# Qwen3.5 397B vs Qwen3.6-27B

> Side-by-side benchmark comparison for Qwen3.5 397B and Qwen3.6-27B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/qwen3-5-397b-vs-qwen3-6-27b
- Last updated: September 4, 2026

- Shared sourced benchmarks: 21
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Pick Qwen3.5 397B if you want the stronger benchmark profile. Qwen3.6-27B only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Qwen3.5 397B leads overall 56.44 to 52.73.
- The clearest category separation is in instruction following, where the averages are 0 for Qwen3.5 397B and 82.2 for Qwen3.6-27B.
- The biggest single benchmark swing is Claw-Eval in Agentic, with scores of 56.8% and 72.4%.
- Qwen3.6-27B is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Qwen3.6-27B also has the larger context window at 262K.

## Model Snapshot

| Property | Qwen3.5 397B | Qwen3.6-27B |
|----------|----------|----------|
| Creator | Alibaba | Alibaba |
| Type | Open Weight | Open Weight |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 128K | 262K |
| Overall Score | 56.44 | 52.73 |
| Benchmarks Covered | 38 | 38 |
| Pricing (input/output) | $0.60 / $3.60 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Coming soon
- Qwen3.5 397B public-lane score: 48.2 (Estimated · #78/151)
- Qwen3.6-27B public-lane score: 33.9 (Supported · #133/151)

| Benchmark | Qwen3.5 397B | Qwen3.6-27B | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 52.5% | 59.3% | Qwen3.6-27B |
| BrowseComp | 62% | Coming soon | Coming soon |
| Claw-Eval | 56.8% | 72.4% | Qwen3.6-27B |
| QwenClawBench | 51.8% | 53.4% | Qwen3.6-27B |
| τ³-bench results | 68.4% | Coming soon | Coming soon |
| VITA-Bench | 43.7% | Coming soon | Coming soon |
| DeepPlanning | 37.6% | Coming soon | Coming soon |
| Toolathlon | 36.3% | Coming soon | Coming soon |
| MCP Atlas | 46.1% | Coming soon | Coming soon |
| MCP-Tasks | 74.2% | Coming soon | Coming soon |
| WideResearch | 74.0% | Coming soon | Coming soon |
| Gert Labs | 46.76% | 54.84% | Qwen3.6-27B |
| ResearchClawBench | 14.2% | Coming soon | Coming soon |
| QwenWebBench | Coming soon | 1487 | Coming soon |
| AndroidWorld | Coming soon | 70.3% | Coming soon |

### Coding

- Winner: Coming soon
- Qwen3.5 397B public-lane score: 52.4 (Estimated · #56/183)
- Qwen3.6-27B public-lane score: 42.6 (Supported · #128/183)

| Benchmark | Qwen3.5 397B | Qwen3.6-27B | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 76.2% | 77.2% | Qwen3.6-27B |
| LiveCodeBench v6 | 83.6% | Coming soon | Coming soon |
| SWE-bench Pro | 50.9% | 53.5% | Qwen3.6-27B |
| SWE Multilingual | Coming soon | 71.3% | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 59.3% | Coming soon |
| LiveCodeBench | Coming soon | 83.9% | Coming soon |
| NL2Repo | Coming soon | 36.2% | Coming soon |

### Multimodal & Grounded

- Winner: Qwen3.5 397B
- Qwen3.5 397B public-lane score: 62.2 (#27/48)
- Qwen3.6-27B public-lane score: 51.5 (#35/48)

| Benchmark | Qwen3.5 397B | Qwen3.6-27B | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | 79% | 75.8% | Qwen3.5 397B |
| MathVision | 88.6% | Coming soon | Coming soon |
| CharXiv | 80.8% | 78.4% | Qwen3.5 397B |
| VideoMMMU | 84.7% | 84.4% | Qwen3.5 397B |
| ScreenSpot Pro | 65.6% | Coming soon | Coming soon |
| V* | 95.8% | 94.7% | Qwen3.5 397B |
| MMMU | Coming soon | 82.9% | Coming soon |
| RealWorldQA | Coming soon | 84.1% | Coming soon |
| DynaMath | Coming soon | 85.6% | Coming soon |
| MStar | Coming soon | 81.4% | Coming soon |
| SimpleVQA | Coming soon | 56.1% | Coming soon |
| CC-OCR | Coming soon | 81.2% | Coming soon |
| CountBench | Coming soon | 97.8% | Coming soon |
| RefCOCO (avg) | Coming soon | 92.5% | Coming soon |
| ERQA | Coming soon | 62.5% | Coming soon |
| Video-MME (with subtitle) | Coming soon | 87.7% | Coming soon |
| MLVU (M-Avg) | Coming soon | 86.6% | Coming soon |

