# MiniMax M2.7 vs Qwen 3.6 Max (preview)

> Side-by-side benchmark comparison for MiniMax M2.7 and Qwen 3.6 Max (preview) across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/minimax-m2-7-vs-qwen3-6-max-preview
- Last updated: September 29, 2026

- Shared sourced benchmarks: 4
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.7

## Quick Verdict

Pick Qwen 3.6 Max (preview) 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

- Qwen 3.6 Max (preview) leads overall 54.95 to 47.85.
- The clearest category separation is in coding, where the averages are 36 for MiniMax M2.7 and 47.1 for Qwen 3.6 Max (preview).
- The biggest single benchmark swing is Terminal-Bench 2.0 in Agentic, with scores of 57% and 65.4%.
- Qwen 3.6 Max (preview) also has the larger context window at 256K.

## Model Snapshot

| Property | MiniMax M2.7 | Qwen 3.6 Max (preview) |
|----------|----------|----------|
| Creator | MiniMax | Alibaba |
| Type | Open Weight | Proprietary |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 200K | 256K |
| Overall Score | 47.85 | 54.95 |
| Benchmarks Covered | 23 | 10 |
| Pricing (input/output) | $0.30 / $1.20 | N/A |

## Category Breakdown

### Agentic

- Winner: Not comparable
- MiniMax M2.7 public-lane score: 29.1 (Supported · #82/117)
- Qwen 3.6 Max (preview) public-lane score: Coming soon

| Benchmark | MiniMax M2.7 | Qwen 3.6 Max (preview) | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 57% | 65.4% | Qwen 3.6 Max (preview) |
| 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% | Coming soon | Coming soon |
| Gert Labs | 40.40% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 48.7% | Coming soon | Coming soon |
| QwenClawBench | Coming soon | 59.0% | Coming soon |

### Coding

- Winner: Qwen 3.6 Max (preview)
- MiniMax M2.7 public-lane score: 36 (Supported · #77/143)
- Qwen 3.6 Max (preview) public-lane score: 47.1 (Supported · #47/143)

| Benchmark | MiniMax M2.7 | Qwen 3.6 Max (preview) | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified* | 75.4% | Coming soon | Coming soon |
| SWE-bench Pro | 56.2% | 57.3% | Qwen 3.6 Max (preview) |
| 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% | 42.9% | Qwen 3.6 Max (preview) |
| Vibe Code Bench | 27.04% | Coming soon | Coming soon |
| React Native Evals | 71.4% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 79.9% | Coming soon | Coming soon |
| SWE-bench (Vals) | 73.8% | 72.8% | MiniMax M2.7 |
| SciCode | Coming soon | 47% | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 65.4% | Coming soon |

### Reasoning

- Winner: Not comparable
- MiniMax M2.7 public-lane score: 76.1 (Unranked · 2 rankable rows)
- Qwen 3.6 Max (preview) public-lane score: Coming soon

### Knowledge

- Winner: Not comparable
- MiniMax M2.7 public-lane score: 43 (Supported · #86/169)
- Qwen 3.6 Max (preview) public-lane score: Coming soon

| Benchmark | MiniMax M2.7 | Qwen 3.6 Max (preview) | Winner |
|-----------|-----------|-----------|--------|
| GPQA-D | 87.0% | Coming soon | Coming soon |
| MMLU-Pro (Arcee) | 80.8% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 86.6% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 80.4% | Coming soon | Coming soon |
| SuperGPQA | Coming soon | 73.9% | Coming soon |

### Instruction Following

- Winner: Not comparable
- MiniMax M2.7 public-lane score: 91.6 (#10/124)
- Qwen 3.6 Max (preview) public-lane score: Coming soon

### Mathematics

- Winner: Not comparable
- MiniMax M2.7 public-lane score: Coming soon
- Qwen 3.6 Max (preview) public-lane score: 41.3 (Unranked · 2 rankable rows)

| Benchmark | MiniMax M2.7 | Qwen 3.6 Max (preview) | Winner |
|-----------|-----------|-----------|--------|
| AIME25 (Arcee) | 80.0% | Coming soon | Coming soon |
| FrontierMath v2 (Tiers 1-3) | Coming soon | 23.103% | Coming soon |
| FrontierMath v2 (Tier 4) | Coming soon | 4.167% | Coming soon |

## FAQ

### Which is better overall, MiniMax M2.7 or Qwen 3.6 Max (preview)?

Qwen 3.6 Max (preview) is ahead overall on BenchLM right now.

### Where is the biggest gap between MiniMax M2.7 and Qwen 3.6 Max (preview)?

The widest category gap is in coding, where the averages are 36 for MiniMax M2.7 and 47.1 for Qwen 3.6 Max (preview).

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

MiniMax M2.7 currently has 23 sourced benchmark scores on BenchLM.

### How many benchmarks does Qwen 3.6 Max (preview) cover on BenchLM?

Qwen 3.6 Max (preview) currently has 10 sourced benchmark scores on BenchLM.

## Related Comparisons

- [MiniMax M2.7 vs GPT-6 Astra](/compare/gpt-6-astra-vs-minimax-m2-7)
- [Qwen 3.6 Max (preview) vs GPT-6 Astra](/compare/gpt-6-astra-vs-qwen3-6-max-preview)
- [MiniMax M2.7 vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-minimax-m2-7)
- [Qwen 3.6 Max (preview) vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-qwen3-6-max-preview)

## Explore More

- [MiniMax M2.7 profile](/models/minimax-m2-7)
- [Qwen 3.6 Max (preview) profile](/models/qwen3-6-max-preview)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)