Skip to main content
BenchLM
Advertise

Model comparison

Qwen3.5 397B vs Step 3.7 Flash

Data verified

Head-to-head evidence from 24 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

57.01/100
Margin
6.1pts
← winning
50.87/100
1 category wins1 category wins

Public leaderboard positions: Qwen3.5 397B #71 (Estimated); Step 3.7 Flash #110 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Qwen3.5 397B and Step 3.7 Flash share 24 comparable benchmark results. 2 of 8 categories are comparable. 31 results are unique to Qwen3.5 397B; 5 to Step 3.7 Flash.

Updated July 23, 2026
Shared results
24
Qwen3.5 397B only
31
Step 3.7 Flash only
5
Comparable categories
2 / 8

Pick Qwen3.5 397B if you want the stronger benchmark profile. Step 3.7 Flash only becomes the better choice if agentic is the priority or you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 24 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

Qwen3.5 397B is clearly ahead on the BenchAlign aggregate, 57.01 to 50.87. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Qwen3.5 397B's sharpest advantage is in coding, where it averages 66.5 against 56.3. The single biggest benchmark swing on the page is BrowseComp, 62% to 75.8%. Step 3.7 Flash does hit back in agentic, so the answer changes if that is the part of the workload you care about most.

Qwen3.5 397B is also the more expensive model on tokens at $0.60 input / $3.60 output per 1M tokens, versus $0.20 input / $1.15 output per 1M tokens for Step 3.7 Flash. That is roughly 3.1x on output cost alone. Step 3.7 Flash is the reasoning model in the pair, while Qwen3.5 397B is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Step 3.7 Flash gives you the larger context window at 256K, 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 Step 3.7 Flash
CategoryQwen3.5 397BΔStep 3.7 Flash
CodingQwen3.5 397B66.5Margin← 10.2Step 3.7 Flash56.3
AgenticQwen3.5 397B56.5Margin→ 9.9Step 3.7 Flash66.4
ReasoningQwen3.5 397B63.2MarginNo overlapStep 3.7 FlashNot measured
KnowledgeQwen3.5 397B56.6MarginNo overlapStep 3.7 FlashNot measured
MathQwen3.5 397B90.6MarginNo overlapStep 3.7 FlashNot measured
MultilingualQwen3.5 397B84.7MarginNo overlapStep 3.7 FlashNot measured
MultimodalQwen3.5 397B79.6MarginNo overlapStep 3.7 FlashNot measured
Inst. FollowingQwen3.5 397B92.6MarginNo overlapStep 3.7 FlashNot measured

Decisive benchmark drivers

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

More
A · Qwen3.5 397BB · Step 3.7 Flash

  1. BrowseComp

    Agentic
    Source ↗
    A 62%B 75.8%
    Winner: Step 3.7 FlashΔ 13.8
    BrowseComp: Qwen3.5 397B scored 62%; Step 3.7 Flash scored 75.8%. Step 3.7 Flash wins this benchmark.

  2. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 52.5%B 59.5%
    Winner: Step 3.7 FlashΔ 7
    Terminal-Bench 2.0: Qwen3.5 397B scored 52.5%; Step 3.7 Flash scored 59.5%. Step 3.7 Flash wins this benchmark.

  3. SWE-bench Pro

    Coding
    Source ↗
    A 50.9%B 56.3%
    Winner: Step 3.7 FlashΔ 5.4
    SWE-bench Pro: Qwen3.5 397B scored 50.9%; Step 3.7 Flash scored 56.3%. 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 397BStep 3.7 FlashComparison
Input / output priceUSD per 1M tokensQwen3.5 397B$0.6 input / $3.6 outputStep 3.7 Flash$0.2 input / $1.15 outputStep 3.7 Flash has the lower combined listed price.
Generation speedtokens per secondQwen3.5 397B96 tok/sStep 3.7 FlashNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenQwen3.5 397B2.44 sStep 3.7 FlashNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensQwen3.5 397B128KStep 3.7 Flash256KStep 3.7 Flash lists the larger context window.

