Drag a grip to reorder the columns, or press ← / → on a focused grip.2 / 5 models
Click a score to show or hide its row; hover a table row to remove it.
MiniMax M3.1 Flash leads on 2 of 3 shared benchmarks; MiniMax M3.1 Flash is ~97% cheaper per blended million tokens.
| Dimension | MiniMax M3.1 Flash | GPT 5.6-Sol |
|---|---|---|
| GPQA Diamond | — | 94.1% |
| HLE | — | 44.5% |
| Terminal-Bench 2.1 | — | 88.8% |
| Terminal-Bench 3.0 | — | 34.4% |
| Terminal-Bench 4.0 | — | 39.9% |
| DeepSWE v1.1 | 73.7% | 73% |
| ProgramBench | — | 23% |
| NL2Repo-Bench | — | 56.8% |
| CyberGym | 82% | 84.5% |
| SEC-Bench Pro | — | 74.3% |
| ExploitGym | — | 33.7% |
| Automation-Bench | — | 45.8% |
| Agents' Last Exam | 29.6% | 26.7% |
| BankerToolBench | 76.2% | — |
| Chartography (w/tools) | — | 79.9% |
| BabyVision (w/tools) | — | 88.9% |
| ZeroBench-main (w/tools) | — | 53% |
| Blended price | $0.375 /1M | $12.00 /1M |
| Full priceInput · Output · Cached input | $0.150 · $0.600 · $0.015 | $4.00 · $20.00 · $0.400 |
| Context window | 1,000K | 1,050K |
Adjust the monthly volume — every model recomputes instantly.
Estimates use list prices and ignore cached input, batch discounts, and off-peak rates.