Skip to main content
BenchLM
Advertise

Model comparison

Claude Sonnet 4.6 vs Qwen3.5 397B

Data verified

Head-to-head evidence from 21 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

65.07/100
Margin
8.1pts
← winning
57.01/100
3 category wins2 category wins

Public leaderboard positions: Claude Sonnet 4.6 #32 (Supported); Qwen3.5 397B #71 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude Sonnet 4.6 and Qwen3.5 397B share 21 comparable benchmark results. 5 of 8 categories are comparable. 12 results are unique to Claude Sonnet 4.6; 34 to Qwen3.5 397B.

Updated July 20, 2026
Shared results
21
Claude Sonnet 4.6 only
12
Qwen3.5 397B only
34
Comparable categories
5 / 8

Pick Claude Sonnet 4.6 if you want the stronger benchmark profile. Qwen3.5 397B only becomes the better choice if mathematics is the priority or you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 21 shared benchmark results across 6 evidence categories; 5 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Claude Sonnet 4.6 is clearly ahead on the BenchAlign aggregate, 65.07 to 57.01. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Claude Sonnet 4.6's sharpest advantage is in knowledge, where it averages 66 against 56.6. The single biggest benchmark swing on the page is SuperGPQA, 95% to 70.4%. Qwen3.5 397B does hit back in mathematics, so the answer changes if that is the part of the workload you care about most.

Claude Sonnet 4.6 is also the more expensive model on tokens at $3.00 input / $15.00 output per 1M tokens, versus $0.60 input / $3.60 output per 1M tokens for Qwen3.5 397B. That is roughly 4.2x on output cost alone. Claude Sonnet 4.6 gives you the larger context window at 200K, 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 Claude Sonnet 4.6 and Qwen3.5 397B
CategoryClaude Sonnet 4.6ΔQwen3.5 397B
MathClaude Sonnet 4.626.4Margin→ 64.2Qwen3.5 397B90.6
KnowledgeClaude Sonnet 4.666.0Margin← 9.4Qwen3.5 397B56.6
AgenticClaude Sonnet 4.665.2Margin← 8.7Qwen3.5 397B56.5
CodingClaude Sonnet 4.669.1Margin← 2.6Qwen3.5 397B66.5
MultimodalClaude Sonnet 4.677.4Margin→ 2.2Qwen3.5 397B79.6
ReasoningClaude Sonnet 4.6Not measuredMarginNo overlapQwen3.5 397B63.2
MultilingualClaude Sonnet 4.6Not measuredMarginNo overlapQwen3.5 397B84.7
Inst. FollowingClaude Sonnet 4.6Not measuredMarginNo overlapQwen3.5 397B92.6

Decisive benchmark drivers

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

More
A · Claude Sonnet 4.6B · Qwen3.5 397B

  1. SuperGPQA

    Knowledge
    Source ↗
    A 95%B 70.4%
    Winner: Claude Sonnet 4.6Δ 24.6
    SuperGPQA: Claude Sonnet 4.6 scored 95%; Qwen3.5 397B scored 70.4%. Claude Sonnet 4.6 wins this benchmark.

  2. HLE

    Knowledge
    Source ↗
    A 49%B 28.7%
    Winner: Claude Sonnet 4.6Δ 20.3
    HLE: Claude Sonnet 4.6 scored 49%; Qwen3.5 397B scored 28.7%. Claude Sonnet 4.6 wins this benchmark.

  3. MMLU-Pro

    Knowledge
    Source ↗
    A 79.2%B 87.8%
    Winner: Qwen3.5 397BΔ 8.6
    MMLU-Pro: Claude Sonnet 4.6 scored 79.2%; Qwen3.5 397B scored 87.8%. Qwen3.5 397B wins this benchmark.

  4. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 59.1%B 52.5%
    Winner: Claude Sonnet 4.6Δ 6.6
    Terminal-Bench 2.0: Claude Sonnet 4.6 scored 59.1%; Qwen3.5 397B scored 52.5%. Claude Sonnet 4.6 wins this benchmark.

  5. SWE-bench Verified

    Coding
    Source ↗
    A 79.6%B 76.2%
    Winner: Claude Sonnet 4.6Δ 3.4
    SWE-bench Verified: Claude Sonnet 4.6 scored 79.6%; Qwen3.5 397B scored 76.2%. Claude Sonnet 4.6 wins this benchmark.

Operational comparison

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

MetricClaude Sonnet 4.6Qwen3.5 397BComparison
Input / output priceUSD per 1M tokensClaude Sonnet 4.6$3 input / $15 outputQwen3.5 397B$0.6 input / $3.6 outputQwen3.5 397B has the lower combined listed price.
Generation speedtokens per secondClaude Sonnet 4.644 tok/sQwen3.5 397B96 tok/sQwen3.5 397B has the higher measured throughput.
First-answer latencyseconds to first tokenClaude Sonnet 4.61.48 sQwen3.5 397B2.44 sClaude Sonnet 4.6 reaches the first token sooner.
Context windowmaximum listed tokensClaude Sonnet 4.6200KQwen3.5 397B128KClaude Sonnet 4.6 lists the larger context window.

