Noometry

Model comparison

Claude Sonnet 5 vs Qwen3.8 Max

Qwen3.8 Max is the stronger model overall, scoring 56.0 to 54.5 on the Noometry Index.

Last verified . 34 shared benchmarks.

Claude Sonnet 5 Anthropic

54.5

Rank #26 Confirmed

Qwen3.8 Max Alibaba (Qwen)

56.0

Rank #21 Confirmed

Summary

  • They share 34 benchmarks with published results for both. Claude Sonnet 5 scores higher in 4 categories and Qwen3.8 Max in 6 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.8 Max leads 73.1 to 66.1.
  • The biggest single-benchmark swing is ProofBench: 77% for Claude Sonnet 5 and 58% for Qwen3.8 Max.
  • Qwen3.8 Max is cheaper at $2 / $6 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.

Side by side

Claude Sonnet 5Qwen3.8 Max
ProviderAnthropicAlibaba (Qwen)
Noometry Index54.556.0
Released2026-06-292026-08-02
WeightsProprietaryProprietary
Context window1M1M
Max output128K131K
Input $ / M tokens$2$2
Output $ / M tokens$10$6
Results tracked5138

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

Category by category

Coding Claude Sonnet 5 leads

Claude Sonnet 5: 55.5 (#20), Qwen3.8 Max: 52.3 (#30)

BenchmarkClaude Sonnet 5Qwen3.8 Max
DeepSWE53.8%57.5%
LMArena WebDev15401671
SciCode53.6%52.9%
LMArena Coding14831499
FrontierCode42.7%—
CursorBench34.1%—
FrontierSWE—15.8%
GSO37.3%—
WeirdML68.8%—
ALE-Bench1,463—

Agentic & Tool Use Too close to call

Claude Sonnet 5: 42.7 (#16), Qwen3.8 Max: 42.6 (#17)

BenchmarkClaude Sonnet 5Qwen3.8 Max
APEX-Agents54.5%—
τ²-bench Banking—55.1%
GBAEval65.3%—
GDP.pdf—23.2%
LMArena Search1194—
Vending-Bench 26,378—

Reasoning Qwen3.8 Max leads

Claude Sonnet 5: 48.2 (#37), Qwen3.8 Max: 53.4 (#26)

BenchmarkClaude Sonnet 5Qwen3.8 Max
NYT Connections (extended)75.1%88.3%
CritPt16.9%20%
Chess Puzzles35%40%
LMArena Hard Prompts14611493
Mystery Game Puzzles35%38%
DTBench92.5%92%
LMCA50%46.2%
Epoch Capabilities Index156.34156.69
SimpleBench60.6%—
Surface Evolver Bench60%—
Bench to the Future 30.14—
ForecastBench61.1—

Math Qwen3.8 Max leads

Claude Sonnet 5: 66.1 (#21), Qwen3.8 Max: 73.1 (#15)

BenchmarkClaude Sonnet 5Qwen3.8 Max
FrontierMath (Tiers 1-3)65.6%74.7%
FrontierMath Tier 429.3%46.3%
OTIS Mock AIME 2024-202594.7%100%
ProofBench77%58%
LMArena Math14671498

Knowledge Qwen3.8 Max leads

Claude Sonnet 5: 55.7 (#42), Qwen3.8 Max: 61.7 (#25)

BenchmarkClaude Sonnet 5Qwen3.8 Max
GPQA Diamond90.5%92.7%
SimpleQA Verified33.7%47.3%
LMArena Expert14911504

Multimodal Claude Sonnet 5 leads

Claude Sonnet 5: 42.4 (#26), Qwen3.8 Max: 36.9 (#70)

BenchmarkClaude Sonnet 5Qwen3.8 Max
LMArena Vision12751314
Blueprint-Bench 224.9%—
Furniture Assembly—20%
LMArena Document1466—

Multilingual Qwen3.8 Max leads

Claude Sonnet 5: 54.0 (#55), Qwen3.8 Max: 56.6 (#18)

BenchmarkClaude Sonnet 5Qwen3.8 Max
LMArena Non-English14311468
LMArena Chinese14751537
LMArena French14571502
LMArena German14481489
LMArena Japanese14221466
LMArena Korean14111467
LMArena Russian14521478
LMArena Spanish14361495

Instruction Following Qwen3.8 Max leads

Claude Sonnet 5: 76.6 (#39), Qwen3.8 Max: 77.7 (#19)

BenchmarkClaude Sonnet 5Qwen3.8 Max
LMArena Instruction Following14531478

Long Context Too close to call

Claude Sonnet 5: 44.8 (#53), Qwen3.8 Max: 45.5 (#30)

BenchmarkClaude Sonnet 5Qwen3.8 Max
LMArena Longer Query14641486

Writing & Preference Claude Sonnet 5 leads

Claude Sonnet 5: 69.4 (#24), Qwen3.8 Max: 67.0 (#31)

BenchmarkClaude Sonnet 5Qwen3.8 Max
LMArena Text14431480
LMArena Creative Writing14161478
LMArena Multi-Turn14541487
EQ-Bench Creative Writing1794—
EQ-Bench 41236—

Frequently asked questions

Is Claude Sonnet 5 better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.0 to 54.5 on the Noometry Index.

Which is cheaper, Claude Sonnet 5 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 5 lists at $2 and $10.

Is Claude Sonnet 5 or Qwen3.8 Max better for coding?

Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 52.3 in the Noometry coding category.

Which has the bigger context window?

Both accept 1M tokens.

How many benchmarks do Claude Sonnet 5 and Qwen3.8 Max share?

34 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Qwen3.8 Max has 38.

Related comparisons

Go deeper