# Qwen3.5 397B vs Step 3.7 Flash

> Side-by-side benchmark comparison for Qwen3.5 397B and Step 3.7 Flash across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/qwen3-5-397b-vs-step-3-7-flash
- Last updated: October 15, 2026

- Shared sourced benchmarks: 7
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Qwen3.5 397B leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Qwen3.5 397B has the higher overall point estimate 55.47 to 43.7. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in knowledge, where the averages are 53.2 for Qwen3.5 397B and 45 for Step 3.7 Flash.
- The biggest single benchmark swing is Toolathlon in Agentic, with scores of 36.3% and 49.5%.
- Step 3.7 Flash is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Step 3.7 Flash also has the larger context window at 256K.

## Model Snapshot

| Property | Qwen3.5 397B | Step 3.7 Flash |
|----------|----------|----------|
| Creator | Alibaba | StepFun |
| Type | Open Weight | Open Weight |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 128K | 256K |
| Overall Score | 55.47 | 43.7 |
| Benchmarks Covered | 62 | 11 |
| Pricing (input/output) | $0.60 / $3.60 | $0.20 / $1.15 |

## Category Breakdown

### Agentic

- Winner: Directional only
- Qwen3.5 397B public-lane score: 44.2 (Estimated · #59/126)
- Step 3.7 Flash public-lane score: 37.1 (Estimated · #74/126)

| Benchmark | Qwen3.5 397B | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 52.5% | Coming soon | Coming soon |
| BrowseComp | 69% | 75.8% | Step 3.7 Flash |
| OSWorld-Verified | 62.2% | Coming soon | Coming soon |
| Claw-Eval | 56.8% | 67.1% | Step 3.7 Flash |
| QwenClawBench | 51.8% | Coming soon | Coming soon |
| 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% | 49.5% | Step 3.7 Flash |
| 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% | 51.57% | Step 3.7 Flash |
| ResearchClawBench | 14.2% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 59.5% | Coming soon |
| DeepSearchQA | Coming soon | 92.8% | Coming soon |
| HLE w/ tools | Coming soon | 47.2% | Coming soon |

### Coding

- Winner: Not comparable
- Qwen3.5 397B public-lane score: Coming soon
- Step 3.7 Flash public-lane score: 30.2 (Estimated · #95/149)

| Benchmark | Qwen3.5 397B | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 76.2% | Coming soon | Coming soon |
| LiveCodeBench v6 | 83.6% | Coming soon | Coming soon |
| SWE-bench Pro | 50.9% | 56.3% | Step 3.7 Flash |
| SWE Multilingual | 69.3% | Coming soon | Coming soon |
| NL2Repo | 32.2% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | 52.5% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 59.5% | Coming soon |

### Reasoning

- Winner: Not comparable
- Qwen3.5 397B public-lane score: 74.9 (Unranked · 2 rankable rows)
- Step 3.7 Flash public-lane score: 76.5 (Unranked · 2 rankable rows)

| Benchmark | Qwen3.5 397B | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | 63.2% | Coming soon | Coming soon |
| AI-Needle | 68.7% | Coming soon | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- Qwen3.5 397B public-lane score: 73.6 (#29/54)
- Step 3.7 Flash public-lane score: 75.4 (Unranked · 3 rankable rows)

| Benchmark | Qwen3.5 397B | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| MMMU | 85.0% | Coming soon | Coming soon |
| MMMU-Pro | 79% | Coming soon | Coming soon |
| RealWorldQA | 83.9% | Coming soon | Coming soon |
| OmniDocBench 1.5 | 90.8% | Coming soon | Coming soon |
| Video-MME (with subtitle) | 87.5% | Coming soon | Coming soon |
| Video-MME (w/o subtitle) | 83.7% | Coming soon | Coming soon |
| MathVision | 88.6% | Coming soon | Coming soon |
| We-Math | 87.9% | Coming soon | Coming soon |
| DynaMath | 86.3% | Coming soon | Coming soon |
| SimpleVQA | 67.1% | 79.2% | Step 3.7 Flash |
| CharXiv | 80.8% | Coming soon | Coming soon |
| MMLongBench-Doc | 61.5% | Coming soon | Coming soon |
| CC-OCR | 82.0% | Coming soon | Coming soon |
| AI2D_TEST | 93.9% | Coming soon | Coming soon |
| CountBench | 97.2% | Coming soon | Coming soon |
| RefCOCO (avg) | 92.3% | Coming soon | Coming soon |
| ODINW13 | 47.0% | Coming soon | Coming soon |
| ERQA | 67.5% | Coming soon | Coming soon |
| VideoMMMU | 84.7% | Coming soon | Coming soon |
| MLVU (M-Avg) | 86.7% | Coming soon | Coming soon |
| ScreenSpot Pro | 65.6% | Coming soon | Coming soon |
| V* | 95.8% | 95.3% | Qwen3.5 397B |

