MiniMax M2.7open
MiniMax
46.1#189 of 427 overall
- Input / output
- US$ 0,30 / US$ 1,20 US$ per 1M tokens
- Context
- 205K tokens
- Release
- 03/18/2026 release date
- Speed
- 0 tok/s first token in 0.00 s
Family history
The 6 versions of this family, from first to newest, by release date. Click a point to open that version.
See the data as a table
| Model | Released | Score | Rank | AA Intel. | Elo Arena |
|---|---|---|---|---|---|
| MiniMax M1 | 06/17/2025 | — | — | — | 1343 |
| MiniMax M2 | 10/23/2025 | 35.0 | #306 | — | 1340 |
| MiniMax M2.1 | 12/23/2025 | 46.8 | #184 | — | 1392 |
| MiniMax M2.5 | 02/12/2026 | 41.7 | #238 | — | 1359 |
| MiniMax M2.7 | 03/18/2026 | 46.1 | #189 | — | 1405 |
| MiniMax M3 | 05/31/2026 | 52.9 | #123 | 18.7 | 1431 |
Scores by source
Scores by sourcepercentile = % of ranked models it beats| Metric | Value | Percentile | Source |
|---|---|---|---|
| Arena text (Elo) weight 2 | 1405 | 47% | LMArena |
| Arena WebDev (Elo) weight 1 | 1398 | 32% | LMArena |
| Humanity's Last Exam weight 1 | 29.6 | 79% | Artificial Analysis |
| Terminal-Bench weight 1 | 0.0 | 22% | Artificial Analysis |
| GPQA Diamond | 87.4 | 85% | Artificial Analysis |
| Long-context reasoning | 78.3 | 81% | Artificial Analysis |
By category
| Category | Score | Rank | Metrics |
|---|---|---|---|
| Agentic | 36.0 | #100 | Terminal-Bench |
| Coding | 41.0 | #78 | Arena WebDev (Elo) |
| Reasoning | 71.2 | #70 | Humanity's Last Exam, GPQA Diamond |
| Research | 65.5 | #62 | Long-context reasoning |
| Design | 41.0 | #78 | Arena WebDev (Elo) |
| Chat | 48.5 | #104 | Arena text (Elo) |
History
RankingIA score on each collection day (hover to see the rank).
Daily collection started on 10/30/2026. The chart appears from the second day the model is ranked.