specs at a glance
| Leaderboard rank | #10 of 13 |
|---|---|
| SWE-bench Verified | 80.5% |
| SWE-bench Pro | 59.0% |
| Terminal-Bench | 66.0 (TB2.1) |
| Input price / 1M | $0.60 |
| Output price / 1M | — |
| Context window | 1M |
| Open weights | Yes |
| Access | Open weights · API |
| Maker | MiniMax |
how good is MiniMax M3 at coding?
MiniMax M3 sits at #10 of 13 ranked models, posting 80.5% on SWE-bench Verified — 15.7 points behind #1 GPT-5.6 Sol. On the harder SWE-bench Pro it scores 59.0%. Terminal-Bench (agentic terminal work): 66.0 (TB2.1).
Score provenance: Vendor-reported at launch (Jun 1, 2026). Independent comparison: vals.ai's bash-only harness measures MiniMax-M3 at 75.0% ±1.94, 5.5 points lower, so treat the 80.5% as a best-case number.
what does MiniMax M3 cost?
$0.60 per 1M input tokens — #2 cheapest of the 13 models we track. Coding workloads are output-heavy, so weight the output rate when budgeting. Run your own volume through the AI API cost calculator for a monthly estimate.
where can you use it?
Available via Open weights · API. Because it ships open weights, you can also self-host it on your own hardware or any inference provider — with the version pinned so the model can't change under you.
Ranked on our AI Coding Leaderboard — scores confirmed against primary sources only, updated 2026-07-17.