M2.7
MiniMax · released Mar 18, 2026
MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...
Specification
- Context window
- 205K
- Max output
- 131K
- Knowledge cutoff
- Not stated
- Parameters
- 228.7B
- Licence
- other
- Serving providers
- 9
- Moderated
- No
- Uptime
- 100.0%
Intelligence
38.9
86th percentile
Coding
52.6
Coding Index
Agentic
25.9
Agentic Index
Output speed
307 t/s
Median across providers
Latency
304ms
Time to first token
Cost per task
$0.10
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- GPQA Diamond87.4%
- τ²-bench (Telecom)84.8%
- IFBench75.7%
- AA-LCR (long context)75.3%
- SciCode47.0%
- Terminal-Bench Hard39.4%
- Humanity's Last Exam29.6%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| GPQA Diamond | 87.4% |
| τ²-bench (Telecom) | 84.8% |
| IFBench | 75.7% |
| AA-LCR (long context) | 75.3% |
| SciCode | 47.0% |
| Terminal-Bench Hard | 39.4% |
| Humanity's Last Exam | 29.6% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- GPT-5.4 NanoOpenAI39.7
- Qwen3.7 PlusQwen39.4
- GLM 5 TurboZ.ai39.1
- M2.7MiniMax38.9
- Claude Opus 4.6Anthropic38.8
- MiMo-V2.5Xiaomi38.0
- Grok 4.20xAI38.0
- Grok 4.3xAI37.9
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| GPT-5.4 Nano | 39.7 |
| Qwen3.7 Plus | 39.4 |
| GLM 5 Turbo | 39.1 |
| M2.7 | 38.9 |
| Claude Opus 4.6 | 38.8 |
| MiMo-V2.5 | 38.0 |
| Grok 4.20 | 38.0 |
| Grok 4.3 | 37.9 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $0.27
- Output / 1M tokens
- $1.08
- Cached input / 1M
- $0.054
- Blended 3:1
- $0.473
One task, estimated
$0.10
- Input tokens
- 50,000
- Output tokens
- 80,000
- Profile
- Reasoning
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).