Model comparison
Qwen3.5 397B vs Step 3.7 Flash
Head-to-head evidence from 25 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Verified leaderboard positions: Qwen3.5 397B #20; Step 3.7 Flash unranked
BenchAlign evidence: Qwen3.5 397B estimated; Step 3.7 Flash estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Qwen3.5 397B and Step 3.7 Flash share 25 comparable benchmark results. 2 of 8 categories are comparable. 31 results are unique to Qwen3.5 397B; 5 to Step 3.7 Flash.
Updated July 16, 2026- Shared results
- 25
- Qwen3.5 397B only
- 31
- Step 3.7 Flash only
- 5
- Comparable categories
- 2 / 8
Pick Qwen3.5 397B if you want the stronger benchmark profile. Step 3.7 Flash only becomes the better choice if agentic is the priority or you want the cheaper token bill.
Confidence note. This is a partial-evidence comparison with 25 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
Qwen3.5 397B has the cleaner provisional overall profile here, landing at 59 versus 57. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
Qwen3.5 397B's sharpest advantage is in coding, where it averages 66.5 against 56.3. The single biggest benchmark swing on the page is BrowseComp, 62% to 75.8%. 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.
Qwen3.5 397B is also the more expensive model on tokens at $0.60 input / $3.60 output per 1M tokens, versus $0.20 input / $1.15 output per 1M tokens for Step 3.7 Flash. That is roughly 3.1x on output cost alone. Step 3.7 Flash is the reasoning model in the pair, while Qwen3.5 397B is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Step 3.7 Flash gives you the larger context window at 256K, compared with 128K for Qwen3.5 397B.
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 | Qwen3.5 397B | Δ | Step 3.7 Flash |
|---|---|---|---|
| Coding | Qwen3.5 397B66.5 | Margin← 10.2 | Step 3.7 Flash56.3 |
| Agentic | Qwen3.5 397B56.5 | Margin→ 9.9 | Step 3.7 Flash66.4 |
| Reasoning | Qwen3.5 397B63.2 | MarginNo overlap | Step 3.7 FlashNot measured |
| Knowledge | Qwen3.5 397B56.9 | MarginNo overlap | Step 3.7 FlashNot measured |
| Math | Qwen3.5 397B90.6 | MarginNo overlap | Step 3.7 FlashNot measured |
| Multilingual | Qwen3.5 397B84.7 | MarginNo overlap | Step 3.7 FlashNot measured |
| Multimodal | Qwen3.5 397B79.6 | MarginNo overlap | Step 3.7 FlashNot measured |
| Inst. Following | Qwen3.5 397B92.6 | MarginNo overlap | Step 3.7 FlashNot measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
BrowseComp
AgenticA 62%B 75.8%Winner: Step 3.7 FlashΔ 13.8BrowseComp: Qwen3.5 397B scored 62%; Step 3.7 Flash scored 75.8%. Step 3.7 Flash wins this benchmark. - Source ↗
Terminal-Bench 2.0
AgenticA 52.5%B 59.5%Winner: Step 3.7 FlashΔ 7Terminal-Bench 2.0: Qwen3.5 397B scored 52.5%; Step 3.7 Flash scored 59.5%. Step 3.7 Flash wins this benchmark. - Source ↗
SWE-bench Pro
CodingA 50.9%B 56.3%Winner: Step 3.7 FlashΔ 5.4SWE-bench Pro: Qwen3.5 397B scored 50.9%; 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 | Qwen3.5 397B | Step 3.7 Flash | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Qwen3.5 397B$0.6 input / $3.6 output | Step 3.7 Flash$0.2 input / $1.15 output | Step 3.7 Flash has the lower combined listed price. |
| Generation speedtokens per second | Qwen3.5 397B96 tok/s | Step 3.7 FlashNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Qwen3.5 397B2.44 s | Step 3.7 FlashNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Qwen3.5 397B128K | Step 3.7 Flash256K | Step 3.7 Flash lists the larger context window. |
Benchmark Deep Dive
AgenticStep 3.7 Flash wins20 benchmarks
| Benchmark | Qwen3.5 397B | Step 3.7 Flash | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 52.5% | 59.5% | Step 3.7 Flash leads |
