# Qwen3.5-122B-A10B vs Qwen3.5 397B

> Side-by-side benchmark comparison for Qwen3.5-122B-A10B and Qwen3.5 397B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/qwen3-5-122b-a10b-vs-qwen3-5-397b
- Last updated: September 29, 2026

- Shared sourced benchmarks: 12
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.7

## Quick Verdict

Pick Qwen3.5 397B if you want the stronger benchmark profile. Qwen3.5-122B-A10B 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 51 to 39.86.
- The clearest category separation is in instruction following, where the averages are 91.6 for Qwen3.5-122B-A10B and 0 for Qwen3.5 397B.
- The biggest single benchmark swing is SWE-bench Verified in Coding, with scores of 72% and 76.2%.
- Qwen3.5-122B-A10B is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Qwen3.5-122B-A10B also has the larger context window at 262K.

## Model Snapshot

| Property | Qwen3.5-122B-A10B | Qwen3.5 397B |
|----------|----------|----------|
| Creator | Alibaba | Alibaba |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Non-Reasoning |
| Context | 262K | 128K |
| Overall Score | 39.86 | null |
| Benchmarks Covered | 15 | 38 |
| Pricing (input/output) | $0.00 / $0.00 | $0.60 / $3.60 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- Qwen3.5-122B-A10B public-lane score: 23.7 (Estimated · #94/117)
- Qwen3.5 397B public-lane score: Coming soon

| Benchmark | Qwen3.5-122B-A10B | Qwen3.5 397B | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 49.4% | 52.5% | Qwen3.5 397B |
| BrowseComp | 63.8% | 62% | Qwen3.5-122B-A10B |
| OSWorld-Verified | 58% | Coming soon | Coming soon |
| Claw-Eval | Coming soon | 56.8% | Coming soon |
| QwenClawBench | Coming soon | 51.8% | Coming soon |
| τ³-bench results | Coming soon | 68.4% | Coming soon |
| VITA-Bench | Coming soon | 43.7% | Coming soon |
| DeepPlanning | Coming soon | 37.6% | Coming soon |
| Toolathlon | Coming soon | 36.3% | Coming soon |
| MCP Atlas | Coming soon | 46.1% | Coming soon |
| MCP-Tasks | Coming soon | 74.2% | Coming soon |
| WideResearch | Coming soon | 74.0% | Coming soon |
| Gert Labs | Coming soon | 46.76% | Coming soon |
| ResearchClawBench | Coming soon | 14.2% | Coming soon |

### Coding

- Winner: Not comparable
- Qwen3.5-122B-A10B public-lane score: 35.6 (Supported · #79/143)
- Qwen3.5 397B public-lane score: Coming soon

| Benchmark | Qwen3.5-122B-A10B | Qwen3.5 397B | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 72% | 76.2% | Qwen3.5 397B |
| LiveCodeBench v6 | Coming soon | 83.6% | Coming soon |
| SWE-bench Pro | Coming soon | 50.9% | Coming soon |

### Reasoning

- Winner: Not comparable
- Qwen3.5-122B-A10B public-lane score: 49.9 (Unranked · 3 rankable rows)
- Qwen3.5 397B public-lane score: 61 (Unranked · 2 rankable rows)

| Benchmark | Qwen3.5-122B-A10B | Qwen3.5 397B | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | 60.2% | 63.2% | Qwen3.5 397B |
| AI-Needle | Coming soon | 68.7% | Coming soon |

### Multimodal & Grounded

- Winner: Directional only
- Qwen3.5-122B-A10B public-lane score: 58 (#34/50)
- Qwen3.5 397B public-lane score: 63.9 (#28/50)

| Benchmark | Qwen3.5-122B-A10B | Qwen3.5 397B | Winner |
|-----------|-----------|-----------|--------|
| MMMU | 83.9% | Coming soon | Coming soon |
| MMVU | 74.7% | Coming soon | Coming soon |
| MathVision | 86.2% | 88.6% | Qwen3.5 397B |
| CharXiv | 77.2% | 80.8% | Qwen3.5 397B |
| V* | 93.2% | 95.8% | Qwen3.5 397B |
| MMMU-Pro | Coming soon | 79% | Coming soon |
| VideoMMMU | Coming soon | 84.7% | Coming soon |
| ScreenSpot Pro | Coming soon | 65.6% | Coming soon |

