Skip to main content

Model comparison

Qwen3.5-35B-A3B vs Step 3.7 Flash

Data verified

Head-to-head evidence from 17 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

56.87/100
Margin
6.1pts
← winning
50.76/100
1 category wins1 category wins

Verified leaderboard positions: Qwen3.5-35B-A3B #30; Step 3.7 Flash unranked

BenchAlign evidence: Qwen3.5-35B-A3B supported; Step 3.7 Flash estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Qwen3.5-35B-A3B and Step 3.7 Flash share 17 comparable benchmark results. 2 of 8 categories are comparable. 12 results are unique to Qwen3.5-35B-A3B; 13 to Step 3.7 Flash.

Updated July 16, 2026
Shared results
17
Qwen3.5-35B-A3B only
12
Step 3.7 Flash only
13
Comparable categories
2 / 8

Pick Step 3.7 Flash if you want the stronger benchmark profile. Qwen3.5-35B-A3B only becomes the better choice if coding is the priority or you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 17 shared benchmark results across 6 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Step 3.7 Flash has the cleaner provisional overall profile here, landing at 57 versus 54. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

Step 3.7 Flash's sharpest advantage is in agentic, where it averages 66.4 against 51. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 40.5% to 59.5%. Qwen3.5-35B-A3B does hit back in coding, so the answer changes if that is the part of the workload you care about most.

Step 3.7 Flash is also the more expensive model on tokens at $0.20 input / $1.15 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Qwen3.5-35B-A3B. That is roughly Infinityx on output cost alone. Qwen3.5-35B-A3B gives you the larger context window at 262K, compared with 256K for Step 3.7 Flash.

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 Step 3.7 Flash
CategoryQwen3.5-35B-A3BΔStep 3.7 Flash
AgenticQwen3.5-35B-A3B51.0Margin 15.4Step 3.7 Flash66.4
CodingQwen3.5-35B-A3B60.6Margin 4.3Step 3.7 Flash56.3
ReasoningQwen3.5-35B-A3B59.0MarginNo overlapStep 3.7 FlashNot measured
KnowledgeQwen3.5-35B-A3B81.7MarginNo overlapStep 3.7 FlashNot measured
MultilingualQwen3.5-35B-A3B81.0MarginNo overlapStep 3.7 FlashNot measured
Inst. FollowingQwen3.5-35B-A3B91.9MarginNo overlapStep 3.7 FlashNot measured

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · Qwen3.5-35B-A3BB · Step 3.7 Flash
  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 40.5%B 59.5%
    Winner: Step 3.7 FlashΔ 19
    Terminal-Bench 2.0: Qwen3.5-35B-A3B scored 40.5%; Step 3.7 Flash scored 59.5%. Step 3.7 Flash wins this benchmark.
  2. BrowseComp

    Agentic
    Source ↗
    A 61%B 75.8%
    Winner: Step 3.7 FlashΔ 14.8
    BrowseComp: Qwen3.5-35B-A3B scored 61%; Step 3.7 Flash scored 75.8%. Step 3.7 Flash wins this benchmark.

Operational comparison

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

MetricQwen3.5-35B-A3BStep 3.7 FlashComparison
Input / output priceUSD per 1M tokensQwen3.5-35B-A3B$0 input / $0 outputStep 3.7 Flash$0.2 input / $1.15 outputQwen3.5-35B-A3B has the lower combined listed price.
Generation speedtokens per secondQwen3.5-35B-A3BNot availableStep 3.7 FlashNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenQwen3.5-35B-A3BNot availableStep 3.7 FlashNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensQwen3.5-35B-A3B262KStep 3.7 Flash256KQwen3.5-35B-A3B lists the larger context window.

