Model comparison
Qwen3.6-35B-A3B vs Step 3.7 Flash
Head-to-head evidence from 24 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Verified leaderboard positions: Qwen3.6-35B-A3B #31; Step 3.7 Flash unranked
BenchAlign evidence: Qwen3.6-35B-A3B estimated; Step 3.7 Flash estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Qwen3.6-35B-A3B and Step 3.7 Flash share 24 comparable benchmark results. 2 of 8 categories are comparable. 34 results are unique to Qwen3.6-35B-A3B; 6 to Step 3.7 Flash.
Updated July 16, 2026- Shared results
- 24
- Qwen3.6-35B-A3B only
- 34
- Step 3.7 Flash only
- 6
- Comparable categories
- 2 / 8
Pick Qwen3.6-35B-A3B if you want the stronger benchmark profile. Step 3.7 Flash only becomes the better choice if agentic is the priority.
Confidence note. This is a partial-evidence comparison with 24 shared benchmark results across 6 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 finishes one point ahead on BenchLM's provisional leaderboard, 58 to 57. That is enough to call, but not enough to treat as a blowout. This matchup comes down to a few meaningful edges rather than one model dominating the board.
Qwen3.6-35B-A3B's sharpest advantage is in coding, where it averages 73.8 against 56.3. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 51.5% to 59.5%. Step 3.7 Flash 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 gives you the larger context window at 262K, compared with 256K for Step 3.7 Flash.
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 | Qwen3.6-35B-A3B | Δ | Step 3.7 Flash |
|---|---|---|---|
| Coding | Qwen3.6-35B-A3B73.8 | Margin← 17.5 | Step 3.7 Flash56.3 |
| Agentic | Qwen3.6-35B-A3B51.5 | Margin→ 14.9 | Step 3.7 Flash66.4 |
| Knowledge | Qwen3.6-35B-A3B51.8 | MarginNo overlap | Step 3.7 FlashNot measured |
| Math | Qwen3.6-35B-A3B88.2 | MarginNo overlap | Step 3.7 FlashNot measured |
| Multimodal | Qwen3.6-35B-A3B76.3 | MarginNo overlap | Step 3.7 FlashNot measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
Terminal-Bench 2.0
AgenticA 51.5%B 59.5%Winner: Step 3.7 FlashΔ 8Terminal-Bench 2.0: Qwen3.6-35B-A3B scored 51.5%; Step 3.7 Flash scored 59.5%. Step 3.7 Flash wins this benchmark. - Source ↗
SWE-bench Pro
CodingA 49.5%B 56.3%Winner: Step 3.7 FlashΔ 6.8SWE-bench Pro: Qwen3.6-35B-A3B scored 49.5%; Step 3.7 Flash scored 56.3%. Step 3.7 Flash wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Qwen3.6-35B-A3B | Step 3.7 Flash | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Qwen3.6-35B-A3BNot available | Step 3.7 Flash$0.2 input / $1.15 output | A complete price comparison is not available. |
| Generation speedtokens per second | Qwen3.6-35B-A3BNot available | Step 3.7 FlashNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Qwen3.6-35B-A3BNot available | Step 3.7 FlashNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Qwen3.6-35B-A3B262K | Step 3.7 Flash256K | Qwen3.6-35B-A3B lists the larger context window. |
Benchmark Deep Dive
AgenticStep 3.7 Flash wins19 benchmarks
| Benchmark | Qwen3.6-35B-A3B | Step 3.7 Flash | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 51.5% | 59.5% | Step 3.7 Flash leads |
| Claw-EvalSource | 68.7% | 67.1% | 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 |
| ToolathlonSource | 26.9% | 49.5% | Step 3.7 Flash leads |
| MCP AtlasSource | 62.8% | — | Not comparable |
| WideResearchSource | 60.1% | — | Not comparable |
| AA Agentic IndexSource | 21.4% | 21.5% | Step 3.7 Flash leads |
| τ²-bench resultsSource | 95.3% | 98.5% | Step 3.7 Flash leads |
| GDPval-AASource | 27.4% | 25.9% | Qwen3.6-35B-A3B leads |
| GDPval-AASource | 1049 | 1017 | Qwen3.6-35B-A3B leads |
| Gert LabsSource | 42.65% | 51.57% | Step 3.7 Flash leads |
| BrowseCompSource | — | 75.8% | Not comparable |
| DeepSearchQASource | — | 92.8% | Not comparable |
| HLE w/ toolsSource | — | 47.2% | Not comparable |
| APEX-Agents-AASource | — | 14.8% | Not comparable |
CodingQwen3.6-35B-A3B wins9 benchmarks
| Benchmark | Qwen3.6-35B-A3B | Step 3.7 Flash | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 73.4% | — | Not comparable |
| SWE MultilingualSource | 67.2% | — | Not comparable |
| SWE-bench ProSource | 49.5% | 56.3% | Step 3.7 Flash leads |
| Terminal-Bench 2.0Source | 51.5% | 59.5% | Step 3.7 Flash leads |
| LiveCodeBenchSource | 80.4% | — | Not comparable |
| NL2RepoSource | 29.4% | — | Not comparable |
| AA Coding IndexSource | 41.9% | 39.6% | Qwen3.6-35B-A3B leads |
| Terminal-Bench HardSource | 34.8% | 35.6% | Step 3.7 Flash leads |
| AA-SciCodeSource | 35.8% | 40.0% | Step 3.7 Flash leads |
Reasoning2 benchmarks
Knowledge11 benchmarks
| Benchmark | Qwen3.6-35B-A3B | Step 3.7 Flash | Result |
|---|---|---|---|
| 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 |
| Artificial Analysis Intelligence IndexSource | 31.6% | 30.3% | Qwen3.6-35B-A3B leads |
| AA-GPQA DiamondSource | 84.1% | 80.9% | Qwen3.6-35B-A3B leads |
| AA-HLESource | 20.2% | 19.9% | Qwen3.6-35B-A3B leads |
| AA-Omniscience IndexSource | -21.4% | -37.5% | Qwen3.6-35B-A3B leads |
| AA-Omniscience AccuracySource | 18.9% | 25.4% | Step 3.7 Flash leads |
| AA-Omniscience Hallucination RateSource | 49.7% | 84.4% | Qwen3.6-35B-A3B leads |
Math5 benchmarks
Multimodal17 benchmarks
| Benchmark | Qwen3.6-35B-A3B | Step 3.7 Flash | Result |
|---|---|---|---|
| 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% | 79.2% | Step 3.7 Flash leads |
| 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% | 75.3% | Step 3.7 Flash leads |
| V*Source | — | 95.3% | Not comparable |
| Design Arena WebsiteSource | — | 1218 | Not comparable |
Inst. Following1 benchmarks
| Benchmark | Qwen3.6-35B-A3B | Step 3.7 Flash | Result |
|---|---|---|---|
| AA-IFBenchSource | 64.4% | 67.3% | Step 3.7 Flash leads |
Frequently Asked Questions (3)
Which is better, Qwen3.6-35B-A3B or Step 3.7 Flash?
Qwen3.6-35B-A3B is ahead on BenchLM's provisional leaderboard, 58 to 57. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 51.5% and 59.5%.
Which is better for coding, Qwen3.6-35B-A3B or Step 3.7 Flash?
Qwen3.6-35B-A3B has the edge for coding in this comparison, averaging 73.8 versus 56.3. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, Qwen3.6-35B-A3B or Step 3.7 Flash?
Step 3.7 Flash has the edge for agentic tasks in this comparison, averaging 66.4 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.