Skip to main content
BenchLM
Advertise

Model comparison

Claude Sonnet 4.6 vs Qwen3.7 Max

Data verified

Head-to-head evidence from 20 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

65.07/100
Margin
7.8pts
winning →
72.84/100
1 category wins3 category wins

Public leaderboard positions: Claude Sonnet 4.6 #32 (Supported); Qwen3.7 Max #10 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude Sonnet 4.6 and Qwen3.7 Max share 20 comparable benchmark results. 4 of 8 categories are comparable. 13 results are unique to Claude Sonnet 4.6; 38 to Qwen3.7 Max.

Updated July 23, 2026
Shared results
20
Claude Sonnet 4.6 only
13
Qwen3.7 Max only
38
Comparable categories
4 / 8

Pick Qwen3.7 Max if you want the stronger benchmark profile. Claude Sonnet 4.6 only becomes the better choice if knowledge is the priority or you would rather avoid the extra latency and token burn of a reasoning model.

Confidence note. This is a partial-evidence comparison with 20 shared benchmark results across 6 evidence categories; 4 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Qwen3.7 Max is clearly ahead on the BenchAlign aggregate, 72.84 to 65.07. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Qwen3.7 Max's sharpest advantage is in mathematics, where it averages 97.1 against 26.4. The single biggest benchmark swing on the page is SuperGPQA, 95% to 73.6%. Claude Sonnet 4.6 does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.

Qwen3.7 Max is the reasoning model in the pair, while Claude Sonnet 4.6 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. Qwen3.7 Max gives you the larger context window at 1M, compared with 200K for Claude Sonnet 4.6.

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 Qwen3.7 Max
CategoryClaude Sonnet 4.6ΔQwen3.7 Max
MathClaude Sonnet 4.626.4Margin→ 70.7Qwen3.7 Max97.1
CodingClaude Sonnet 4.669.1Margin→ 8.8Qwen3.7 Max77.9
AgenticClaude Sonnet 4.665.2Margin→ 4.5Qwen3.7 Max69.7
KnowledgeClaude Sonnet 4.666.0Margin← 1.8Qwen3.7 Max64.2
ReasoningClaude Sonnet 4.6Not measuredMarginNo overlapQwen3.7 Max90.4
MultilingualClaude Sonnet 4.6Not measuredMarginNo overlapQwen3.7 Max87.0
MultimodalClaude Sonnet 4.677.4MarginNo overlapQwen3.7 MaxNot measured
Inst. FollowingClaude Sonnet 4.6Not measuredMarginNo overlapQwen3.7 Max84.4

Decisive benchmark drivers

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

More
A · Claude Sonnet 4.6B · Qwen3.7 Max

  1. SuperGPQA

    Knowledge
    Source ↗
    A 95%B 73.6%
    Winner: Claude Sonnet 4.6Δ 21.4
    SuperGPQA: Claude Sonnet 4.6 scored 95%; Qwen3.7 Max scored 73.6%. Claude Sonnet 4.6 wins this benchmark.

  2. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 59.1%B 69.7%
    Winner: Qwen3.7 MaxΔ 10.6
    Terminal-Bench 2.0: Claude Sonnet 4.6 scored 59.1%; Qwen3.7 Max scored 69.7%. Qwen3.7 Max wins this benchmark.

  3. MMLU-Pro

    Knowledge
    Source ↗
    A 79.2%B 89.6%
    Winner: Qwen3.7 MaxΔ 10.4
    MMLU-Pro: Claude Sonnet 4.6 scored 79.2%; Qwen3.7 Max scored 89.6%. Qwen3.7 Max wins this benchmark.

  4. HLE

    Knowledge
    Source ↗
    A 49%B 41.4%
    Winner: Claude Sonnet 4.6Δ 7.6
    HLE: Claude Sonnet 4.6 scored 49%; Qwen3.7 Max scored 41.4%. Claude Sonnet 4.6 wins this benchmark.

  5. GPQA

    Knowledge
    Source ↗
    A 89.9%B 92.4%
    Winner: Qwen3.7 MaxΔ 2.5
    GPQA: Claude Sonnet 4.6 scored 89.9%; Qwen3.7 Max scored 92.4%. Qwen3.7 Max wins this benchmark.

Operational comparison

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

MetricClaude Sonnet 4.6Qwen3.7 MaxComparison
Input / output priceUSD per 1M tokensClaude Sonnet 4.6$3 input / $15 outputQwen3.7 MaxNot availableA complete price comparison is not available.
Generation speedtokens per secondClaude Sonnet 4.644 tok/sQwen3.7 MaxNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenClaude Sonnet 4.61.48 sQwen3.7 MaxNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensClaude Sonnet 4.6200KQwen3.7 Max1MQwen3.7 Max lists the larger context window.

