Model comparison

Qwen3.5-35B-A3B vs Qwen3 Max

Data verified July 23, 2026

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

Qwen3.5-35B-A3B

Alibaba

56.97/100

Margin

8.8pts

← winning

Qwen3 Max

Alibaba

48.16/100

0 category wins0 category wins

Public leaderboard positions: Qwen3.5-35B-A3B #72 (Supported); Qwen3 Max #128 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Qwen3.5-35B-A3B and Qwen3 Max share 12 comparable benchmark results. 0 of 8 categories are comparable. 16 results are unique to Qwen3.5-35B-A3B; 2 to Qwen3 Max.

Updated July 23, 2026

Shared results: 12
Qwen3.5-35B-A3B only: 16
Qwen3 Max only: 2
Comparable categories: 0 / 8

Benchmark data for Qwen3.5-35B-A3B 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 262K for Qwen3.5-35B-A3B.

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 Qwen3.5-35B-A3B and Qwen3 Max
Category	Qwen3.5-35B-A3B	Δ	Qwen3 Max
Agentic	Qwen3.5-35B-A3B51.0	MarginNo overlap	Qwen3 MaxNot measured
Coding	Qwen3.5-35B-A3B60.6	MarginNo overlap	Qwen3 MaxNot measured
Reasoning	Qwen3.5-35B-A3B59.0	MarginNo overlap	Qwen3 MaxNot measured
Knowledge	Qwen3.5-35B-A3B81.6	MarginNo overlap	Qwen3 MaxNot measured
Multilingual	Qwen3.5-35B-A3B81.0	MarginNo overlap	Qwen3 MaxNot measured
Inst. Following	Qwen3.5-35B-A3B91.9	MarginNo overlap	Qwen3 MaxNot measured

Operational comparison

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

Metric	Qwen3.5-35B-A3B	Qwen3 Max	Comparison
Input / output priceUSD per 1M tokens	Qwen3.5-35B-A3B$0 input / $0 output	Qwen3 MaxNot available	A complete price comparison is not available.
Generation speedtokens per second	Qwen3.5-35B-A3BNot available	Qwen3 MaxNot available	A complete speed comparison is not available.
First-answer latencyseconds to first token	Qwen3.5-35B-A3BNot available	Qwen3 MaxNot available	A complete latency comparison is not available.
Context windowmaximum listed tokens	Qwen3.5-35B-A3B262K	Qwen3 Max1M	Qwen3 Max lists the larger context window.

Benchmark Deep Dive

Agentic

5 benchmarks

Benchmark	Qwen3.5-35B-A3B	Qwen3 Max	Result
Terminal-Bench 2.0Source	40.5%	—	Not comparable
BrowseCompSource	61%	—	Not comparable
OSWorld-VerifiedSource	54.5%	—	Not comparable
τ²-bench resultsSource	89.2%	74.3%	Qwen3.5-35B-A3B leads
Gert LabsSource	28.96%	43.74%	Qwen3 Max leads

Coding

4 benchmarks

Benchmark	Qwen3.5-35B-A3B	Qwen3 Max	Result
SWE-bench VerifiedSource	69.2%	—	Not comparable
SWE-RebenchSource	53.7%	—	Not comparable
AA-SciCodeSource	37.7%	38.3%	Qwen3 Max leads
Vibe Code BenchSource	—	3.51%	Not comparable

Reasoning

3 benchmarks

Benchmark	Qwen3.5-35B-A3B	Qwen3 Max	Result
LongBench v2Source	59%	—	Not comparable
AA-LCRSource	62.7%	46.7%	Qwen3.5-35B-A3B leads
CritPtSource	0.9%	0.0%	Qwen3.5-35B-A3B leads

Knowledge

9 benchmarks

Benchmark	Qwen3.5-35B-A3B	Qwen3 Max	Result
MMLU-ProSource	85.3%	—	Not comparable
SuperGPQASource	63.4%	—	Not comparable
GPQASource	84.2%	—	Not comparable
Artificial Analysis Intelligence IndexSource	29.3%	24.0%	Qwen3.5-35B-A3B leads
AA-GPQA DiamondSource	84.5%	76.4%	Qwen3.5-35B-A3B leads
AA-HLESource	19.7%	11.1%	Qwen3.5-35B-A3B leads
AA-Omniscience IndexSource	-46.4%	-43.1%	Qwen3 Max leads
AA-Omniscience AccuracySource	20.5%	24.4%	Qwen3 Max leads
AA-Omniscience Hallucination RateSource	84.0%	89.4%	Qwen3.5-35B-A3B leads

Multilingual

1 benchmarks

Benchmark	Qwen3.5-35B-A3B	Qwen3 Max	Result
MMLU-ProXSource	81%	—	Not comparable

Multimodal

6 benchmarks

Benchmark	Qwen3.5-35B-A3B	Qwen3 Max	Result
MMMUSource	81.4%	—	Not comparable
MMVUSource	72.3%	—	Not comparable
MathVisionSource	83.9%	—	Not comparable
V*Source	92.7%	—	Not comparable
AA-MMMU-ProSource	72.7%	—	Not comparable
Design Arena WebsiteSource	—	1148	Not comparable

Inst. Following

2 benchmarks

Benchmark	Qwen3.5-35B-A3B	Qwen3 Max	Result
IFEvalSource	91.9%	—	Not comparable
AA-IFBenchSource	72.5%	44.1%	Qwen3.5-35B-A3B leads

Frequently Asked Questions (3)

Can I compare Qwen3.5-35B-A3B 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 Qwen3.5-35B-A3B and Qwen3 Max today?

Qwen3.5-35B-A3B: $0.00 input / $0.00 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

Alibaba Compare Pricing Methodology Find Your Best LLM Overall Rankings

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.