Model comparison
MiniMax M2.7 vs Qwen3.6-35B-A3B
Head-to-head evidence from 23 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Verified leaderboard positions: MiniMax M2.7 unranked; Qwen3.6-35B-A3B #31
BenchAlign evidence: MiniMax M2.7 supported; Qwen3.6-35B-A3B estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. MiniMax M2.7 and Qwen3.6-35B-A3B share 23 comparable benchmark results. 2 of 8 categories are comparable. 14 results are unique to MiniMax M2.7; 35 to Qwen3.6-35B-A3B.
Updated July 15, 2026- Shared results
- 23
- MiniMax M2.7 only
- 14
- Qwen3.6-35B-A3B only
- 35
- Comparable categories
- 2 / 8
Pick Qwen3.6-35B-A3B if you want the stronger benchmark profile. MiniMax M2.7 only becomes the better choice if agentic is the priority or you would rather avoid the extra latency and token burn of a reasoning model.
Confidence note. This is a partial-evidence comparison with 23 shared benchmark results across 5 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Qwen3.6-35B-A3B is clearly ahead on the provisional aggregate, 59 to 52. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Qwen3.6-35B-A3B's sharpest advantage is in coding, where it averages 73.8 against 53.3. The single biggest benchmark swing on the page is SWE-bench Pro, 56.2% to 49.5%. MiniMax M2.7 does hit back in agentic, so the answer changes if that is the part of the workload you care about most.
Qwen3.6-35B-A3B is the reasoning model in the pair, while MiniMax M2.7 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Qwen3.6-35B-A3B gives you the larger context window at 262K, compared with 200K for MiniMax M2.7.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | MiniMax M2.7 | Δ | Qwen3.6-35B-A3B |
|---|---|---|---|
| Coding | MiniMax M2.753.3 | Margin→ 20.5 | Qwen3.6-35B-A3B73.8 |
| Agentic | MiniMax M2.757.0 | Margin← 5.5 | Qwen3.6-35B-A3B51.5 |
| Knowledge | MiniMax M2.7Not measured | MarginNo overlap | Qwen3.6-35B-A3B51.8 |
| Math | MiniMax M2.7Not measured | MarginNo overlap | Qwen3.6-35B-A3B88.2 |
| Multimodal | MiniMax M2.7Not measured | MarginNo overlap | Qwen3.6-35B-A3B76.3 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
SWE-bench Pro
CodingA 56.2%B 49.5%Winner: MiniMax M2.7Δ 6.7SWE-bench Pro: MiniMax M2.7 scored 56.2%; Qwen3.6-35B-A3B scored 49.5%. MiniMax M2.7 wins this benchmark. - Source ↗
Terminal-Bench 2.0
AgenticA 57%B 51.5%Winner: MiniMax M2.7Δ 5.5Terminal-Bench 2.0: MiniMax M2.7 scored 57%; Qwen3.6-35B-A3B scored 51.5%. MiniMax M2.7 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | MiniMax M2.7 | Qwen3.6-35B-A3B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | MiniMax M2.7$0.3 input / $1.2 output | Qwen3.6-35B-A3BNot available | A complete price comparison is not available. |
| Generation speedtokens per second | MiniMax M2.745 tok/s | Qwen3.6-35B-A3BNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | MiniMax M2.72.53 s | Qwen3.6-35B-A3BNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | MiniMax M2.7200K | Qwen3.6-35B-A3B262K | Qwen3.6-35B-A3B lists the larger context window. |
Benchmark Deep Dive
AgenticMiniMax M2.7 wins18 benchmarks
| Benchmark | MiniMax M2.7 | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 57% | 51.5% | MiniMax M2.7 leads |
| τ²-bench resultsSource | 84.8% | 95.3% | Qwen3.6-35B-A3B leads |
| ToolathlonSource | 46.3% | 26.9% | MiniMax M2.7 leads |
| MLE-Bench LiteSource | 66.6% | — | Not comparable |
| MM-ClawBenchSource | 62.7% | — | Not comparable |
| Claw-EvalSource | 48.7% | 68.7% | Qwen3.6-35B-A3B leads |
| AA Agentic IndexSource | 25.6% | 21.4% | MiniMax M2.7 leads |
| APEX-Agents-AASource | 10.6% | — | Not comparable |
| GDPval-AASource | 32.9% | 27.4% | MiniMax M2.7 leads |
| GDPval-AASource | 1158 | 1049 | MiniMax M2.7 leads |
| Gert LabsSource | 40.40% | 42.65% | Qwen3.6-35B-A3B leads |
| QwenClawBenchSource | — | 52.6% | Not comparable |
| QwenWebBenchSource | — | 1397 | Not comparable |