### Knowledge

- Winner: Directional only
- Qwen3.5 397B public-lane score: 53.2 (Estimated · #66/182)
- Step 3.7 Flash public-lane score: 45 (Estimated · #96/182)

| Benchmark | Qwen3.5 397B | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 88.4% | Coming soon | Coming soon |
| SuperGPQA | 70.4% | Coming soon | Coming soon |
| MMLU-Pro | 87.8% | Coming soon | Coming soon |
| MMLU-Redux | 94.9% | Coming soon | Coming soon |
| C-Eval | 93% | Coming soon | Coming soon |
| HLE | 28.7% | Coming soon | Coming soon |

### Multilingual

- Winner: Not comparable
- Qwen3.5 397B public-lane score: 93.8 (#5/17)
- Step 3.7 Flash public-lane score: Coming soon

| Benchmark | Qwen3.5 397B | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| MMLU-ProX | 84.7% | Coming soon | Coming soon |
| NOVA-63 | 59.1% | Coming soon | Coming soon |
| INCLUDE | 85.6% | Coming soon | Coming soon |
| PolyMath | 73.3% | Coming soon | Coming soon |
| MAXIFE | 88.2% | Coming soon | Coming soon |

### Instruction Following

- Winner: Directional only
- Qwen3.5 397B public-lane score: 79.9 (#57/146)
- Step 3.7 Flash public-lane score: 82.1 (#54/146)

| Benchmark | Qwen3.5 397B | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 92.6% | Coming soon | Coming soon |
| IFBench | 76.5% | Coming soon | Coming soon |

### Mathematics

- Winner: Not comparable
- Qwen3.5 397B public-lane score: 81.7 (Unranked · 5 rankable rows)
- Step 3.7 Flash public-lane score: Coming soon

| Benchmark | Qwen3.5 397B | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| AIME26 | 93.3% | Coming soon | Coming soon |
| HMMT Feb 2025 | 94.8% | Coming soon | Coming soon |
| HMMT Nov 2025 | 92.7% | Coming soon | Coming soon |
| HMMT Feb 2026 | 87.9% | Coming soon | Coming soon |
| MMAnswerBench | 80.9% | Coming soon | Coming soon |

## FAQ

### Which is better overall, Qwen3.5 397B or Step 3.7 Flash?

Qwen3.5 397B has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between Qwen3.5 397B and Step 3.7 Flash?

The widest category gap is in knowledge, where the averages are 53.2 for Qwen3.5 397B and 45 for Step 3.7 Flash.

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

Qwen3.5 397B currently has 62 sourced benchmark scores on BenchLM.

### How many benchmarks does Step 3.7 Flash cover on BenchLM?

Step 3.7 Flash currently has 11 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Qwen3.5 397B vs Qwen3.5 397B (Reasoning)](/compare/qwen3-5-397b-vs-qwen3-5-397b-reasoning)
- [Step 3.7 Flash vs Qwen3.5 397B (Reasoning)](/compare/qwen3-5-397b-reasoning-vs-step-3-7-flash)
- [Qwen3.5 397B vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-qwen3-5-397b)
- [Step 3.7 Flash vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-step-3-7-flash)

## Explore More

- [Qwen3.5 397B profile](/models/qwen3-5-397b)
- [Step 3.7 Flash profile](/models/step-3-7-flash)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)