# Qwen3.6-35B-A3B vs Step 3.7 Flash

> Side-by-side benchmark comparison for Qwen3.6-35B-A3B and Step 3.7 Flash across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/qwen3-6-35b-a3b-vs-step-3-7-flash
- Last updated: October 15, 2026

- Shared sourced benchmarks: 5
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Qwen3.6-35B-A3B leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Qwen3.6-35B-A3B has the higher overall point estimate 43.79 to 43.7. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in multimodal & grounded, where the averages are 66.4 for Qwen3.6-35B-A3B and 75.4 for Step 3.7 Flash.
- The biggest single benchmark swing is Toolathlon in Agentic, with scores of 26.9% and 49.5%.
- Qwen3.6-35B-A3B also has the larger context window at 262K.

## Model Snapshot

| Property | Qwen3.6-35B-A3B | Step 3.7 Flash |
|----------|----------|----------|
| Creator | Alibaba | StepFun |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 262K | 256K |
| Overall Score | 43.79 | 43.7 |
| Benchmarks Covered | 42 | 11 |
| Pricing (input/output) | N/A | $0.20 / $1.15 |

## Category Breakdown

### Agentic

- Winner: Directional only
- Qwen3.6-35B-A3B public-lane score: 30.1 (Estimated · #92/126)
- Step 3.7 Flash public-lane score: 37.1 (Estimated · #74/126)

| Benchmark | Qwen3.6-35B-A3B | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 51.5% | Coming soon | Coming soon |
| Claw-Eval | 68.7% | 67.1% | Qwen3.6-35B-A3B |
| QwenClawBench | 52.6% | Coming soon | Coming soon |
| QwenWebBench | 1397 | Coming soon | Coming soon |
| τ³-bench results | 67.2% | Coming soon | Coming soon |
| VITA-Bench | 35.6% | Coming soon | Coming soon |
| DeepPlanning | 25.9% | Coming soon | Coming soon |
| Toolathlon | 26.9% | 49.5% | Step 3.7 Flash |
| MCP Atlas | 62.8% | Coming soon | Coming soon |
| WideResearch | 60.1% | Coming soon | Coming soon |
| Gert Labs | 42.65% | 51.57% | Step 3.7 Flash |
| Terminal-Bench 2.1 | Coming soon | 59.5% | Coming soon |
| BrowseComp | Coming soon | 75.8% | Coming soon |
| DeepSearchQA | Coming soon | 92.8% | Coming soon |
| HLE w/ tools | Coming soon | 47.2% | Coming soon |

### Coding

- Winner: Directional only
- Qwen3.6-35B-A3B public-lane score: 31.6 (Estimated · #91/149)
- Step 3.7 Flash public-lane score: 30.2 (Estimated · #95/149)

| Benchmark | Qwen3.6-35B-A3B | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 73.4% | Coming soon | Coming soon |
| SWE Multilingual | 67.2% | Coming soon | Coming soon |
| SWE-bench Pro | 49.5% | 56.3% | Step 3.7 Flash |
| Terminal-Bench 2.0 | 51.5% | Coming soon | Coming soon |
| LiveCodeBench v6 | 80.4% | Coming soon | Coming soon |
| NL2Repo | 29.4% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 59.5% | Coming soon |

### Reasoning

- Winner: Not comparable
- Qwen3.6-35B-A3B public-lane score: 75.1 (Unranked · 2 rankable rows)
- Step 3.7 Flash public-lane score: 76.5 (Unranked · 2 rankable rows)

### Multimodal & Grounded

- Winner: Not comparable
- Qwen3.6-35B-A3B public-lane score: 66.4 (#40/54)
- Step 3.7 Flash public-lane score: 75.4 (Unranked · 3 rankable rows)

| Benchmark | Qwen3.6-35B-A3B | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| MMMU | 81.7% | Coming soon | Coming soon |
| MMMU-Pro | 75.3% | Coming soon | Coming soon |
| RealWorldQA | 85.3% | Coming soon | Coming soon |
| OmniDocBench 1.5 | 89.9% | Coming soon | Coming soon |
| CharXiv | 78% | Coming soon | Coming soon |
| SimpleVQA | 58.9% | 79.2% | Step 3.7 Flash |
| CC-OCR | 81.9% | Coming soon | Coming soon |
| AI2D_TEST | 92.7% | Coming soon | Coming soon |
| RefCOCO (avg) | 92.0% | Coming soon | Coming soon |
| ODINW13 | 50.8% | Coming soon | Coming soon |
| Video-MME (with subtitle) | 86.6% | Coming soon | Coming soon |
| Video-MME (w/o subtitle) | 82.5% | Coming soon | Coming soon |
| VideoMMMU | 83.7% | Coming soon | Coming soon |
| MLVU (M-Avg) | 86.2% | Coming soon | Coming soon |
| V* | Coming soon | 95.3% | Coming soon |

### Knowledge

- Winner: Directional only
- Qwen3.6-35B-A3B public-lane score: 42.9 (Estimated · #106/182)
- Step 3.7 Flash public-lane score: 45 (Estimated · #96/182)

| Benchmark | Qwen3.6-35B-A3B | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| MMLU-Pro | 85.2% | Coming soon | Coming soon |
| SuperGPQA | 64.7% | Coming soon | Coming soon |
| C-Eval | 90% | Coming soon | Coming soon |
| GPQA | 86% | Coming soon | Coming soon |
| HLE | 21.4% | Coming soon | Coming soon |

### Instruction Following

- Winner: Directional only
- Qwen3.6-35B-A3B public-lane score: 78.3 (#59/146)
- Step 3.7 Flash public-lane score: 82.1 (#54/146)

### Mathematics

- Winner: Not comparable
- Qwen3.6-35B-A3B public-lane score: 58.4 (#10/12)
- Step 3.7 Flash public-lane score: Coming soon

| Benchmark | Qwen3.6-35B-A3B | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| HMMT Feb 2025 | 90.7% | Coming soon | Coming soon |
| HMMT Nov 2025 | 89.1% | Coming soon | Coming soon |
| HMMT Feb 2026 | 83.6% | Coming soon | Coming soon |
| MMAnswerBench | 78.9% | Coming soon | Coming soon |
| AIME26 | 92.7% | Coming soon | Coming soon |
| FrontierMath v2 (Tiers 1-3) | 20.351% | Coming soon | Coming soon |

## FAQ

### Which is better overall, Qwen3.6-35B-A3B or Step 3.7 Flash?

Qwen3.6-35B-A3B has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between Qwen3.6-35B-A3B and Step 3.7 Flash?

The widest category gap is in multimodal & grounded, where the averages are 66.4 for Qwen3.6-35B-A3B and 75.4 for Step 3.7 Flash.

### How many benchmarks does Qwen3.6-35B-A3B cover on BenchLM?

Qwen3.6-35B-A3B currently has 42 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

- [Qwen3.6-35B-A3B vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-qwen3-6-35b-a3b)
- [Step 3.7 Flash vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-step-3-7-flash)
- [Qwen3.6-35B-A3B vs GPT-6.1 Sol](/compare/gpt-6-1-sol-vs-qwen3-6-35b-a3b)
- [Step 3.7 Flash vs GPT-6.1 Sol](/compare/gpt-6-1-sol-vs-step-3-7-flash)

## Explore More

- [Qwen3.6-35B-A3B profile](/models/qwen3-6-35b-a3b)
- [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)