Benchmark Deep Dive

AgenticClaude Sonnet 4.6 wins
BenchmarkClaude Sonnet 4.6Qwen3.5 397BResult
Terminal-Bench 2.0Source 59.1%52.5%Claude Sonnet 4.6 leads
OSWorld-VerifiedSource 72.1%—Not comparable
Claw-EvalSource 67.8%56.8%Claude Sonnet 4.6 leads
CyberGymSource 65.2%—Not comparable
τ²-bench resultsSource 79.5%95.6%Qwen3.5 397B leads
Gert LabsSource 62.92%46.76%Claude Sonnet 4.6 leads
OSWorld 2.0Source 8.3%—Not comparable
JobBenchSource 36.9%—Not comparable
BrowseCompSource —62%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
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
CodingClaude Sonnet 4.6 wins
BenchmarkClaude Sonnet 4.6Qwen3.5 397BResult
SWE-bench VerifiedSource 79.6%76.2%Claude Sonnet 4.6 leads
SWE-RebenchSource 60.7%—Not comparable
React Native EvalsSource 80.6%—Not comparable
Vibe Code BenchSource 51.48%—Not comparable
cursorBench31Source 48.8%—Not comparable
AA-SciCodeSource 46.9%42.0%Claude Sonnet 4.6 leads
FrontierCode 1.1 MainSource 24.3%—Not comparable
LiveCodeBench v6Source —83.6%Not comparable
SWE-bench ProSource —50.9%Not comparable
AA Coding IndexSource —48.2%Not comparable
Reasoning
BenchmarkClaude Sonnet 4.6Qwen3.5 397BResult
AA-LCRSource 57.7%65.7%Qwen3.5 397B leads
CritPtSource 0.9%1.7%Qwen3.5 397B leads
LongBench v2Source —63.2%Not comparable
AI-NeedleSource —68.7%Not comparable
KnowledgeClaude Sonnet 4.6 wins
BenchmarkClaude Sonnet 4.6Qwen3.5 397BResult
GPQASource 89.9%88.4%Claude Sonnet 4.6 leads
SuperGPQASource 95%70.4%Claude Sonnet 4.6 leads
MMLU-ProSource 79.2%87.8%Qwen3.5 397B leads
HLESource 49%28.7%Claude Sonnet 4.6 leads
Artificial Analysis Intelligence IndexSource 35.9%33.7%Claude Sonnet 4.6 leads
AA-GPQA DiamondSource 79.9%89.3%Qwen3.5 397B leads
AA-HLESource 13.2%27.3%Qwen3.5 397B leads
AA-Omniscience IndexSource -2.9%-29.8%Claude Sonnet 4.6 leads
AA-Omniscience AccuracySource 38.0%31.4%Claude Sonnet 4.6 leads
AA-Omniscience Hallucination RateSource 65.9%89.1%Claude Sonnet 4.6 leads
MMLU-ReduxSource —94.9%Not comparable
C-EvalSource —93%Not comparable
MathQwen3.5 397B wins
BenchmarkClaude Sonnet 4.6Qwen3.5 397BResult
FrontierMath v2 (Tiers 1-3)Source 32.400%—Not comparable
FrontierMath v2 (Tier 4)Source 8.300%—Not comparable
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
BenchmarkClaude Sonnet 4.6Qwen3.5 397BResult
MMLU-ProXSource —84.7%Not comparable
NOVA-63Source —59.1%Not comparable
MultimodalQwen3.5 397B wins
BenchmarkClaude Sonnet 4.6Qwen3.5 397BResult
CharXivSource 77.4%80.8%Qwen3.5 397B leads
AA-MMMU-ProSource 70.6%77.3%Qwen3.5 397B leads
Design Arena WebsiteSource 1317—Not comparable
MMMU-ProSource —79%Not comparable
MathVisionSource —88.6%Not comparable
VideoMMMUSource —84.7%Not comparable
ScreenSpot ProSource —65.6%Not comparable
V*Source —95.8%Not comparable
Inst. Following
BenchmarkClaude Sonnet 4.6Qwen3.5 397BResult
AA-IFBenchSource 41.2%78.8%Qwen3.5 397B leads
IFEvalSource —92.6%Not comparable
Frequently Asked Questions (6)

Which is better, Claude Sonnet 4.6 or Qwen3.5 397B?

Claude Sonnet 4.6 is ahead on BenchLM's BenchAlign leaderboard, 65.07 to 57.01. The biggest single separator in this matchup is SuperGPQA, where the scores are 95% and 70.4%.

Which is better for knowledge tasks, Claude Sonnet 4.6 or Qwen3.5 397B?

Claude Sonnet 4.6 has the edge for knowledge tasks in this comparison, averaging 66 versus 56.6. Inside this category, AA-Omniscience Index is the benchmark that creates the most daylight between them.

Which is better for coding, Claude Sonnet 4.6 or Qwen3.5 397B?

Claude Sonnet 4.6 has the edge for coding in this comparison, averaging 69.1 versus 66.5. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.

Which is better for math, Claude Sonnet 4.6 or Qwen3.5 397B?

Qwen3.5 397B has the edge for math in this comparison, averaging 90.6 versus 26.4. Claude Sonnet 4.6 stays close enough that the answer can still flip depending on your workload.

Which is better for agentic tasks, Claude Sonnet 4.6 or Qwen3.5 397B?

Claude Sonnet 4.6 has the edge for agentic tasks in this comparison, averaging 65.2 versus 56.5. Inside this category, Gert Labs is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Claude Sonnet 4.6 or Qwen3.5 397B?

Qwen3.5 397B has the edge for multimodal and grounded tasks in this comparison, averaging 79.6 versus 77.4. Inside this category, AA-MMMU-Pro is the benchmark that creates the most daylight between them.

Related Comparisons

Explore More

Anthropic Compare Pricing Methodology Find Your Best LLM Overall Rankings
Last updated: July 20, 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.