Noometry

Model comparison

Claude 3 Sonnet vs Qwen3.6 27B

Qwen3.6 27B is the stronger model overall, scoring 42.2 to 29.0 on the Noometry Index.

Last verified . 4 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

Qwen3.6 27B Alibaba (Qwen)

42.2

Rank #117 Confirmed

Summary

  • They share 4 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and Qwen3.6 27B in 5 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.6 27B leads 48.5 to 10.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 91.1% for Qwen3.6 27B.
  • Qwen3.6 27B has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetQwen3.6 27B
ProviderAnthropicAlibaba (Qwen)
Noometry Index29.042.2
Released2024-02-292026-04-22
WeightsProprietaryOpen
Context window—262K
Max output—66K
Input $ / M tokens—$0.60
Output $ / M tokens—$3.60
Results tracked3011

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

Category by category

Coding Qwen3.6 27B leads

Claude 3 Sonnet: 29.6 (#302), Qwen3.6 27B: 39.1 (#163)

BenchmarkClaude 3 SonnetQwen3.6 27B
SciCode—37.3%
WeirdML10.2%—
BigCodeBench Instruct42.7%—
LMArena Coding1223—
BigCodeBench Complete53.8%—
HumanEval+64%—
MBPP+69.3%—

Reasoning Qwen3.6 27B leads

Claude 3 Sonnet: 20.5 (#237), Qwen3.6 27B: 25.0 (#153)

BenchmarkClaude 3 SonnetQwen3.6 27B
DTBench53.6%78.1%
Epoch Capabilities Index120.7146.5
CritPt—0.9%
Chess Puzzles—22%
LMArena Hard Prompts1197—
Mystery Game Puzzles—7%
LMCA—34.5%
WinoGrande75.1%—

Math Qwen3.6 27B leads

Claude 3 Sonnet: 10.7 (#310), Qwen3.6 27B: 48.5 (#62)

BenchmarkClaude 3 SonnetQwen3.6 27B
OTIS Mock AIME 2024-20252.5%91.1%
FrontierMath (Tiers 1-3)—35.1%
LMArena Math1213—
MATH Level 518.2%—

Knowledge Qwen3.6 27B leads

Claude 3 Sonnet: 21.1 (#276), Qwen3.6 27B: 52.4 (#63)

BenchmarkClaude 3 SonnetQwen3.6 27B
GPQA Diamond40.6%85.9%
LMArena Expert1173—
MMLU75.9%—

Multimodal Not comparable

Claude 3 Sonnet: 25.2 (#125), Qwen3.6 27B: —

BenchmarkClaude 3 SonnetQwen3.6 27B
LMArena Vision984—

Multilingual Not comparable

Claude 3 Sonnet: 37.8 (#234), Qwen3.6 27B: —

BenchmarkClaude 3 SonnetQwen3.6 27B
LMArena Non-English1205—
LMArena Chinese1189—
LMArena French1229—
LMArena German1204—
LMArena Japanese1131—
LMArena Korean1128—
LMArena Russian1227—
LMArena Spanish1204—

Instruction Following Not comparable

Claude 3 Sonnet: 62.8 (#235), Qwen3.6 27B: —

BenchmarkClaude 3 SonnetQwen3.6 27B
LMArena Instruction Following1199—

Long Context Not comparable

Claude 3 Sonnet: 36.7 (#228), Qwen3.6 27B: —

BenchmarkClaude 3 SonnetQwen3.6 27B
LMArena Longer Query1211—

Writing & Preference Qwen3.6 27B leads

Claude 3 Sonnet: 42.1 (#238), Qwen3.6 27B: 50.3 (#181)

BenchmarkClaude 3 SonnetQwen3.6 27B
LMArena Text1218—
LMArena Creative Writing1186—
EQ-Bench 4—1026
LMArena Multi-Turn1227—

Frequently asked questions

Is Claude 3 Sonnet better than Qwen3.6 27B?

Qwen3.6 27B is the stronger model overall, scoring 42.2 to 29.0 on the Noometry Index.

Is Claude 3 Sonnet or Qwen3.6 27B better for coding?

Qwen3.6 27B scores higher on coding benchmarks: 39.1 versus 29.6 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and Qwen3.6 27B share?

4 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Qwen3.6 27B has 11.

Related comparisons

Go deeper