Model comparison
Qwen3.5 397B (Reasoning) vs Qwen 3.6 Max (preview)
Head-to-head evidence from 11 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Qwen3.5 397B (Reasoning) #56 (Estimated); Qwen 3.6 Max (preview) #53 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Qwen3.5 397B (Reasoning) and Qwen 3.6 Max (preview) share 11 comparable benchmark results. 0 of 8 categories are comparable. 6 results are unique to Qwen3.5 397B (Reasoning); 10 to Qwen 3.6 Max (preview).
Updated July 23, 2026- Shared results
- 11
- Qwen3.5 397B (Reasoning) only
- 6
- Qwen 3.6 Max (preview) only
- 10
- Comparable categories
- 0 / 8
Benchmark data for Qwen3.5 397B (Reasoning) and Qwen 3.6 Max (preview) is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 11 shared benchmark results across 5 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.
Qwen 3.6 Max (preview) has the larger context window at 256K, compared with 128K for Qwen3.5 397B (Reasoning).
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 (Reasoning) | Δ | Qwen 3.6 Max (preview) |
|---|---|---|---|
| Agentic | Qwen3.5 397B (Reasoning)Not measured | MarginNo overlap | Qwen 3.6 Max (preview)65.4 |
| Coding | Qwen3.5 397B (Reasoning)Not measured | MarginNo overlap | Qwen 3.6 Max (preview)51.0 |
| Knowledge | Qwen3.5 397B (Reasoning)Not measured | MarginNo overlap | Qwen 3.6 Max (preview)73.9 |
| Math | Qwen3.5 397B (Reasoning)Not measured | MarginNo overlap | Qwen 3.6 Max (preview)18.4 |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Qwen3.5 397B (Reasoning) | Qwen 3.6 Max (preview) | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Qwen3.5 397B (Reasoning)$0.6 input / $3.6 output | Qwen 3.6 Max (preview)Not available | A complete price comparison is not available. |
| Generation speedtokens per second | Qwen3.5 397B (Reasoning)Not available | Qwen 3.6 Max (preview)Not available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Qwen3.5 397B (Reasoning)Not available | Qwen 3.6 Max (preview)Not available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Qwen3.5 397B (Reasoning)128K | Qwen 3.6 Max (preview)256K | Qwen 3.6 Max (preview) lists the larger context window. |
Benchmark Deep Dive
Agentic8 benchmarks
| Benchmark | Qwen3.5 397B (Reasoning) | Qwen 3.6 Max (preview) | Result |
|---|---|---|---|
| AA Agentic IndexSource | 19.9% | — | Not comparable |
| APEX-Agents-AASource | 15.3% | — | Not comparable |
| τ²-bench resultsSource | 95.6% | 95.9% | Qwen 3.6 Max (preview) leads |
| GDPval-AASource | 23.1% | — | Not comparable |
| GDPval-AASource | 962 | — | Not comparable |
| Terminal-Bench 2.0Source | — | 65.4% | Not comparable |
| QwenClawBenchSource | — | 59.0% | Not comparable |
| QwenWebBenchSource | — | 1532 | Not comparable |
Coding6 benchmarks
| Benchmark | Qwen3.5 397B (Reasoning) | Qwen 3.6 Max (preview) | Result |
|---|---|---|---|
| AA Coding IndexSource | 48.2% | — | Not comparable |
| AA-SciCodeSource | 42.0% | 46.9% | Qwen 3.6 Max (preview) leads |
| SWE-bench ProSource | — | 57.3% | Not comparable |
| SciCodeSource | — | 47% | Not comparable |
| NL2RepoSource | — | 42.9% | Not comparable |
| Terminal-Bench 2.0Source | — | 65.4% | Not comparable |
Reasoning2 benchmarks
Knowledge7 benchmarks
| Benchmark | Qwen3.5 397B (Reasoning) | Qwen 3.6 Max (preview) | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 33.7% | 40.0% | Qwen 3.6 Max (preview) leads |
| AA-GPQA DiamondSource | 89.3% | 88.8% | Qwen3.5 397B (Reasoning) leads |
| AA-HLESource | 27.3% | 28.9% | Qwen 3.6 Max (preview) leads |
| AA-Omniscience IndexSource | -29.8% | 10.2% | Qwen 3.6 Max (preview) leads |
| AA-Omniscience AccuracySource | 31.4% | 37.7% | Qwen 3.6 Max (preview) leads |
| AA-Omniscience Hallucination RateSource | 89.1% | 44.2% | Qwen 3.6 Max (preview) leads |
| SuperGPQASource | — | 73.9% | Not comparable |
Math2 benchmarks
Multimodal1 benchmarks
| Benchmark | Qwen3.5 397B (Reasoning) | Qwen 3.6 Max (preview) | Result |
|---|---|---|---|
| AA-MMMU-ProSource | 77.3% | — | Not comparable |
Inst. Following1 benchmarks
| Benchmark | Qwen3.5 397B (Reasoning) | Qwen 3.6 Max (preview) | Result |
|---|---|---|---|
| AA-IFBenchSource | 78.8% | 76.6% | Qwen3.5 397B (Reasoning) leads |
Frequently Asked Questions (3)
Can I compare Qwen3.5 397B (Reasoning) and Qwen 3.6 Max (preview) 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 (Reasoning) and Qwen 3.6 Max (preview) today?
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.