| BrowseCompSource | 62% | 75.8% | Step 3.7 Flash leads |
| Claw-EvalSource | 56.8% | 67.1% | Step 3.7 Flash leads |
| QwenClawBenchSource | 51.8% | — | Not comparable |
| τ³-bench resultsSource | 68.4% | — | Not comparable |
| VITA-BenchSource | 43.7% | — | Not comparable |
| DeepPlanningSource | 37.6% | — | Not comparable |
| ToolathlonSource | 36.3% | 49.5% | Step 3.7 Flash leads |
| MCP AtlasSource | 46.1% | — | Not comparable |
| MCP-TasksSource | 74.2% | — | Not comparable |
| WideResearchSource | 74.0% | — | Not comparable |
| τ²-bench resultsSource | 95.6% | 98.5% | Step 3.7 Flash leads |
| Gert LabsSource | 46.76% | 51.57% | Step 3.7 Flash leads |
| ResearchClawBenchSource | 14.2% | — | Not comparable |
| AA Agentic IndexSource | 19.9% | 21.5% | Step 3.7 Flash leads |
| APEX-Agents-AASource | 15.3% | 14.8% | Qwen3.5 397B leads |
| GDPval-AASource | 23.1% | 25.9% | Step 3.7 Flash leads |
| GDPval-AASource | 962 | 1017 | Step 3.7 Flash leads |
| DeepSearchQASource | — | 92.8% | Not comparable |
| HLE w/ toolsSource | — | 47.2% | Not comparable |
CodingQwen3.5 397B wins7 benchmarks
| Benchmark | Qwen3.5 397B | Step 3.7 Flash | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 76.2% | — | Not comparable |
| LiveCodeBench v6Source | 83.6% | — | Not comparable |
| SWE-bench ProSource | 50.9% | 56.3% | Step 3.7 Flash leads |
| Terminal-Bench HardSource | 40.9% | 35.6% | Qwen3.5 397B leads |
| AA-SciCodeSource | 42.0% | 40.0% | Qwen3.5 397B leads |
| AA Coding IndexSource | 48.2% | 39.6% | Qwen3.5 397B leads |
| Terminal-Bench 2.0Source | — | 59.5% | Not comparable |
Reasoning4 benchmarks
Knowledge12 benchmarks
| Benchmark | Qwen3.5 397B | Step 3.7 Flash | Result |
|---|---|---|---|
| GPQASource | 88.4% | — | Not comparable |
| SuperGPQASource | 70.4% | — | Not comparable |
| MMLU-ProSource | 87.8% | — | Not comparable |
| MMLU-ReduxSource | 94.9% | — | Not comparable |
| C-EvalSource | 93% | — | Not comparable |
| HLESource | 28.7% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 33.7% | 30.3% | Qwen3.5 397B leads |
| AA-GPQA DiamondSource | 89.3% | 80.9% | Qwen3.5 397B leads |
| AA-HLESource | 27.3% | 19.9% | Qwen3.5 397B leads |
| AA-Omniscience IndexSource | -29.8% | -37.5% | Qwen3.5 397B leads |
| AA-Omniscience AccuracySource | 31.4% | 25.4% | Qwen3.5 397B leads |
| AA-Omniscience Hallucination RateSource | 89.1% | 84.4% | Step 3.7 Flash leads |
Math5 benchmarks
Multilingual2 benchmarks
Multimodal9 benchmarks
| Benchmark | Qwen3.5 397B | Step 3.7 Flash | Result |
|---|---|---|---|
| MMMU-ProSource | 79% | — | Not comparable |
| MathVisionSource | 88.6% | — | Not comparable |
| CharXivSource | 80.8% | — | Not comparable |
| VideoMMMUSource | 84.7% | — | Not comparable |
| ScreenSpot ProSource | 65.6% | — | Not comparable |
| V*Source | 95.8% | 95.3% | Qwen3.5 397B leads |
| AA-MMMU-ProSource | 77.3% | 75.3% | Qwen3.5 397B leads |
| SimpleVQASource | — | 79.2% | Not comparable |
| Design Arena WebsiteSource | — | 1218 | Not comparable |
Frequently Asked Questions (3)
Which is better, Qwen3.5 397B or Step 3.7 Flash?
Qwen3.5 397B is ahead on BenchLM's provisional leaderboard, 59 to 57. The biggest single separator in this matchup is BrowseComp, where the scores are 62% and 75.8%.
Which is better for coding, Qwen3.5 397B or Step 3.7 Flash?
Qwen3.5 397B has the edge for coding in this comparison, averaging 66.5 versus 56.3. Inside this category, AA Coding Index is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, Qwen3.5 397B or Step 3.7 Flash?
Step 3.7 Flash has the edge for agentic tasks in this comparison, averaging 66.4 versus 56.5. 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.