Benchmark Deep Dive

AgenticQwen3.7 Max wins
BenchmarkClaude Sonnet 4.6Qwen3.7 MaxResult
Terminal-Bench 2.0Source 59.1%69.7%Qwen3.7 Max leads
OSWorld-VerifiedSource 72.1%—Not comparable
Claw-EvalSource 67.8%65.2%Claude Sonnet 4.6 leads
CyberGymSource 65.2%—Not comparable
τ²-bench resultsSource 79.5%94.7%Qwen3.7 Max leads
Gert LabsSource 62.92%64.27%Qwen3.7 Max leads
OSWorld 2.0Source 8.3%—Not comparable
JobBenchSource 36.9%—Not comparable
QwenClawBenchSource —64.3%Not comparable
QwenWebBenchSource —1568Not comparable
BFCL v4Source —75.0%Not comparable
MCP AtlasSource —76.4%Not comparable
VITA-BenchSource —47.9%Not comparable
HLE w/ toolsSource —53.5%Not comparable
AA Agentic IndexSource —30.6%Not comparable
GDPval-AASource —38.7%Not comparable
GDPval-AASource —1273Not comparable
ResearchClawBenchSource —18.7%Not comparable
AA BriefcaseSource —908Not comparable
AA AutomationBenchSource —25.6%Not comparable
AA EnterpriseOps-GymSource —45.0%Not comparable
AA ITBenchSource —42.5%Not comparable
terminalBenchHardSource —50.8%Not comparable
aaTerminalBench21Source —74.5%Not comparable
AA Harvey LABSource —83.4%Not comparable
CodingQwen3.7 Max wins
BenchmarkClaude Sonnet 4.6Qwen3.7 MaxResult
SWE-bench VerifiedSource 79.6%80.4%Qwen3.7 Max 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%48.8%Qwen3.7 Max leads
FrontierCode 1.1 MainSource 24.3%—Not comparable
SWE-bench ProSource —60.6%Not comparable
SWE MultilingualSource —78.3%Not comparable
NL2RepoSource —47.2%Not comparable
SciCodeSource —53.5%Not comparable
LiveCodeBenchSource —91.6%Not comparable
Terminal-Bench 2.0Source —69.7%Not comparable
AA Coding IndexSource —66.0%Not comparable
Reasoning
BenchmarkClaude Sonnet 4.6Qwen3.7 MaxResult
AA-LCRSource 57.7%69.0%Qwen3.7 Max leads
CritPtSource 0.9%13.4%Qwen3.7 Max leads
MRCRv2Source —90.4%Not comparable
KnowledgeClaude Sonnet 4.6 wins
BenchmarkClaude Sonnet 4.6Qwen3.7 MaxResult
GPQASource 89.9%92.4%Qwen3.7 Max leads
SuperGPQASource 95%73.6%Claude Sonnet 4.6 leads
MMLU-ProSource 79.2%89.6%Qwen3.7 Max leads
HLESource 49%41.4%Claude Sonnet 4.6 leads
Artificial Analysis Intelligence IndexSource 35.9%46.0%Qwen3.7 Max leads
AA-GPQA DiamondSource 79.9%92.3%Qwen3.7 Max leads
AA-HLESource 13.2%38.1%Qwen3.7 Max leads
AA-Omniscience IndexSource -2.9%14.1%Qwen3.7 Max leads
AA-Omniscience AccuracySource 38.0%30.1%Claude Sonnet 4.6 leads
AA-Omniscience Hallucination RateSource 65.9%22.9%Qwen3.7 Max leads
GPQA-DSource —92.4%Not comparable
MMLU-ReduxSource —95%Not comparable
MMMLUSource —90.3%Not comparable
MathQwen3.7 Max wins
BenchmarkClaude Sonnet 4.6Qwen3.7 MaxResult
FrontierMath v2 (Tiers 1-3)Source 32.400%—Not comparable
FrontierMath v2 (Tier 4)Source 8.300%—Not comparable
HMMT Feb 2026Source —97.1%Not comparable
IMOAnswerBenchSource —90.0%Not comparable
ApexSource —44.5%Not comparable
Multilingual
BenchmarkClaude Sonnet 4.6Qwen3.7 MaxResult
MMLU-ProXSource —87%Not comparable
NOVA-63Source —59.0%Not comparable
INCLUDESource —86.2%Not comparable
MAXIFESource —89.2%Not comparable
PolyMathSource —86.5%Not comparable
Multimodal
BenchmarkClaude Sonnet 4.6Qwen3.7 MaxResult
CharXivSource 77.4%—Not comparable
AA-MMMU-ProSource 70.6%—Not comparable
Design Arena WebsiteSource 13141293Claude Sonnet 4.6 leads
Inst. Following
BenchmarkClaude Sonnet 4.6Qwen3.7 MaxResult
AA-IFBenchSource 41.2%80.5%Qwen3.7 Max leads
IFEvalSource —94.3%Not comparable
IFBenchSource —79.1%Not comparable
Frequently Asked Questions (5)

Which is better, Claude Sonnet 4.6 or Qwen3.7 Max?

Qwen3.7 Max is ahead on BenchLM's BenchAlign leaderboard, 72.84 to 65.07. The biggest single separator in this matchup is SuperGPQA, where the scores are 95% and 73.6%.

Which is better for knowledge tasks, Claude Sonnet 4.6 or Qwen3.7 Max?

Claude Sonnet 4.6 has the edge for knowledge tasks in this comparison, averaging 66 versus 64.2. Inside this category, AA-Omniscience Hallucination Rate is the benchmark that creates the most daylight between them.

Which is better for coding, Claude Sonnet 4.6 or Qwen3.7 Max?

Qwen3.7 Max has the edge for coding in this comparison, averaging 77.9 versus 69.1. 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 Qwen3.7 Max?

Qwen3.7 Max has the edge for math in this comparison, averaging 97.1 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 Qwen3.7 Max?

Qwen3.7 Max has the edge for agentic tasks in this comparison, averaging 69.7 versus 65.2. Inside this category, τ²-bench results 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 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.