### Reasoning

- Winner: Coming soon
- Qwen3.5 397B public-lane score: 59.8 (Unranked · 2 rankable rows)
- Qwen3.6-27B public-lane score: 73.7 (Unranked · 2 rankable rows)

| Benchmark | Qwen3.5 397B | Qwen3.6-27B | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | 63.2% | Coming soon | Coming soon |
| AI-Needle | 68.7% | Coming soon | Coming soon |

### Knowledge

- Winner: Coming soon
- Qwen3.5 397B public-lane score: 51.5 (Estimated · #82/181)
- Qwen3.6-27B public-lane score: 49 (Estimated · #95/181)

| Benchmark | Qwen3.5 397B | Qwen3.6-27B | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 88.4% | 87.8% | Qwen3.5 397B |
| SuperGPQA | 70.4% | 66% | Qwen3.5 397B |
| MMLU-Pro | 87.8% | 86.2% | Qwen3.5 397B |
| MMLU-Redux | 94.9% | 93.5% | Qwen3.5 397B |
| C-Eval | 93% | 91.4% | Qwen3.5 397B |
| HLE | 28.7% | 24% | Qwen3.5 397B |

### Instruction Following

- Winner: Coming soon
- Qwen3.5 397B public-lane score: 0 (#120/120)
- Qwen3.6-27B public-lane score: 82.2 (#50/120)

| Benchmark | Qwen3.5 397B | Qwen3.6-27B | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 92.6% | Coming soon | Coming soon |

### Multilingual

- Winner: Coming soon
- Qwen3.5 397B public-lane score: 69.7 (#5/12)
- Qwen3.6-27B public-lane score: Coming soon

| Benchmark | Qwen3.5 397B | Qwen3.6-27B | Winner |
|-----------|-----------|-----------|--------|
| MMLU-ProX | 84.7% | Coming soon | Coming soon |
| NOVA-63 | 59.1% | Coming soon | Coming soon |

### Mathematics

- Winner: Coming soon
- Qwen3.5 397B public-lane score: 74.2 (Unranked · 5 rankable rows)
- Qwen3.6-27B public-lane score: 72.8 (Unranked · 5 rankable rows)

| Benchmark | Qwen3.5 397B | Qwen3.6-27B | Winner |
|-----------|-----------|-----------|--------|
| AIME26 | 93.3% | 94.1% | Qwen3.6-27B |
| HMMT Feb 2025 | 94.8% | 93.8% | Qwen3.5 397B |
| HMMT Nov 2025 | 92.7% | 90.7% | Qwen3.5 397B |
| HMMT Feb 2026 | 87.9% | 84.3% | Qwen3.5 397B |
| MMAnswerBench | 80.9% | 80.8% | Qwen3.5 397B |

## FAQ

### Which is better overall, Qwen3.5 397B or Qwen3.6-27B?

Qwen3.5 397B is ahead overall on BenchLM right now.

### Where is the biggest gap between Qwen3.5 397B and Qwen3.6-27B?

The widest category gap is in instruction following, where the averages are 0 for Qwen3.5 397B and 82.2 for Qwen3.6-27B.

### How many benchmarks does Qwen3.5 397B cover on BenchLM?

Qwen3.5 397B currently has 38 sourced benchmark scores on BenchLM.

### How many benchmarks does Qwen3.6-27B cover on BenchLM?

Qwen3.6-27B currently has 38 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Qwen3.5 397B vs Qwen3.5 397B (Reasoning)](/compare/qwen3-5-397b-vs-qwen3-5-397b-reasoning)
- [Qwen3.6-27B vs Qwen3.5 397B (Reasoning)](/compare/qwen3-5-397b-reasoning-vs-qwen3-6-27b)
- [Qwen3.5 397B vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-qwen3-5-397b)
- [Qwen3.6-27B vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-qwen3-6-27b)

## Explore More

- [Qwen3.5 397B profile](/models/qwen3-5-397b)
- [Qwen3.6-27B profile](/models/qwen3-6-27b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)