MiniMax-M2: benchmark scores, price and ranking
MiniMax-M2 from MiniMax ranks #330 of 743 LLMs on the LLMs Tiger aggregate benchmark score (48.7), based on 5 benchmark results captured up to 2026-10-13.
- Organisation
- MiniMax
- Type
- Open-weight / local model
- Open weights
- Yes
- Released
- 2025-10-27 (source: curated)
- Cheapest API price
- $0.300 in / $1.20 out per million tokens (via bedrock, observed 2026-10-13T20:47Z)
- Aggregate rank
- #330 of 743 (score 48.7)
Relative to other models, MiniMax-M2 is strongest on MMLU-Pro (#25 of 136) and weakest on Vending-Bench 2 (#17 of 19).
Across the 5 benchmarks where at least ten models are scored, MiniMax-M2 is in the top 10% on 0 and in the top half on 2.
Its cheapest listed input price, $0.300 per million tokens, is lower than that of 58% of the 427 models with a listed price.
MiniMax-M2 benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| MMLU-Pro | 82.0% | #25 of 136 | HuggingFace MMLU-Pro leaderboard | 2026-10-13 |
| SWE-bench Verified | 61.0% | #31 of 73 | SWE-bench Verified leaderboard | 2026-10-13 |
| Terminal-Bench 2.0 | 30.0% | #18 of 28 | Epoch AI Benchmarking Hub | 2026-10-13 |
| WebDev Arena | 1,298 | #54 of 67 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Vending-Bench 2 | $161 | #17 of 19 | Epoch AI Benchmarking Hub | 2026-10-13 |
About MiniMax-M2
MiniMax-M2 is an open-weight model that can run on your own hardware from MiniMax. It was released on 2025-10-27, according to the developer's announcement. The cheapest API listing we track charges $0.300 per million input tokens and $1.20 per million output tokens, through bedrock. We hold 5 benchmark results for it across 3 areas, and none is in the top tenth of its board.
Where MiniMax-M2 stands
On our aggregate score, MiniMax-M2 is #330 of 743 ranked models, around the middle of the table. Its score is 48.7; the scale is centred on 50, so it sits 1.3 points below the typical model. That beats 56% of the ranked field. Among the 6 ranked MiniMax models it is #3. The next one up is MiniMax-M2.1 at 49.9. The next one down is MiniMax-M2.5 at 46.8.
MiniMax-M2, benchmark by benchmark
MMLU-Pro puts MiniMax-M2 at 82.0%, #25 of 136. That beats 82% of the models tested, but 6.1 points short of Darwin-180B-RSI (88.1%). The results either side are seed-oss-36b-instruct (82.7%) and NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 (81.9%). It covers 57-subject knowledge + reasoning. The board median is 55.3%, so MiniMax-M2 is 26.7 points above it. Source: HuggingFace MMLU-Pro leaderboard, captured 2026-10-13.
On SWE-bench Verified, MiniMax-M2 reaches 61.0%. It ranks #31 of 73, ahead of 58% of the field, and 22.5 points behind Claude Opus 4.7 (max) at 83.5%. The results either side are swe-search (62.2%) and claude-3-7-sonnet-20250219 (61.0%). It covers real GitHub issues resolved. The board median is 56.4%, so MiniMax-M2 is 4.6 points above it. Source: SWE-bench Verified leaderboard, captured 2026-10-13.
MiniMax-M2 lands below the middle on Terminal-Bench 2.0: 30.0%, #18 of 28, with 61% of the field scoring higher. Gemini 3 Pro Preview leads at 69.4%; the closest result above is GLM-4.7 at 33.4%. It covers real terminal tasks (agent + model). The board median is 37.3%, so MiniMax-M2 is 7.3 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
WebDev Arena is a weak spot. MiniMax-M2 scores 1,298, #54 of 67, behind 79% of the models measured. The leader, Claude Opus 5.5 (max), reaches 1,820. It covers building web apps, crowd-voted (Elo). The board median is 1,433, so MiniMax-M2 is 136 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Vending-Bench 2 is a weak spot. MiniMax-M2 scores $161, #17 of 19, behind 84% of the models measured. The leader, Kimi K2.6, reaches $6,205. It covers running a vending business for a year (final money, $). The board median is $2,377, so MiniMax-M2 is 2,216 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
Software engineering: uneven, ahead of 38% of the field on average across 3 benchmarks. Its best board here is SWE-bench Verified (#31 of 73) and its weakest is WebDev Arena (#54 of 67).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so MiniMax-M2 costs less than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), DeepSeek V4 Flash 0731 (max) ($0.016, 53.1). Similar scores cost more on Devstral (2512) ($0.400) and GLM-4.5 Thinking ($0.400).
Release history
The MiniMax model released before it was MiniMax-M1-80k on 2025-06-13, which scores 50.9. The next one was MiniMax-M2.1 on 2025-12-23, at 49.9.
Reading these numbers
The 5 scores on this page come from 3 sources: Epoch AI Benchmarking Hub (3), HuggingFace MMLU-Pro leaderboard (1), SWE-bench Verified leaderboard (1). 1 of them come from an official leaderboard and 4 from datasets or third-party runs. With 5 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #327 GLM-4.5-Air (48.7)
- #328 GPT-5.1 Codex Mini (48.7)
- #329 Amazon.nova Premier v1:0 (48.7)
- #331 gemini-1.5-flash-exp-0827 (48.7)
- #332 grok-4.20-beta-0309-reasoning (48.7)
- #333 qwen3-4b-instruct-2507 (48.7)
More from MiniMax
- MiniMax-M1-80k (#160, 50.9)
- MiniMax-M2.1 (#228, 49.9)
- MiniMax-M2.5 (#484, 46.8)
- MiniMax-M3 (#566, 45.6)
- MiniMax-M2.7 (#568, 45.6)
Compare it on the live leaderboard → · How the aggregate score works