Skip to main content

Model comparison

Qwen3.5 397B vs Qwen3 Max

Data verified

Head-to-head evidence from 12 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

57.01/100
Margin
8.9pts
← winning
Alibaba
48.16/100
0 category wins0 category wins

Public leaderboard positions: Qwen3.5 397B #71 (Estimated); Qwen3 Max #128 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Qwen3.5 397B and Qwen3 Max share 12 comparable benchmark results. 0 of 8 categories are comparable. 43 results are unique to Qwen3.5 397B; 2 to Qwen3 Max.

Updated July 23, 2026
Shared results
12
Qwen3.5 397B only
43
Qwen3 Max only
2
Comparable categories
0 / 8

Benchmark data for Qwen3.5 397B and Qwen3 Max is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 12 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.

Qwen3 Max has 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 scores and score margins for Qwen3.5 397B and Qwen3 Max
CategoryQwen3.5 397BΔQwen3 Max
AgenticQwen3.5 397B56.5MarginNo overlapQwen3 MaxNot measured
CodingQwen3.5 397B66.5MarginNo overlapQwen3 MaxNot measured
ReasoningQwen3.5 397B63.2MarginNo overlapQwen3 MaxNot measured
KnowledgeQwen3.5 397B56.6MarginNo overlapQwen3 MaxNot measured
MathQwen3.5 397B90.6MarginNo overlapQwen3 MaxNot measured
MultilingualQwen3.5 397B84.7MarginNo overlapQwen3 MaxNot measured
MultimodalQwen3.5 397B79.6MarginNo overlapQwen3 MaxNot measured
Inst. FollowingQwen3.5 397B92.6MarginNo overlapQwen3 MaxNot measured

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricQwen3.5 397BQwen3 MaxComparison
Input / output priceUSD per 1M tokensQwen3.5 397B$0.6 input / $3.6 outputQwen3 MaxNot availableA complete price comparison is not available.
Generation speedtokens per secondQwen3.5 397B96 tok/sQwen3 MaxNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenQwen3.5 397B2.44 sQwen3 MaxNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensQwen3.5 397B128KQwen3 Max1MQwen3 Max lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkQwen3.5 397BQwen3 MaxResult
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%74.3%Qwen3.5 397B leads
Gert LabsSource 46.76%43.74%Qwen3.5 397B leads
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 962Not comparable
Coding
BenchmarkQwen3.5 397BQwen3 MaxResult
SWE-bench VerifiedSource 76.2%Not comparable
LiveCodeBench v6Source 83.6%Not comparable
SWE-bench ProSource 50.9%Not comparable
AA-SciCodeSource 42.0%38.3%Qwen3.5 397B leads
AA Coding IndexSource 48.2%Not comparable
Vibe Code BenchSource 3.51%Not comparable
Reasoning
BenchmarkQwen3.5 397BQwen3 MaxResult
LongBench v2Source 63.2%Not comparable
AI-NeedleSource 68.7%Not comparable
AA-LCRSource 65.7%46.7%Qwen3.5 397B leads
CritPtSource 1.7%0.0%Qwen3.5 397B leads
Knowledge
BenchmarkQwen3.5 397BQwen3 MaxResult
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%24.0%Qwen3.5 397B leads
AA-GPQA DiamondSource 89.3%76.4%Qwen3.5 397B leads
AA-HLESource 27.3%11.1%Qwen3.5 397B leads
AA-Omniscience IndexSource -29.8%-43.1%Qwen3.5 397B leads
AA-Omniscience AccuracySource 31.4%24.4%Qwen3.5 397B leads
AA-Omniscience Hallucination RateSource 89.1%89.4%Qwen3.5 397B leads
Math
BenchmarkQwen3.5 397BQwen3 MaxResult
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
Multilingual
BenchmarkQwen3.5 397BQwen3 MaxResult
MMLU-ProXSource 84.7%Not comparable
NOVA-63Source 59.1%Not comparable
Multimodal
BenchmarkQwen3.5 397BQwen3 MaxResult
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
Design Arena WebsiteSource 1148Not comparable
Inst. Following
BenchmarkQwen3.5 397BQwen3 MaxResult
IFEvalSource 92.6%Not comparable
AA-IFBenchSource 78.8%44.1%Qwen3.5 397B leads
Frequently Asked Questions (3)

Can I compare Qwen3.5 397B and Qwen3 Max 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 Max today?

Qwen3.5 397B: $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

Last updated: July 23, 2026

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.