### Knowledge

- Winner: Not comparable
- Qwen3.5-122B-A10B public-lane score: 41.6 (Supported · #93/169)
- Qwen3.5 397B public-lane score: Coming soon

| Benchmark | Qwen3.5-122B-A10B | Qwen3.5 397B | Winner |
|-----------|-----------|-----------|--------|
| MMLU-Pro | 86.7% | 87.8% | Qwen3.5 397B |
| SuperGPQA | 67.1% | 70.4% | Qwen3.5 397B |
| GPQA | 86.6% | 88.4% | Qwen3.5 397B |
| MMLU-Redux | Coming soon | 94.9% | Coming soon |
| C-Eval | Coming soon | 93% | Coming soon |
| HLE | Coming soon | 28.7% | Coming soon |

### Multilingual

- Winner: Qwen3.5 397B
- Qwen3.5-122B-A10B public-lane score: 36.8 (#10/12)
- Qwen3.5 397B public-lane score: 69.7 (#5/12)

| Benchmark | Qwen3.5-122B-A10B | Qwen3.5 397B | Winner |
|-----------|-----------|-----------|--------|
| MMLU-ProX | 82.2% | 84.7% | Qwen3.5 397B |
| NOVA-63 | Coming soon | 59.1% | Coming soon |

### Instruction Following

- Winner: Directional only
- Qwen3.5-122B-A10B public-lane score: 91.6 (#11/124)
- Qwen3.5 397B public-lane score: 0 (#124/124)

| Benchmark | Qwen3.5-122B-A10B | Qwen3.5 397B | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 93.4% | 92.6% | Qwen3.5-122B-A10B |

### Mathematics

- Winner: Not comparable
- Qwen3.5-122B-A10B public-lane score: Coming soon
- Qwen3.5 397B public-lane score: 73.5 (Unranked · 5 rankable rows)

| Benchmark | Qwen3.5-122B-A10B | Qwen3.5 397B | Winner |
|-----------|-----------|-----------|--------|
| AIME26 | Coming soon | 93.3% | Coming soon |
| HMMT Feb 2025 | Coming soon | 94.8% | Coming soon |
| HMMT Nov 2025 | Coming soon | 92.7% | Coming soon |
| HMMT Feb 2026 | Coming soon | 87.9% | Coming soon |
| MMAnswerBench | Coming soon | 80.9% | Coming soon |

## FAQ

### Which is better overall, Qwen3.5-122B-A10B or Qwen3.5 397B?

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

### Where is the biggest gap between Qwen3.5-122B-A10B and Qwen3.5 397B?

The widest category gap is in instruction following, where the averages are 91.6 for Qwen3.5-122B-A10B and 0 for Qwen3.5 397B.

### How many benchmarks does Qwen3.5-122B-A10B cover on BenchLM?

Qwen3.5-122B-A10B currently has 15 sourced benchmark scores on BenchLM.

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

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

## Related Comparisons

- [Qwen3.5-122B-A10B vs Qwen3.5 397B (Reasoning)](/compare/qwen3-5-122b-a10b-vs-qwen3-5-397b-reasoning)
- [Qwen3.5 397B vs Qwen3.5 397B (Reasoning)](/compare/qwen3-5-397b-vs-qwen3-5-397b-reasoning)
- [Qwen3.5-122B-A10B vs GPT-6 Astra](/compare/gpt-6-astra-vs-qwen3-5-122b-a10b)
- [Qwen3.5 397B vs GPT-6 Astra](/compare/gpt-6-astra-vs-qwen3-5-397b)

## Explore More

- [Qwen3.5-122B-A10B profile](/models/qwen3-5-122b-a10b)
- [Qwen3.5 397B profile](/models/qwen3-5-397b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)