Model comparison
Qwen3.5 397B vs Qwen3.5 397B (Reasoning)
Head-to-head evidence from 17 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Sibling matchup inside the Qwen3.5 397B family.
Public leaderboard positions: Qwen3.5 397B #71 (Estimated); Qwen3.5 397B (Reasoning) #56 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Qwen3.5 397B and Qwen3.5 397B (Reasoning) share 17 comparable benchmark results. 0 of 8 categories are comparable. 38 results are unique to Qwen3.5 397B; 0 to Qwen3.5 397B (Reasoning).
Updated July 20, 2026- Shared results
- 17
- Qwen3.5 397B only
- 38
- Qwen3.5 397B (Reasoning) only
- 0
- Comparable categories
- 0 / 8
Benchmark data for Qwen3.5 397B and Qwen3.5 397B (Reasoning) is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 17 shared benchmark results across 6 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.
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 | Qwen3.5 397B (Reasoning) |
|---|---|---|---|
| Agentic | Qwen3.5 397B56.5 | MarginNo overlap | Qwen3.5 397B (Reasoning)Not measured |
| Coding | Qwen3.5 397B66.5 | MarginNo overlap | Qwen3.5 397B (Reasoning)Not measured |
| Reasoning | Qwen3.5 397B63.2 | MarginNo overlap | Qwen3.5 397B (Reasoning)Not measured |
| Knowledge | Qwen3.5 397B56.6 | MarginNo overlap | Qwen3.5 397B (Reasoning)Not measured |
| Math | Qwen3.5 397B90.6 | MarginNo overlap | Qwen3.5 397B (Reasoning)Not measured |
| Multilingual | Qwen3.5 397B84.7 | MarginNo overlap | Qwen3.5 397B (Reasoning)Not measured |
| Multimodal | Qwen3.5 397B79.6 | MarginNo overlap | Qwen3.5 397B (Reasoning)Not measured |
| Inst. Following | Qwen3.5 397B92.6 | MarginNo overlap | Qwen3.5 397B (Reasoning)Not measured |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Qwen3.5 397B | Qwen3.5 397B (Reasoning) | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Qwen3.5 397B$0.6 input / $3.6 output | Qwen3.5 397B (Reasoning)$0.6 input / $3.6 output | Listed prices are equal. |
| Generation speedtokens per second | Qwen3.5 397B96 tok/s | Qwen3.5 397B (Reasoning)Not available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Qwen3.5 397B2.44 s | Qwen3.5 397B (Reasoning)Not available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Qwen3.5 397B128K | Qwen3.5 397B (Reasoning)128K | Listed context windows are equal. |
Benchmark Deep Dive
Agentic18 benchmarks
| Benchmark | Qwen3.5 397B | Qwen3.5 397B (Reasoning) | 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% | 95.6% | Tie |
| Gert LabsSource | 46.76% | — | Not comparable |
| ResearchClawBenchSource | 14.2% | — | Not comparable |
| AA Agentic IndexSource | 19.9% | 19.9% | Tie |
| APEX-Agents-AASource | 15.3% | 15.3% | Tie |
| GDPval-AASource | 23.1% | 23.1% | Tie |
| GDPval-AASource | 962 | 962 | Tie |
Coding5 benchmarks
Reasoning4 benchmarks
Knowledge12 benchmarks
| Benchmark | Qwen3.5 397B | Qwen3.5 397B (Reasoning) | 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% | 33.7% | Tie |
| AA-GPQA DiamondSource | 89.3% | 89.3% | Tie |
| AA-HLESource | 27.3% | 27.3% | Tie |
| AA-Omniscience IndexSource | -29.8% | -29.8% | Tie |
| AA-Omniscience AccuracySource | 31.4% | 31.4% | Tie |
| AA-Omniscience Hallucination RateSource | 89.1% | 89.1% | Tie |
Math5 benchmarks
Multilingual2 benchmarks
Multimodal7 benchmarks
Frequently Asked Questions (3)
Can I compare Qwen3.5 397B and Qwen3.5 397B (Reasoning) on BenchLM yet?
Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.
Why does this comparison show “coming soon”?
BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.
What data is available for Qwen3.5 397B and Qwen3.5 397B (Reasoning) today?
Qwen3.5 397B: $0.60 input / $3.60 output per 1M tokens Qwen3.5 397B (Reasoning): $0.60 input / $3.60 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.
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.