| τ³-bench resultsSource | — | 67.2% | Not comparable |
| VITA-BenchSource | — | 35.6% | Not comparable |
| DeepPlanningSource | — | 25.9% | Not comparable |
| MCP AtlasSource | — | 62.8% | Not comparable |
| WideResearchSource | — | 60.1% | Not comparable |
CodingQwen3.6-35B-A3B wins15 benchmarks
| Benchmark | MiniMax M2.7 | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| SWE-bench Verified*Source | 75.4% | — | Not comparable |
| SWE-bench ProSource | 56.2% | 49.5% | MiniMax M2.7 leads |
| SWE-RebenchSource | 51.9% | — | Not comparable |
| SWE MultilingualSource | 76.5% | 67.2% | MiniMax M2.7 leads |
| Multi-SWE BenchSource | 52.7% | — | Not comparable |
| VIBE-ProSource | 55.6% | — | Not comparable |
| NL2RepoSource | 39.8% | 29.4% | MiniMax M2.7 leads |
| Vibe Code BenchSource | 27.04% | — | Not comparable |
| React Native EvalsSource | 71.4% | — | Not comparable |
| AA Coding IndexSource | 52.6% | 41.9% | MiniMax M2.7 leads |
| Terminal-Bench HardSource | 39.4% | 34.8% | MiniMax M2.7 leads |
| AA-SciCodeSource | 47.0% | 35.8% | MiniMax M2.7 leads |
| SWE-bench VerifiedSource | — | 73.4% | Not comparable |
| Terminal-Bench 2.0Source | — | 51.5% | Not comparable |
| LiveCodeBenchSource | — | 80.4% | Not comparable |
Reasoning2 benchmarks
Knowledge13 benchmarks
| Benchmark | MiniMax M2.7 | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| GPQA-DSource | 87.0% | — | Not comparable |
| MMLU-Pro (Arcee)Source | 80.8% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 38.1% | 31.6% | MiniMax M2.7 leads |
| AA-GPQA DiamondSource | 87.4% | 84.1% | MiniMax M2.7 leads |
| AA-HLESource | 28.1% | 20.2% | MiniMax M2.7 leads |
| AA-Omniscience IndexSource | 0.7% | -21.4% | MiniMax M2.7 leads |
| AA-Omniscience AccuracySource | 26.1% | 18.9% | MiniMax M2.7 leads |
| AA-Omniscience Hallucination RateSource | 34.4% | 49.7% | MiniMax M2.7 leads |
| MMLU-ProSource | — | 85.2% | Not comparable |
| SuperGPQASource | — | 64.7% | Not comparable |
| C-EvalSource | — | 90% | Not comparable |
| GPQASource | — | 86% | Not comparable |
| HLESource | — | 21.4% | Not comparable |
Math6 benchmarks
Multimodal17 benchmarks
| Benchmark | MiniMax M2.7 | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| GDPval-AASource | 1495 | — | Not comparable |
| Design Arena WebsiteSource | 1279 | — | Not comparable |
| MMMUSource | — | 81.7% | Not comparable |
| MMMU-ProSource | — | 75.3% | Not comparable |
| RealWorldQASource | — | 85.3% | Not comparable |
| OmniDocBench 1.5Source | — | 89.9% | Not comparable |
| CharXivSource | — | 78% | Not comparable |
| SimpleVQASource | — | 58.9% | Not comparable |
| CC-OCRSource | — | 81.9% | Not comparable |
| AI2D_TESTSource | — | 92.7% | Not comparable |
| RefCOCO (avg)Source | — | 92.0% | Not comparable |
| ODINW13Source | — | 50.8% | Not comparable |
| Video-MME (with subtitle)Source | — | 86.6% | Not comparable |
| Video-MME (w/o subtitle)Source | — | 82.5% | Not comparable |
| VideoMMMUSource | — | 83.7% | Not comparable |
| MLVU (M-Avg)Source | — | 86.2% | Not comparable |
| AA-MMMU-ProSource | — | 75.0% | Not comparable |
Inst. Following1 benchmarks
| Benchmark | MiniMax M2.7 | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| AA-IFBenchSource | 75.7% | 64.4% | MiniMax M2.7 leads |
Frequently Asked Questions (3)
Which is better, MiniMax M2.7 or Qwen3.6-35B-A3B?
Qwen3.6-35B-A3B is ahead on BenchLM's provisional leaderboard, 59 to 52. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 56.2% and 49.5%.
Which is better for coding, MiniMax M2.7 or Qwen3.6-35B-A3B?
Qwen3.6-35B-A3B has the edge for coding in this comparison, averaging 73.8 versus 53.3. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, MiniMax M2.7 or Qwen3.6-35B-A3B?
MiniMax M2.7 has the edge for agentic tasks in this comparison, averaging 57 versus 51.5. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
The AI models change fast. We track them for you.
A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.