Model comparison
Qwen3.5 397B vs Qwen3.7 Plus
Head-to-head evidence from 39 shared benchmark results across 8 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Qwen3.5 397B #71 (Estimated); Qwen3.7 Plus #21 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Qwen3.5 397B and Qwen3.7 Plus share 39 comparable benchmark results. 8 of 8 categories are comparable. 16 results are unique to Qwen3.5 397B; 30 to Qwen3.7 Plus.
Updated July 23, 2026- Shared results
- 39
- Qwen3.5 397B only
- 16
- Qwen3.7 Plus only
- 30
- Comparable categories
- 8 / 8
Pick Qwen3.7 Plus if you want the stronger benchmark profile. Qwen3.5 397B only becomes the better choice if instruction following is the priority or you would rather avoid the extra latency and token burn of a reasoning model.
Why this result
Qwen3.7 Plus is clearly ahead on the BenchAlign aggregate, 67.22 to 57.01. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Qwen3.7 Plus's sharpest advantage is in reasoning, where it averages 91.7 against 63.2. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 52.5% to 70.3%. Qwen3.5 397B does hit back in instruction following, so the answer changes if that is the part of the workload you care about most.
Qwen3.7 Plus 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. Qwen3.7 Plus gives you the larger context window at 1M, 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 | Qwen3.7 Plus |
|---|---|---|---|
| Reasoning | Qwen3.5 397B63.2 | Margin→ 28.5 | Qwen3.7 Plus91.7 |
| Agentic | Qwen3.5 397B56.5 | Margin→ 15.2 | Qwen3.7 Plus71.7 |
| Coding | Qwen3.5 397B66.5 | Margin→ 9.1 | Qwen3.7 Plus75.6 |
| Inst. Following | Qwen3.5 397B92.6 | Margin← 8.1 | Qwen3.7 Plus84.5 |
| Knowledge | Qwen3.5 397B56.6 | Margin→ 3.5 | Qwen3.7 Plus60.1 |
| Math | Qwen3.5 397B90.6 | Margin→ 2.3 | Qwen3.7 Plus92.9 |
| Multimodal | Qwen3.5 397B79.6 | Margin→ 1.9 | Qwen3.7 Plus81.5 |
| Multilingual | Qwen3.5 397B84.7 | Margin→ 0.7 | Qwen3.7 Plus85.4 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
Terminal-Bench 2.0
AgenticA 52.5%B 70.3%Winner: Qwen3.7 PlusΔ 17.8Terminal-Bench 2.0: Qwen3.5 397B scored 52.5%; Qwen3.7 Plus scored 70.3%. Qwen3.7 Plus wins this benchmark. - Source ↗
SWE-bench Pro
CodingA 50.9%B 57.6%Winner: Qwen3.7 PlusΔ 6.7SWE-bench Pro: Qwen3.5 397B scored 50.9%; Qwen3.7 Plus scored 57.6%. Qwen3.7 Plus wins this benchmark. - Source ↗
HLE
KnowledgeA 28.7%B 34.7%Winner: Qwen3.7 PlusΔ 6HLE: Qwen3.5 397B scored 28.7%; Qwen3.7 Plus scored 34.7%. Qwen3.7 Plus wins this benchmark. - Source ↗
CharXiv
MultimodalA 80.8%B 85.9%Winner: Qwen3.7 PlusΔ 5.1CharXiv: Qwen3.5 397B scored 80.8%; Qwen3.7 Plus scored 85.9%. Qwen3.7 Plus wins this benchmark. - Source ↗
HMMT Feb 2026
MathA 87.9%B 92.9%Winner: Qwen3.7 PlusΔ 5HMMT Feb 2026: Qwen3.5 397B scored 87.9%; Qwen3.7 Plus scored 92.9%. Qwen3.7 Plus wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Qwen3.5 397B | Qwen3.7 Plus | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Qwen3.5 397B$0.6 input / $3.6 output | Qwen3.7 PlusNot available | A complete price comparison is not available. |
| Generation speedtokens per second | Qwen3.5 397B96 tok/s | Qwen3.7 PlusNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Qwen3.5 397B2.44 s | Qwen3.7 PlusNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Qwen3.5 397B128K | Qwen3.7 Plus1M | Qwen3.7 Plus lists the larger context window. |
Benchmark Deep Dive
