MiniMax-M2.7
MiniMax-M2.7 (MiniMax) was released on Mar 18, 2026. In the Epoch AI capability ranking (ECI), it ranks #86 out of 267 models, with 145.88. On Arena, which measures human preference in blind comparisons, it has 1,454 ELO points (#92). Against models of the same generation, its best result is on SciCode: 50.1%, #13 of 45.
Where MiniMax-M2.7 stands out and where it falls behind, by the numbers
MiniMax-M2.7 has published results on 9 tests compiled by Epoch AI. The yardstick here is its generation: its position among the models released between Jun 21, 2025 and Jun 16, 2026 that took the same test. Against the whole archive, which includes 2023 models, a recent release lands near the top of almost everything, and that says nothing.
Where it stands out
Tests where it sits in the top third of its own generation.
Where it falls behind
Tests where it sits in the bottom half of its own generation.
See all 9 tests, one by one
| Test | Score | In its generation | Overall | Test record |
|---|---|---|---|---|
| CritPt | 0.6% | #39 / 49 (tied with 1) | #81 / 112 | 32.3% GPT-5.6 Sol |
| WeirdML | 37.0% | #51 / 54 | #82 / 112 | 93.6% GPT-6 Astra |
| SciCode | 50.1% | #13 / 45 | #47 / 104 | 66.9% Claude Opus 5.5 |
| ALE-Bench | 599 | #42 / 49 | #71 / 82 | 2,951 GPT-6 Astra |
| WebDev Arena | 1,398 | #28 / 48 | #61 / 82 | 1,820 Claude Opus 5.5 |
| ProofBench | 3.0% | #33 / 34 | #71 / 74 | 100.0% Claude Fable 5.1 |
| Terminal-Bench | 45.1% | #17 / 32 | #17 / 33 | 84.7% GPT-5.5 |
| Gbaeval | 0.0% | #15 / 16 (tied with 1) | #21 / 22 | 79.6% Claude Opus 5 |
| Exploitbench | 13.3% | #8 / 8 | #8 / 8 | 47.4% GPT-5.5 |
For each test, the model's best effort level counts, as in the ranking. Source of the scores: Epoch AI, under CC BY 4.0.
What to compare MiniMax-M2.7 with
The models from other labs closest in capability and released in the same period, at most two per lab. Click any of them to see its page.
| Model | Lab | ECI | ELO | LiveBench | Release |
|---|---|---|---|---|---|
| DeepSeek-V3.2 | DeepSeek | 146.11 | 1,455 | n/a | Dec 1, 2025 |
| DeepSeek-V4-Flash | DeepSeek | 146.05 | 1,468 | 65.5 | Apr 24, 2026 |
| Kimi K2 Thinking | Moonshot | 145.96 | n/a | n/a | Nov 6, 2025 |
| MiniMax-M2.7 | MiniMax | 145.88 | 1,454 | n/a | Mar 18, 2026 |
| Kimi K2 Thinking Turbo | Moonshot | 145.79 | 1,456 | n/a | Nov 6, 2025 |
| GLM-5 | Z.ai (Zhipu AI) | 145.78 | 1,511 | n/a | Feb 11, 2026 |
| Nemotron 3 Ultra | Nvidia | 145.77 | n/a | n/a | Jun 4, 2026 |
Other models from MiniMax
The models from the same lab closest in time, newest first.
| Model | Release | ECI | ELO | LiveBench | Access |
|---|---|---|---|---|---|
| MiniMax-M3 | Jun 1, 2026 | 147.13 | 1,471 | 67.3 | Open weights (restricted use) |
| MiniMax-M2.7 | Mar 18, 2026 | 145.88 | 1,454 | n/a | Open weights (non-commercial) |
| MiniMax-M2.5 | Feb 12, 2026 | 146.67 | 1,393 | n/a | Open weights (unrestricted) |
Have you used MiniMax-M2.7? Rate it
Users' opinion, not measurement: the rating is kept apart from the ranking and does not move anyone's position. One vote per browser, no sign-up, and you can change your rating later.
What people ask about MiniMax-M2.7
Where does MiniMax-M2.7 rank among AI models?
In the ROO3 AI Benchmark, ordered by the Epoch AI ECI, MiniMax-M2.7 ranks #86 out of 267 models, with an ECI of 145.88. The ECI is a composite index that combines several hard benchmarks into a single scale. The position changes when a new model comes out, and the page is refreshed six times a day.
What is MiniMax-M2.7 best at?
Against models of the same generation (released up to 9 months before and up to 3 months after it), the best relative results of MiniMax-M2.7 are: SciCode (#13 of 45). The yardstick is its position among the models of that period that took the same test.
Where do the numbers on this page come from?
From the same three sources as the ranking, all openly licensed: Epoch AI (ECI and individual tests, CC BY 4.0), Arena (human-preference ELO, CC BY 4.0) and LiveBench (overall average, CC BY-SA 4.0). ROO3 does not measure any model. When the page shows a figure published by the maker itself, it appears in the written analysis, labeled as the maker's, and never enters the ranking.
Where each number comes from
Epoch AI, "AI Benchmarking Hub". Published at epoch.ai. Data under the CC BY 4.0 licence, reordered by roo3.co.
The Arena (LMArena) leaderboard, from the public lmarena-ai/leaderboard-dataset on Hugging Face, under the CC BY 4.0 licence. We are not affiliated with the Arena.
LiveBench, by the LiveBench team, published at livebench.ai under the CC BY-SA 4.0 license. The overall average is recomputed by roo3.co with the same formula as the website (average of the categories), and those numbers stay under CC BY-SA 4.0. We are not affiliated with LiveBench.
← See the full ranking