Noometry

Model comparison

Claude Sonnet 5 vs Qwen1.5-72B

Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 30.3 on the Noometry Index.

Last verified . 18 shared benchmarks.

Claude Sonnet 5 Anthropic

54.5

Rank #26 Confirmed

Qwen1.5-72B Alibaba (Qwen)

30.3

Rank #282 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Claude Sonnet 5 scores higher in 8 categories and Qwen1.5-72B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Claude Sonnet 5 leads 55.7 to 11.5.
  • The biggest single-benchmark swing is GPQA Diamond: 90.5% for Claude Sonnet 5 and 28.8% for Qwen1.5-72B.
  • Qwen1.5-72B has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 5Qwen1.5-72B
ProviderAnthropicAlibaba (Qwen)
Noometry Index54.530.3
Released2026-06-292024-02-04
WeightsProprietaryOpen
Context window1M—
Max output128K—
Input $ / M tokens$2—
Output $ / M tokens$10—
Results tracked5122

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), Qwen1.5-72B: 31.4 (#272)

BenchmarkClaude Sonnet 5Qwen1.5-72B
LMArena Coding14831166
DeepSWE53.8%—
FrontierCode42.7%—
CursorBench34.1%—
LMArena WebDev1540—
SciCode53.6%—
GSO37.3%—
WeirdML68.8%—
BigCodeBench Instruct—33.2%
BigCodeBench Complete—40.3%
ALE-Bench1,463—
HumanEval+—59.1%
MBPP+—61.6%

Agentic & Tool Use Not comparable

Claude Sonnet 5: 42.7 (#16), Qwen1.5-72B: —

BenchmarkClaude Sonnet 5Qwen1.5-72B
APEX-Agents54.5%—
GBAEval65.3%—
LMArena Search1194—
Vending-Bench 26,378—

Reasoning Claude Sonnet 5 leads

Claude Sonnet 5: 48.2 (#37), Qwen1.5-72B: 21.2 (#201)

BenchmarkClaude Sonnet 5Qwen1.5-72B
LMArena Hard Prompts14611148
SimpleBench60.6%—
NYT Connections (extended)75.1%—
CritPt16.9%—
Chess Puzzles35%—
Mystery Game Puzzles35%—
DTBench92.5%—
LMCA50%—
Surface Evolver Bench60%—
Bench to the Future 30.14—
Epoch Capabilities Index156.34—
ForecastBench61.1—

Math Claude Sonnet 5 leads

Claude Sonnet 5: 66.1 (#21), Qwen1.5-72B: 30.7 (#205)

BenchmarkClaude Sonnet 5Qwen1.5-72B
LMArena Math14671164
FrontierMath (Tiers 1-3)65.6%—
FrontierMath Tier 429.3%—
OTIS Mock AIME 2024-202594.7%—
ProofBench77%—

Knowledge Claude Sonnet 5 leads

Claude Sonnet 5: 55.7 (#42), Qwen1.5-72B: 11.5 (#295)

BenchmarkClaude Sonnet 5Qwen1.5-72B
GPQA Diamond90.5%28.8%
LMArena Expert14911136
SimpleQA Verified33.7%—

Multimodal Not comparable

Claude Sonnet 5: 42.4 (#26), Qwen1.5-72B: —

BenchmarkClaude Sonnet 5Qwen1.5-72B
LMArena Vision1275—
Blueprint-Bench 224.9%—
LMArena Document1466—

Multilingual Claude Sonnet 5 leads

Claude Sonnet 5: 54.0 (#55), Qwen1.5-72B: 33.4 (#248)

BenchmarkClaude Sonnet 5Qwen1.5-72B
LMArena Non-English14311135
LMArena Chinese14751186
LMArena French14571158
LMArena German14481084
LMArena Japanese14221061
LMArena Korean14111049
LMArena Russian14521104
LMArena Spanish14361110

Instruction Following Claude Sonnet 5 leads

Claude Sonnet 5: 76.6 (#39), Qwen1.5-72B: 59.6 (#251)

BenchmarkClaude Sonnet 5Qwen1.5-72B
LMArena Instruction Following14531142

Long Context Claude Sonnet 5 leads

Claude Sonnet 5: 44.8 (#53), Qwen1.5-72B: 35.0 (#238)

BenchmarkClaude Sonnet 5Qwen1.5-72B
LMArena Longer Query14641157

Writing & Preference Claude Sonnet 5 leads

Claude Sonnet 5: 69.4 (#24), Qwen1.5-72B: 37.4 (#253)

BenchmarkClaude Sonnet 5Qwen1.5-72B
LMArena Text14431166
LMArena Creative Writing14161137
LMArena Multi-Turn14541160
EQ-Bench Creative Writing1794—
EQ-Bench 41236—

Frequently asked questions

Is Claude Sonnet 5 better than Qwen1.5-72B?

Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 30.3 on the Noometry Index.

Is Claude Sonnet 5 or Qwen1.5-72B better for coding?

Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 31.4 in the Noometry coding category.

How many benchmarks do Claude Sonnet 5 and Qwen1.5-72B share?

18 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Qwen1.5-72B has 22.

Related comparisons

Go deeper