56.7% | 45.8% |
| Maths | ||
| AIME-style maths (OTIS mock) | 91.4% | 71.1% |
| Chess puzzles | 36.0% | 17.0% |
| Coding | ||
| LiveCodeBench | 85.9% | 82.2% |
| SWE-bench | 69.0% | 75.0% |
| Vibe Code Bench v1.1 | 20.1% | 47.6% |
| Agents | ||
| DTBench | 90.7% | 78.9% |
| LMCA | 40.0% | 33.7% |
| Mystery game puzzles | 23.0% | 8.0% |
| Professional work | ||
| CorpFin v2 | 61.1% | 68.1% |
| LegalBench | 86.0% | 85.4% |
| MedCode | 49.6% | 46.3% |
| MedScribe | 83.7% | 87.3% |
| MortgageTax | 65.5% | 68.4% |
| TaxEval v2 | 73.4% | 72.7% |
Task length · METR42 sec
Tests at least two of these models have taken. Bold rows are the core tests.