Benchmark Deep Dive

AgenticStep 3.7 Flash wins
BenchmarkQwen3.5-35B-A3BStep 3.7 FlashResult
Terminal-Bench 2.0Source 40.5%59.5%Step 3.7 Flash leads
BrowseCompSource 61%75.8%Step 3.7 Flash leads
OSWorld-VerifiedSource 54.5%Not comparable
τ²-bench resultsSource 89.2%98.5%Step 3.7 Flash leads
Gert LabsSource 28.96%51.57%Step 3.7 Flash leads
DeepSearchQASource 92.8%Not comparable
GDPval-AASource 25.9%Not comparable
ToolathlonSource 49.5%Not comparable
Claw-EvalSource 67.1%Not comparable
HLE w/ toolsSource 47.2%Not comparable
AA Agentic IndexSource 21.5%Not comparable
GDPval-AASource 1017Not comparable
APEX-Agents-AASource 14.8%Not comparable
CodingQwen3.5-35B-A3B wins
BenchmarkQwen3.5-35B-A3BStep 3.7 FlashResult
SWE-bench VerifiedSource 69.2%Not comparable
SWE-RebenchSource 53.7%Not comparable
Terminal-Bench HardSource 26.5%35.6%Step 3.7 Flash leads
AA-SciCodeSource 37.7%40.0%Step 3.7 Flash leads
SWE-bench ProSource 56.3%Not comparable
Terminal-Bench 2.0Source 59.5%Not comparable
AA Coding IndexSource 39.6%Not comparable
Reasoning
BenchmarkQwen3.5-35B-A3BStep 3.7 FlashResult
LongBench v2Source 59%Not comparable
AA-LCRSource 62.7%63.7%Step 3.7 Flash leads
CritPtSource 0.9%2.3%Step 3.7 Flash leads
Knowledge
BenchmarkQwen3.5-35B-A3BStep 3.7 FlashResult
MMLU-ProSource 85.3%Not comparable
SuperGPQASource 63.4%Not comparable
GPQASource 84.2%Not comparable
Artificial Analysis Intelligence IndexSource 29.3%30.3%Step 3.7 Flash leads
AA-GPQA DiamondSource 84.5%80.9%Qwen3.5-35B-A3B leads
AA-HLESource 19.7%19.9%Step 3.7 Flash leads
AA-Omniscience IndexSource -46.4%-37.5%Step 3.7 Flash leads
AA-Omniscience AccuracySource 20.5%25.4%Step 3.7 Flash leads
AA-Omniscience Hallucination RateSource 84.0%84.4%Qwen3.5-35B-A3B leads
Multilingual
BenchmarkQwen3.5-35B-A3BStep 3.7 FlashResult
MMLU-ProXSource 81%Not comparable
Multimodal
BenchmarkQwen3.5-35B-A3BStep 3.7 FlashResult
MMMUSource 81.4%Not comparable
MMVUSource 72.3%Not comparable
MathVisionSource 83.9%Not comparable
V*Source 92.7%95.3%Step 3.7 Flash leads
AA-MMMU-ProSource 72.7%75.3%Step 3.7 Flash leads
SimpleVQASource 79.2%Not comparable
Design Arena WebsiteSource 1218Not comparable
Inst. Following
BenchmarkQwen3.5-35B-A3BStep 3.7 FlashResult
IFEvalSource 91.9%Not comparable
AA-IFBenchSource 72.5%67.3%Qwen3.5-35B-A3B leads
Frequently Asked Questions (3)

Which is better, Qwen3.5-35B-A3B or Step 3.7 Flash?

Step 3.7 Flash is ahead on BenchLM's provisional leaderboard, 57 to 54. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 40.5% and 59.5%.

Which is better for coding, Qwen3.5-35B-A3B or Step 3.7 Flash?

Qwen3.5-35B-A3B has the edge for coding in this comparison, averaging 60.6 versus 56.3. Inside this category, Terminal-Bench Hard is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Qwen3.5-35B-A3B or Step 3.7 Flash?

Step 3.7 Flash has the edge for agentic tasks in this comparison, averaging 66.4 versus 51. Inside this category, Gert Labs is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 16, 2026

The AI models change fast. We track them for you.

A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.