# MiniMax M2.7 vs MiniMax M3

> Side-by-side benchmark comparison for MiniMax M2.7 and MiniMax M3 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/minimax-m2-7-vs-minimax-m3
- Last updated: October 15, 2026

- Shared sourced benchmarks: 8
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Pick MiniMax M3 if you want the stronger benchmark profile. MiniMax M2.7 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- MiniMax M3 leads overall 54.94 to 48.14.
- The clearest category separation is in agentic, where the averages are 32.4 for MiniMax M2.7 and 39.4 for MiniMax M3.
- The biggest single benchmark swing is Claw-Eval in Agentic, with scores of 48.7% and 74.5%.
- MiniMax M3 also has the larger context window at 1M.

## Model Snapshot

| Property | MiniMax M2.7 | MiniMax M3 |
|----------|----------|----------|
| Creator | MiniMax | MiniMax |
| Type | Open Weight | Open Weight |
| Reasoning | Non-Reasoning | Non-Reasoning |
| Context | 200K | 1M |
| Overall Score | 48.14 | 54.94 |
| Benchmarks Covered | 29 | 27 |
| Pricing (input/output) | $0.30 / $1.20 | $0.30 / $1.20 |

## Category Breakdown

### Agentic

- Winner: MiniMax M3
- MiniMax M2.7 public-lane score: 32.4 (Supported · #88/126)
- MiniMax M3 public-lane score: 39.4 (Supported · #67/126)

| Benchmark | MiniMax M2.7 | MiniMax M3 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 57% | Coming soon | Coming soon |
| τ³-bench results | 67.6% | Coming soon | Coming soon |
| Toolathlon | 46.3% | Coming soon | Coming soon |
| MLE-Bench Lite | 66.6% | Coming soon | Coming soon |
| MM-ClawBench | 62.7% | Coming soon | Coming soon |
| Claw-Eval | 48.7% | 74.5% | MiniMax M3 |
| Gert Labs | 40.40% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 48.7% | 53.6% | MiniMax M3 |
| Terminal-Bench 2.1 | Coming soon | 66.0% | Coming soon |
| BrowseComp | Coming soon | 83.5% | Coming soon |
| OSWorld-Verified | Coming soon | 70.1% | Coming soon |
| MCP Atlas | Coming soon | 74.2% | Coming soon |
| BankerToolBench | Coming soon | 76.1% | Coming soon |
| ResearchClawBench | Coming soon | 19.8% | Coming soon |
| OSWorld 2.0 | Coming soon | 4.6% | Coming soon |

### Coding

- Winner: MiniMax M3
- MiniMax M2.7 public-lane score: 34.5 (Supported · #79/149)
- MiniMax M3 public-lane score: 36.5 (Supported · #73/149)

| Benchmark | MiniMax M2.7 | MiniMax M3 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified* | 75.4% | Coming soon | Coming soon |
| SWE-bench Pro | 56.2% | 59% | MiniMax M3 |
| SWE-Rebench | 51.9% | Coming soon | Coming soon |
| SWE Multilingual | 76.5% | Coming soon | Coming soon |
| Multi-SWE Bench | 52.7% | Coming soon | Coming soon |
| VIBE-Pro | 55.6% | Coming soon | Coming soon |
| NL2Repo | 39.8% | 42.1% | MiniMax M3 |
| Terminal-Bench 2.0 | 57.0% | Coming soon | Coming soon |
| Vibe Code Bench | 27.04% | Coming soon | Coming soon |
| React Native Evals | 71.4% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 79.9% | 82.2% | MiniMax M3 |
| SWE-bench (Vals) | 73.8% | 75.0% | MiniMax M3 |
| SWE-bench Verified | Coming soon | 80.5% | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 66.0% | Coming soon |
| VIBE V2 | Coming soon | 50.1% | Coming soon |
| SVG-Bench | Coming soon | 63.7% | Coming soon |
| KernelBench Hard | Coming soon | 28.8% | Coming soon |
| OpenHarmony Bench | Coming soon | 48.4% | Coming soon |

### Reasoning

- Winner: Not comparable
- MiniMax M2.7 public-lane score: 79.6 (Unranked · 2 rankable rows)
- MiniMax M3 public-lane score: 82.9 (#5/29)

### Multimodal & Grounded

- Winner: Not comparable
- MiniMax M2.7 public-lane score: Coming soon
- MiniMax M3 public-lane score: 61.5 (#43/54)

| Benchmark | MiniMax M2.7 | MiniMax M3 | Winner |
|-----------|-----------|-----------|--------|
| OfficeQA Pro | Coming soon | 45.1% | Coming soon |
| OmniDocBench 1.5 | Coming soon | 91.6% | Coming soon |
| MMMU-Pro | Coming soon | 78.1% | Coming soon |
| VideoMMMU | Coming soon | 84.6% | Coming soon |
| Video-MME (with subtitle) | Coming soon | 85.4% | Coming soon |

### Knowledge

- Winner: MiniMax M3
- MiniMax M2.7 public-lane score: 46 (Supported · #92/182)
- MiniMax M3 public-lane score: 49.6 (Supported · #81/182)

| Benchmark | MiniMax M2.7 | MiniMax M3 | Winner |
|-----------|-----------|-----------|--------|
| HLE | 28% | Coming soon | Coming soon |
| GPQA-D | 87.0% | Coming soon | Coming soon |
| MMLU-Pro (Arcee) | 80.8% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 86.6% | 92.7% | MiniMax M3 |
| MMLU-Pro (Vals) | 80.4% | 84.2% | MiniMax M3 |

### Instruction Following

- Winner: Directional only
- MiniMax M2.7 public-lane score: 93 (#13/146)
- MiniMax M3 public-lane score: 93.8 (#5/146)

### Mathematics

- Winner: Not comparable
- MiniMax M2.7 public-lane score: 70.5 (Unranked · 4 rankable rows)
- MiniMax M3 public-lane score: Coming soon

| Benchmark | MiniMax M2.7 | MiniMax M3 | Winner |
|-----------|-----------|-----------|--------|
| AIME25 (Arcee) | 80.0% | Coming soon | Coming soon |
| AIME26 | 89.8% | Coming soon | Coming soon |
| HMMT Nov 2025 | 81.0% | Coming soon | Coming soon |
| HMMT Feb 2026 | 72.7% | Coming soon | Coming soon |
| USAMO 2026 | Coming soon | 85.7% | Coming soon |

## FAQ

### Which is better overall, MiniMax M2.7 or MiniMax M3?

MiniMax M3 is ahead overall on BenchLM right now.

### Where is the biggest gap between MiniMax M2.7 and MiniMax M3?

The widest category gap is in agentic, where the averages are 32.4 for MiniMax M2.7 and 39.4 for MiniMax M3.

### How many benchmarks does MiniMax M2.7 cover on BenchLM?

MiniMax M2.7 currently has 29 sourced benchmark scores on BenchLM.

### How many benchmarks does MiniMax M3 cover on BenchLM?

MiniMax M3 currently has 27 sourced benchmark scores on BenchLM.

## Related Comparisons

- [MiniMax M2.7 vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-minimax-m2-7)
- [MiniMax M3 vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-minimax-m3)
- [MiniMax M2.7 vs GPT-6.1 Sol](/compare/gpt-6-1-sol-vs-minimax-m2-7)
- [MiniMax M3 vs GPT-6.1 Sol](/compare/gpt-6-1-sol-vs-minimax-m3)

## Explore More

- [MiniMax M2.7 profile](/models/minimax-m2-7)
- [MiniMax M3 profile](/models/minimax-m3)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)