Noometry

Model comparison

Claude Sonnet 4.6 vs Qwen3.8 Max

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 50.3 on the Noometry Index.

Last verified . 34 shared benchmarks.

Claude Sonnet 4.6 Anthropic

50.3

Rank #50 Confirmed

Qwen3.8 Max Alibaba (Qwen)

56.8

Rank #22 Confirmed

Summary

  • They share 34 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 2 categories and Qwen3.8 Max in 8 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.8 Max leads 73.2 to 52.9.
  • The biggest single-benchmark swing is DeepSWE: 29.9% for Claude Sonnet 4.6 and 57.5% for Qwen3.8 Max.
  • Qwen3.8 Max is cheaper at $2 / $6 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.

Side by side

Claude Sonnet 4.6Qwen3.8 Max
ProviderAnthropicAlibaba (Qwen)
Noometry Index50.356.8
Released2026-02-172026-08-02
WeightsProprietaryProprietary
Context window1M1M
Max output128K131K
Input $ / M tokens$3$2
Output $ / M tokens$15$6
Results tracked5739

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Qwen3.8 Max leads

Claude Sonnet 4.6: 46.3 (#67), Qwen3.8 Max: 53.5 (#29)

BenchmarkClaude Sonnet 4.6Qwen3.8 Max
DeepSWE29.9%57.5%
LMArena WebDev15221674
SciCode46.8%53.2%
LMArena Coding15041502
SWE-bench Verified75.2%—
FrontierCode24.3%—
FrontierSWE—17.8%
WeirdML66.1%—
ALE-Bench1,327—

Agentic & Tool Use Qwen3.8 Max leads

Claude Sonnet 4.6: 39.1 (#28), Qwen3.8 Max: 45.4 (#14)

BenchmarkClaude Sonnet 4.6Qwen3.8 Max
APEX-Agents43%63.3%
GDP.pdf18%23.2%
Terminal-Bench53.4%—
OSWorld 2.09.3%—
τ²-bench Banking—55.1%
DeepResearch Bench54.9%—
OSWorld72.1%—
ExploitBench23.6%—
GBAEval48.8%—
LMArena Search1221—
Vending-Bench 27,204—

Reasoning Qwen3.8 Max leads

Claude Sonnet 4.6: 46.1 (#45), Qwen3.8 Max: 54.4 (#26)

BenchmarkClaude Sonnet 4.6Qwen3.8 Max
NYT Connections (extended)80.9%88.3%
CritPt3.1%20%
Chess Puzzles13%40%
LMArena Hard Prompts14841496
Mystery Game Puzzles16%38%
DTBench89.9%92%
LMCA46.5%46.2%
Epoch Capabilities Index152.24156.41
ARC-AGI-260.4%—
ARC-AGI-186.5%—
Thematic Generalization76.3%—
ForecastBench62—

Math Qwen3.8 Max leads

Claude Sonnet 4.6: 52.9 (#49), Qwen3.8 Max: 73.2 (#20)

BenchmarkClaude Sonnet 4.6Qwen3.8 Max
OTIS Mock AIME 2024-202585.8%100%
ProofBench45%58%
LMArena Math14621499
FrontierMath (Tiers 1-3)—74.7%
FrontierMath Tier 4—46.3%
FrontierMath (Feb 2025 set)32.4%—
FrontierMath Tier 4 (v1)8.3%—

Knowledge Qwen3.8 Max leads

Claude Sonnet 4.6: 51.7 (#65), Qwen3.8 Max: 61.7 (#27)

BenchmarkClaude Sonnet 4.6Qwen3.8 Max
GPQA Diamond87.4%92.7%
SimpleQA Verified35.5%47.3%
LMArena Expert15001507
Vectara Hallucination Rate10.6%—

Multimodal Too close to call

Claude Sonnet 4.6: 38.0 (#68), Qwen3.8 Max: 37.2 (#75)

BenchmarkClaude Sonnet 4.6Qwen3.8 Max
LMArena Vision12831314
Blueprint-Bench 26.7%—
Furniture Assembly—20%
LMArena Document1482—

Multilingual Qwen3.8 Max leads

Claude Sonnet 4.6: 54.4 (#41), Qwen3.8 Max: 56.7 (#18)

BenchmarkClaude Sonnet 4.6Qwen3.8 Max
LMArena Non-English14401472
LMArena Chinese14911538
LMArena French14651503
LMArena German14281483
LMArena Japanese14201467
LMArena Korean14111461
LMArena Russian14401481
LMArena Spanish14641492

Instruction Following Too close to call

Claude Sonnet 4.6: 77.4 (#25), Qwen3.8 Max: 77.6 (#17)

BenchmarkClaude Sonnet 4.6Qwen3.8 Max
LMArena Instruction Following14751479

Long Context Too close to call

Claude Sonnet 4.6: 45.3 (#44), Qwen3.8 Max: 45.6 (#31)

BenchmarkClaude Sonnet 4.6Qwen3.8 Max
LMArena Longer Query14791489

Writing & Preference Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 70.2 (#22), Qwen3.8 Max: 67.1 (#30)

BenchmarkClaude Sonnet 4.6Qwen3.8 Max
LMArena Text14581483
LMArena Creative Writing14351479
LMArena Multi-Turn14641489
EQ-Bench Creative Writing1810—
EQ-Bench 41207—

Frequently asked questions

Is Claude Sonnet 4.6 better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 50.3 on the Noometry Index.

Which is cheaper, Claude Sonnet 4.6 or Qwen3.8 Max?

Qwen3.8 Max is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.

Is Claude Sonnet 4.6 or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 46.3 in the Noometry coding category.

Which has the bigger context window?

Both accept 1M tokens.

How many benchmarks do Claude Sonnet 4.6 and Qwen3.8 Max share?

34 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Qwen3.8 Max has 39.

Related comparisons

Go deeper