Noometry

Model comparison

Claude 3.7 Sonnet vs Qwen3-4B

Claude 3.7 Sonnet is the stronger model overall, scoring 39.5 to 31.9 on the Noometry Index.

Last verified . 2 shared benchmarks.

Claude 3.7 Sonnet Anthropic

39.5

Rank #164 Confirmed

Qwen3-4B Alibaba (Qwen)

31.9

Rank #264 Confirmed

Summary

  • They share 2 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 3 categories and Qwen3-4B in 1 category; 3 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude 3.7 Sonnet leads 37.5 to 29.7.
  • The biggest single-benchmark swing is GPQA Diamond: 79.7% for Claude 3.7 Sonnet and 52.3% for Qwen3-4B.
  • Qwen3-4B has downloadable open weights; the other is API-only.

Side by side

Claude 3.7 SonnetQwen3-4B
ProviderAnthropicAlibaba (Qwen)
Noometry Index39.531.9
Released2025-02-242025-04-29
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked586

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

Category by category

Coding Not comparable

Claude 3.7 Sonnet: 40.6 (#136), Qwen3-4B: —

BenchmarkClaude 3.7 SonnetQwen3-4B
SWE-bench Verified61%—
SWE-bench Verified (bash only)52.8%—
Aider Polyglot64.9%—
GSO3.8%—
LiveBench Coding74.5%—
LMArena Coding1361—
CadEval54%—

Agentic & Tool Use Claude 3.7 Sonnet leads

Claude 3.7 Sonnet: 34.1 (#50), Qwen3-4B: 27.6 (#100)

BenchmarkClaude 3.7 SonnetQwen3-4B
Berkeley Function Calling Leaderboard—35.7%
TheAgentCompany30.9%—
Cybench20%—
DeepResearch Bench43.6%—
OSWorld35.8%—
METR Time Horizons60%—

Reasoning Too close to call

Claude 3.7 Sonnet: 18.6 (#277), Qwen3-4B: 19.2 (#268)

BenchmarkClaude 3.7 SonnetQwen3-4B
ARC-AGI-20.9%—
SimpleBench46.4%—
ARC-AGI-128.6%—
Chess Puzzles—4%
EnigmaEval4.2%—
LiveBench Reasoning87.8%—
LMArena Hard Prompts1333—
LiveBench Data Analysis74%—
Epoch Capabilities Index141.16—
ForecastBench61.8—
LiveBench76.1%—

Math Claude 3.7 Sonnet leads

Claude 3.7 Sonnet: 37.5 (#153), Qwen3-4B: 29.7 (#240)

BenchmarkClaude 3.7 SonnetQwen3-4B
OTIS Mock AIME 2024-202557.8%52.2%
MathArena Final-Answer Competitions—38.5%
Omni-MATH33%—
LiveBench Math79%—
LMArena Math1337—
MATH Level 591.2%—
FrontierMath (Feb 2025 set)4.1%—

Knowledge Claude 3.7 Sonnet leads

Claude 3.7 Sonnet: 39.8 (#130), Qwen3-4B: 33.0 (#208)

BenchmarkClaude 3.7 SonnetQwen3-4B
GPQA Diamond79.7%52.3%
Humanity's Last Exam8%—
MMLU-Pro78.4%—
Confabulations14.7%—
Vectara Hallucination Rate—5.7%
GPQA (HELM)60.8%—
LMArena Expert1321—

Multimodal Not comparable

Claude 3.7 Sonnet: 33.7 (#95), Qwen3-4B: —

BenchmarkClaude 3.7 SonnetQwen3-4B
LMArena Vision1169—
GeoBench68%—
VPCT39%—
SpatialViz-Bench33.9%—

Multilingual Not comparable

Claude 3.7 Sonnet: 44.1 (#179), Qwen3-4B: —

BenchmarkClaude 3.7 SonnetQwen3-4B
LMArena Non-English1296—
LMArena Chinese1299—
LMArena French1303—
LMArena German1301—
LMArena Japanese1267—
LMArena Korean1249—
LMArena Russian1311—
LMArena Spanish1298—

Instruction Following Not comparable

Claude 3.7 Sonnet: 72.9 (#125), Qwen3-4B: —

BenchmarkClaude 3.7 SonnetQwen3-4B
LiveBench Instruction Following81.3%—
IFEval83.4%—
LMArena Instruction Following1352—

Long Context Not comparable

Claude 3.7 Sonnet: 50.3 (#10), Qwen3-4B: —

BenchmarkClaude 3.7 SonnetQwen3-4B
Fiction.LiveBench83.3%—
LMArena Longer Query1373—

Writing & Preference Not comparable

Claude 3.7 Sonnet: 54.4 (#150), Qwen3-4B: —

BenchmarkClaude 3.7 SonnetQwen3-4B
LMArena Text1314—
LMArena Creative Writing1332—
Short-Story Creative Writing81.1%—
EQ-Bench Creative Writing1412—
WildBench81.4%—
LMArena Multi-Turn1339—
LiveBench Language59.9%—

Frequently asked questions

Is Claude 3.7 Sonnet better than Qwen3-4B?

Claude 3.7 Sonnet is the stronger model overall, scoring 39.5 to 31.9 on the Noometry Index.

How many benchmarks do Claude 3.7 Sonnet and Qwen3-4B share?

2 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Qwen3-4B has 6.

Related comparisons

Go deeper