Model comparison
Qwen3 235B 2507 (Reasoning) vs Qwen3.5 397B
Head-to-head evidence from 0 shared benchmark results across 0 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Qwen3 235B 2507 (Reasoning) #66 (Estimated); Qwen3.5 397B #71 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Qwen3 235B 2507 (Reasoning) and Qwen3.5 397B share 0 comparable benchmark results. 1 of 8 categories are comparable. 2 results are unique to Qwen3 235B 2507 (Reasoning); 55 to Qwen3.5 397B.
Updated July 22, 2026- Shared results
- 0
- Qwen3 235B 2507 (Reasoning) only
- 2
- Qwen3.5 397B only
- 55
- Comparable categories
- 1 / 8
Pick Qwen3 235B 2507 (Reasoning) if you want the stronger benchmark profile. Qwen3.5 397B only becomes the better choice if mathematics is the priority or you would rather avoid the extra latency and token burn of a reasoning model.
Confidence note. This is a partial-evidence comparison with 0 shared benchmark results across 0 evidence categories; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Qwen3 235B 2507 (Reasoning) finishes one point ahead on BenchLM's BenchAlign leaderboard, 58.01 to 57.01. 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.
Qwen3.5 397B is also the more expensive model on tokens at $0.60 input / $3.60 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Qwen3 235B 2507 (Reasoning). That is roughly Infinityx on output cost alone. Qwen3 235B 2507 (Reasoning) 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.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Qwen3 235B 2507 (Reasoning) | Qwen3.5 397B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Qwen3 235B 2507 (Reasoning)$0 input / $0 output | Qwen3.5 397B$0.6 input / $3.6 output | Qwen3 235B 2507 (Reasoning) has the lower combined listed price. |
| Generation speedtokens per second | Qwen3 235B 2507 (Reasoning)Not available | Qwen3.5 397B96 tok/s | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Qwen3 235B 2507 (Reasoning)Not available | Qwen3.5 397B2.44 s | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Qwen3 235B 2507 (Reasoning)128K | Qwen3.5 397B128K | Listed context windows are equal. |
Benchmark Deep Dive
Agentic18 benchmarks
| Benchmark | Qwen3 235B 2507 (Reasoning) | Qwen3.5 397B | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | — | 52.5% | Not comparable |
| BrowseCompSource | — | 62% | Not comparable |
| Claw-EvalSource | — | 56.8% | Not comparable |
| 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% | Not comparable |
| MCP AtlasSource | — | 46.1% | Not comparable |
| MCP-TasksSource | — | 74.2% | Not comparable |
| WideResearchSource | — | 74.0% | Not comparable |
| τ²-bench resultsSource | — | 95.6% | Not comparable |
| Gert LabsSource | — | 46.76% | Not comparable |
| ResearchClawBenchSource | — | 14.2% | Not comparable |
| AA Agentic IndexSource | — | 19.9% | Not comparable |
| APEX-Agents-AASource | — | 15.3% | Not comparable |
| GDPval-AASource | — | 23.1% | Not comparable |
| GDPval-AASource | — | 962 | Not comparable |
Coding5 benchmarks
Reasoning4 benchmarks
Knowledge12 benchmarks
| Benchmark | Qwen3 235B 2507 (Reasoning) | Qwen3.5 397B | 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% | Not comparable |
| AA-GPQA DiamondSource | — | 89.3% | Not comparable |
| AA-HLESource | — | 27.3% | Not comparable |
| AA-Omniscience IndexSource | — | -29.8% | Not comparable |
| AA-Omniscience AccuracySource | — | 31.4% | Not comparable |
| AA-Omniscience Hallucination RateSource | — | 89.1% | Not comparable |
MathQwen3.5 397B wins7 benchmarks
| Benchmark | Qwen3 235B 2507 (Reasoning) | Qwen3.5 397B | Result |
|---|---|---|---|
| FrontierMath v2 (Tiers 1-3)Source | 8.481% | — | Not comparable |
| FrontierMath v2 (Tier 4)Source | 0.000% | — | Not comparable |
| AIME26Source | — | 93.3% | Not comparable |
| HMMT Feb 2025Source | — | 94.8% | Not comparable |
| HMMT Nov 2025Source | — | 92.7% | Not comparable |
| HMMT Feb 2026Source | — | 87.9% | Not comparable |
| MMAnswerBenchSource | — | 80.9% | Not comparable |
Multilingual2 benchmarks
Multimodal7 benchmarks
| Benchmark | Qwen3 235B 2507 (Reasoning) | Qwen3.5 397B | 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% | Not comparable |
| AA-MMMU-ProSource | — | 77.3% | Not comparable |
Frequently Asked Questions (2)
Which is better, Qwen3 235B 2507 (Reasoning) or Qwen3.5 397B?
Qwen3 235B 2507 (Reasoning) is ahead on BenchLM's BenchAlign leaderboard, 58.01 to 57.01.
Which is better for math, Qwen3 235B 2507 (Reasoning) or Qwen3.5 397B?
Qwen3.5 397B has the edge for math in this comparison, averaging 90.6 versus 6.4. Qwen3 235B 2507 (Reasoning) stays close enough that the answer can still flip depending on your workload.
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.