MiniMaxMiniMax M2.7
MiniMax M2.7 is a MiniMax open-weights reasoning model, released 18 Mar 2026. Its best configuration ranks #225 of 785 on the BenchLeader Index at 55.6 ±4.3, in the upper half. The ± is the point: 276 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in instruction following (74) and lowest in agents & tools (47). At $0.525 per million tokens blended it is mid-priced. Output speed of 55 tokens per second puts it slower than most, with a first answer in 46.8 s. Last measured 23 Oct 2026.
- Blended price
- $0.525/M
- $0.300 in · $1.20 out
- Output speed
- 55 tok/s
- measured by Artificial Analysis
- First answer
- 47 s
- first token 1.16 s
- Context
- 205k
- Full answer
- 56 s
- median, reasoning included
- Cost per run
- –
- Released
- 18 Mar 2026
- Overall index56
- Reasoning48
- Coding51
- Agents & tools47
- Maths54
- Knowledge55
- Instruction following74
- Human preference59
- Long context64
- Composite55
Versions
MiniMax has shipped 3 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| MiniMax M2.7this page | 18 Mar 2026 | 55.6 | #225 |
| MiniMax M2.5 | 12 Feb 2026 | 53.6 | #280 |
| MiniMax-M2.1 | 23 Dec 2025 | 53.8 | #268 |
How its index has moved
8 Sept 2026 to 21 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Hard Prompts | 1441#124 | Arena (LMArena) | |
| GPQA Diamond (AA)not in index | 87.4%#99 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 29.6%#154 | Artificial Analysis | |
| GPQA Diamond (Vals)not in index | 86.6%#39 | Vals AI | |
| CritPt | 0.6%#254 | Artificial Analysis |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| SciCode | 50.1%#109 | SciCode | |
| WeirdML | 37.0%#120 | WeirdML | |
| Arena Coding | 1480#106 | Arena (LMArena) | |
| Arena WebDev | 1398#92 | Arena (LMArena) | |
| SciCode (AA)not in index | 50.1%#110 | Artificial Analysis | |
| LiveCodeBench | 79.9%#69 | Vals AI | |
| SWE-bench (Vals)not in index | 73.8%#49 | Vals AI | |
| Code Migrationnot in index | 8.7%#62 | Vals AI | |
| ProgramBenchnot in index | 0.0%#32 | Vals AI | |
| Vibe Code Bench v1.1not in index | 11.9%#96 | Vals AI | |
| ALE-Benchnot in index | 599.3#97 | Epoch AI Benchmarking Hub | |
| Terminal-Bench 4.0 (AA)not in index | 0.0%#152 | Artificial Analysis | |
| Terminal-Bench 2.1 (AA)not in index | 55.4%#107 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Terminal-Bench | 45.1%#40 | Terminal-Bench | |
| Terminal-Bench Hard | 39.4%#57 | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 84.8%#97 | Artificial Analysis | |
| Terminal-Bench 2.1 (Vals) | 48.7%#61 | Vals AI | |
| τ³-Banking (AA) | 9.9%#144 | Artificial Analysis | |
| ITBench SRE (AA)not in index | 26.5%#36 | Artificial Analysis | |
| Analyst Agent (AA)not in index | 11.3%#44 | Artificial Analysis | |
| APEX-Agents (AA)not in index | 10.6%#29 | Artificial Analysis | |
| Finance Agent v2not in index | 27.9%#72 | Vals AI | |
| Harvey's Legal Agent Benchmark v1not in index | 0.0%#61 | Vals AI | |
| Legal Research Benchnot in index | 10.6%#72 | Vals AI | |
| Tax Agent Benchnot in index | 6.9%#65 | Vals AI | |
| Terminal-Bench 2.0 (Vals)not in index | 47.2%#22 | Vals AI | |
| ExploitBenchnot in index | 13.3%#9 | Epoch AI Benchmarking Hub | |
| GBAEvalnot in index | 0.0%#22 | Epoch AI Benchmarking Hub | |
| AutomationBenchnot in index | 4.4%#169 | Artificial Analysis | |
| GDP.pdf (AA)not in index | 6.0%#154 | Artificial Analysis |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| ProofBench | 3.0%#74 | Vals AI | |
| AIME (Vals) | 91.0%#26 | Vals AI | |
| Arena Maths | 1422#119 | Arena (LMArena) |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-Omniscience | 0.8#130 | Artificial Analysis | |
| MMLU-Pro | 80.4%#84 | Vals AI | |
| LegalBench | 84.0%#44 | Vals AI | |
| CorpFin | 61.2%#56 | Vals AI | |
| TaxEval | 66.6%#106 | Vals AI | |
| CaseLaw v2not in index | 60.9%#23 | Vals AI | |
| Excel Modeling Benchmarknot in index | 28.4%#64 | Vals AI | |
| MedCodenot in index | 34.4%#77 | Vals AI | |
| MedScribenot in index | 79.9%#58 | Vals AI | |
| AA-Omniscience: accuracynot in index | 26.8%#212 | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 64.4%#65 | Artificial Analysis |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| IFBench | 75.7%#27 | Artificial Analysis | |
| Arena Instruction Followingnot in index | 1409#125 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 1415#130 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1364#154 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1425#117 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1432#119 | Arena (LMArena) |
Long context
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-LCR | 78.3%#112 | Artificial Analysis | |
| MLCRnot in index | 5.6%#140 | Artificial Analysis |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Epoch Capabilities Indexnot in index | 145.8#82 | Epoch AI Benchmarking Hub | |
| AA Intelligence Index v4.3.2 | 22.8#197 | Artificial Analysis |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Groq | 284 tok/s | 0.26 s | $0.600 | $1.80 | 197k | – |
| MiniMax | 42 tok/s | 1.22 s | $0.300 | $1.20 | 205k | fp8 |
| MiniMax | 41 tok/s | 1.39 s | $0.600 | $2.40 | 205k | fp8 |
| AtlasCloud | 35 tok/s | 1.28 s | $0.300 | $1.20 | 197k | fp8 |
| NovitaAI | 34 tok/s | 1.42 s | $0.270 | $1.08 | 205k | fp8 |
| GMICloud | 31 tok/s | 1.23 s | $0.210 | $0.840 | 197k | fp8 |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.060 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0005 | $0.0004 | 52.3 s |
| Summarize a 30-page report | 12,000 / 600 | $0.0043 | $0.0022 | 57.8 s |
| Code edit | 6,000 / 1,500 | $0.0036 | $0.0025 | 1.2 min |
| Agentic coding session | 60,000 / 4,000 | $0.023 | $0.012 | 2.0 min |
| Structured extraction | 2,000 / 200 | $0.0008 | $0.0005 | 50.5 s |
See also
Questions people ask
- What are MiniMax M2.7's benchmark scores?
- As of 25 Oct 2026, MiniMax M2.7 scores 55.6 ±4.3 on the BenchLeader Index, strongest in instruction following (74) and weakest in agents & tools (47). That rests on 23 independent benchmark results, and every score on this page links to its publisher.
- How does MiniMax M2.7 rank?
- MiniMax M2.7 is #225 of 785 ranked configurations on 25 Oct 2026. 276 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- How much does MiniMax M2.7 cost per 1M tokens?
- As of 25 Oct 2026, MiniMax M2.7 costs $0.300 per 1M input tokens and $1.20 per 1M output tokens, $0.525 blended (three input tokens per output token).
- When was MiniMax M2.7 released?
- MiniMax released MiniMax M2.7 on 18 Mar 2026.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “MiniMax M2.7: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/minimax-m2-7.