AgenticQwen3.7 Plus wins23 benchmarks
| Benchmark | Qwen3.5 397B | Qwen3.7 Plus | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 52.5% | 70.3% | Qwen3.7 Plus leads |
| BrowseCompSource | 62% | — | Not comparable |
| Claw-EvalSource | 56.8% | 62.7% | Qwen3.7 Plus leads |
| QwenClawBenchSource | 51.8% | 61.8% | Qwen3.7 Plus leads |
| τ³-bench resultsSource | 68.4% | — | Not comparable |
| VITA-BenchSource | 43.7% | 45.6% | Qwen3.7 Plus leads |
| DeepPlanningSource | 37.6% | 62.3% | Qwen3.7 Plus leads |
| ToolathlonSource | 36.3% | — | Not comparable |
| MCP AtlasSource | 46.1% | 73.2% | Qwen3.7 Plus leads |
| MCP-TasksSource | 74.2% | — | Not comparable |
| WideResearchSource | 74.0% | — | Not comparable |
| τ²-bench resultsSource | 95.6% | 93% | Qwen3.5 397B leads |
| Gert LabsSource | 46.76% | — | Not comparable |
| ResearchClawBenchSource | 14.2% | — | Not comparable |
| AA Agentic IndexSource | 19.9% | 20.8% | Qwen3.7 Plus leads |
| APEX-Agents-AASource | 15.3% | 22.4% | Qwen3.7 Plus leads |
| GDPval-AASource | 23.1% | 21.8% | Qwen3.5 397B leads |
| GDPval-AASource | 962 | 936 | Qwen3.5 397B leads |
| QwenWebBenchSource | — | 1536 | Not comparable |
| BFCL v4Source | — | 72.9% | Not comparable |
| OSWorld-VerifiedSource | — | 73.3% | Not comparable |
| AndroidWorldSource | — | 81.0% | Not comparable |
| OSWorld 2.0Source | — | 2.8% | Not comparable |
CodingQwen3.7 Plus wins10 benchmarks
| Benchmark | Qwen3.5 397B | Qwen3.7 Plus | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 76.2% | 77.7% | Qwen3.7 Plus leads |
| LiveCodeBench v6Source | 83.6% | — | Not comparable |
| SWE-bench ProSource | 50.9% | 57.6% | Qwen3.7 Plus leads |
| AA-SciCodeSource | 42.0% | 45.5% | Qwen3.7 Plus leads |
| AA Coding IndexSource | 48.2% | 55.9% | Qwen3.7 Plus leads |
| Terminal-Bench 2.0Source | — | 70.3% | Not comparable |
| SWE MultilingualSource | — | 75.8% | Not comparable |
| NL2RepoSource | — | 41.1% | Not comparable |
| SciCodeSource | — | 51.3% | Not comparable |
| LiveCodeBenchSource | — | 89.6% | Not comparable |
ReasoningQwen3.7 Plus wins5 benchmarks
KnowledgeQwen3.7 Plus wins14 benchmarks
| Benchmark | Qwen3.5 397B | Qwen3.7 Plus | Result |
|---|---|---|---|
| GPQASource | 88.4% | 90.3% | Qwen3.7 Plus leads |
| SuperGPQASource | 70.4% | 71.4% | Qwen3.7 Plus leads |
| MMLU-ProSource | 87.8% | 88.5% | Qwen3.7 Plus leads |
| MMLU-ReduxSource | 94.9% | 94.5% | Qwen3.5 397B leads |
| C-EvalSource | 93% | — | Not comparable |
| HLESource | 28.7% | 34.7% | Qwen3.7 Plus leads |
| Artificial Analysis Intelligence IndexSource | 33.7% | 39.0% | Qwen3.7 Plus leads |
| AA-GPQA DiamondSource | 89.3% | 90.0% | Qwen3.7 Plus leads |
| AA-HLESource | 27.3% | 33.4% | Qwen3.7 Plus leads |
| AA-Omniscience IndexSource | -29.8% | 2.4% | Qwen3.7 Plus leads |
| AA-Omniscience AccuracySource | 31.4% | 22.2% | Qwen3.5 397B leads |
| AA-Omniscience Hallucination RateSource | 89.1% | 25.5% | Qwen3.7 Plus leads |
| GPQA-DSource | — | 90.3% | Not comparable |
| MMMLUSource | — | 89.0% | Not comparable |
MathQwen3.7 Plus wins7 benchmarks
| Benchmark | Qwen3.5 397B | Qwen3.7 Plus | Result |
|---|---|---|---|
| AIME26Source | 93.3% | — | Not comparable |
| HMMT Feb 2025Source | 94.8% | — | Not comparable |
| HMMT Nov 2025Source | 92.7% | — | Not comparable |
| HMMT Feb 2026Source | 87.9% | 92.9% | Qwen3.7 Plus leads |
| MMAnswerBenchSource | 80.9% | — | Not comparable |