Benchmark Deep Dive

AgenticStep 3.7 Flash wins
BenchmarkQwen3.5 397BStep 3.7 FlashResult
Terminal-Bench 2.0Source 52.5%59.5%Step 3.7 Flash leads
BrowseCompSource 62%75.8%Step 3.7 Flash leads
Claw-EvalSource 56.8%67.1%Step 3.7 Flash leads
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%49.5%Step 3.7 Flash leads
MCP AtlasSource 46.1%—Not comparable
MCP-TasksSource 74.2%—Not comparable
WideResearchSource 74.0%—Not comparable
τ²-bench resultsSource 95.6%98.5%Step 3.7 Flash leads
Gert LabsSource 46.76%51.57%Step 3.7 Flash leads
ResearchClawBenchSource 14.2%—Not comparable
AA Agentic IndexSource 19.9%21.5%Step 3.7 Flash leads
APEX-Agents-AASource 15.3%14.8%Qwen3.5 397B leads
GDPval-AASource 23.1%25.9%Step 3.7 Flash leads
GDPval-AASource 9621017Step 3.7 Flash leads
DeepSearchQASource —92.8%Not comparable
HLE w/ toolsSource —47.2%Not comparable
CodingQwen3.5 397B wins
BenchmarkQwen3.5 397BStep 3.7 FlashResult
SWE-bench VerifiedSource 76.2%—Not comparable
LiveCodeBench v6Source 83.6%—Not comparable
SWE-bench ProSource 50.9%56.3%Step 3.7 Flash leads
AA-SciCodeSource 42.0%40.0%Qwen3.5 397B leads
AA Coding IndexSource 48.2%39.6%Qwen3.5 397B leads
Terminal-Bench 2.0Source —59.5%Not comparable
Reasoning
BenchmarkQwen3.5 397BStep 3.7 FlashResult
LongBench v2Source 63.2%—Not comparable
AI-NeedleSource 68.7%—Not comparable
AA-LCRSource 65.7%63.7%Qwen3.5 397B leads
CritPtSource 1.7%2.3%Step 3.7 Flash leads
Knowledge
BenchmarkQwen3.5 397BStep 3.7 FlashResult
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%30.3%Qwen3.5 397B leads
AA-GPQA DiamondSource 89.3%80.9%Qwen3.5 397B leads
AA-HLESource 27.3%19.9%Qwen3.5 397B leads
AA-Omniscience IndexSource -29.8%-37.5%Qwen3.5 397B leads
AA-Omniscience AccuracySource 31.4%25.4%Qwen3.5 397B leads
AA-Omniscience Hallucination RateSource 89.1%84.4%Step 3.7 Flash leads
Math
BenchmarkQwen3.5 397BStep 3.7 FlashResult
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 397BStep 3.7 FlashResult
MMLU-ProXSource 84.7%—Not comparable
NOVA-63Source 59.1%—Not comparable
Multimodal
BenchmarkQwen3.5 397BStep 3.7 FlashResult
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%95.3%Qwen3.5 397B leads
AA-MMMU-ProSource 77.3%75.3%Qwen3.5 397B leads
SimpleVQASource —79.2%Not comparable
Design Arena WebsiteSource —1211Not comparable
Inst. Following
BenchmarkQwen3.5 397BStep 3.7 FlashResult
IFEvalSource 92.6%—Not comparable
AA-IFBenchSource 78.8%67.3%Qwen3.5 397B leads
Frequently Asked Questions (3)

Which is better, Qwen3.5 397B or Step 3.7 Flash?

Qwen3.5 397B is ahead on BenchLM's BenchAlign leaderboard, 57.01 to 50.87. The biggest single separator in this matchup is BrowseComp, where the scores are 62% and 75.8%.

Which is better for coding, Qwen3.5 397B or Step 3.7 Flash?

Qwen3.5 397B has the edge for coding in this comparison, averaging 66.5 versus 56.3. Inside this category, AA Coding Index is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Qwen3.5 397B or Step 3.7 Flash?

Step 3.7 Flash has the edge for agentic tasks in this comparison, averaging 66.4 versus 56.5. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.

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.