| IMOAnswerBenchSource | — | 86.0% | Not comparable |
| ApexSource | — | 22.7% | Not comparable |
MultilingualQwen3.7 Plus wins5 benchmarks
MultimodalQwen3.7 Plus wins18 benchmarks
| Benchmark | Qwen3.5 397B | Qwen3.7 Plus | Result |
|---|---|---|---|
| MMMU-ProSource | 79% | 79% | Tie |
| MathVisionSource | 88.6% | 90.3% | Qwen3.7 Plus leads |
| CharXivSource | 80.8% | 85.9% | Qwen3.7 Plus leads |
| VideoMMMUSource | 84.7% | 85.4% | Qwen3.7 Plus leads |
| ScreenSpot ProSource | 65.6% | 79.0% | Qwen3.7 Plus leads |
| V*Source | 95.8% | — | Not comparable |
| AA-MMMU-ProSource | 77.3% | 80.5% | Qwen3.7 Plus leads |
| ERQASource | — | 69.8% | Not comparable |
| MedXpertQA (MM)Source | — | 71.0% | Not comparable |
| SimpleVQASource | — | 81.7% | Not comparable |
| MMSearch-PlusSource | — | 41.4% | Not comparable |
| RealWorldQASource | — | 86.9% | Not comparable |
| OmniDocBench 1.5Source | — | 91.4% | Not comparable |
| OCRBench V2Source | — | 70.7% | Not comparable |
| ODINW13Source | — | 51.1% | Not comparable |
| Video-MME (with subtitle)Source | — | 88.0% | Not comparable |
| MLVU (M-Avg)Source | — | 87.4% | Not comparable |
| Design Arena WebsiteSource | — | 1288 | Not comparable |
Frequently Asked Questions (9)
Which is better, Qwen3.5 397B or Qwen3.7 Plus?
Qwen3.7 Plus is ahead on BenchLM's BenchAlign leaderboard, 67.22 to 57.01. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 52.5% and 70.3%.
Which is better for knowledge tasks, Qwen3.5 397B or Qwen3.7 Plus?
Qwen3.7 Plus has the edge for knowledge tasks in this comparison, averaging 60.1 versus 56.6. Inside this category, AA-Omniscience Hallucination Rate is the benchmark that creates the most daylight between them.
Which is better for coding, Qwen3.5 397B or Qwen3.7 Plus?
Qwen3.7 Plus has the edge for coding in this comparison, averaging 75.6 versus 66.5. Inside this category, AA Coding Index is the benchmark that creates the most daylight between them.
Which is better for math, Qwen3.5 397B or Qwen3.7 Plus?
Qwen3.7 Plus has the edge for math in this comparison, averaging 92.9 versus 90.6. Inside this category, HMMT Feb 2026 is the benchmark that creates the most daylight between them.
Which is better for reasoning, Qwen3.5 397B or Qwen3.7 Plus?
Qwen3.7 Plus has the edge for reasoning in this comparison, averaging 91.7 versus 63.2. Inside this category, CritPt is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, Qwen3.5 397B or Qwen3.7 Plus?
Qwen3.7 Plus has the edge for agentic tasks in this comparison, averaging 71.7 versus 56.5. Inside this category, MCP Atlas is the benchmark that creates the most daylight between them.
Which is better for multimodal and grounded tasks, Qwen3.5 397B or Qwen3.7 Plus?
Qwen3.7 Plus has the edge for multimodal and grounded tasks in this comparison, averaging 81.5 versus 79.6. Inside this category, ScreenSpot Pro is the benchmark that creates the most daylight between them.
Which is better for instruction following, Qwen3.5 397B or Qwen3.7 Plus?
Qwen3.5 397B has the edge for instruction following in this comparison, averaging 92.6 versus 84.5. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Which is better for multilingual tasks, Qwen3.5 397B or Qwen3.7 Plus?
Qwen3.7 Plus has the edge for multilingual tasks in this comparison, averaging 85.4 versus 84.7. Inside this category, MMLU-ProX is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.