Noometry

Model comparison

Claude 3 Sonnet vs Qwen2-72B

Claude 3 Sonnet and Qwen2-72B score almost the same on the Noometry Index (29.0 vs 30.0), so choose on price, context window or the category you care about most.

Last verified . 24 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

Qwen2-72B Alibaba (Qwen)

30.0

Rank #300 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Claude 3 Sonnet scores higher in 5 categories and Qwen2-72B in 3 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen2-72B leads 30.2 to 10.7.
  • The biggest single-benchmark swing is MATH Level 5: 18.2% for Claude 3 Sonnet and 39.1% for Qwen2-72B.
  • Qwen2-72B has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetQwen2-72B
ProviderAnthropicAlibaba (Qwen)
Noometry Index29.030.0
Released2024-02-292024-06-07
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3026

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

Category by category

Coding Too close to call

Claude 3 Sonnet: 29.6 (#302), Qwen2-72B: 29.1 (#310)

BenchmarkClaude 3 SonnetQwen2-72B
WeirdML10.2%11.3%
BigCodeBench Instruct42.7%38.5%
LMArena Coding12231196
BigCodeBench Complete53.8%54%
HumanEval+64%—
MBPP+69.3%—

Agentic & Tool Use Not comparable

Claude 3 Sonnet: —, Qwen2-72B: 17.0 (#146)

BenchmarkClaude 3 SonnetQwen2-72B
TheAgentCompany—1.1%
METR Time Horizons—29.9%

Reasoning Qwen2-72B leads

Claude 3 Sonnet: 20.5 (#237), Qwen2-72B: 23.2 (#181)

BenchmarkClaude 3 SonnetQwen2-72B
LMArena Hard Prompts11971191
Epoch Capabilities Index120.7125.28
DTBench53.6%—
WinoGrande75.1%—

Math Qwen2-72B leads

Claude 3 Sonnet: 10.7 (#310), Qwen2-72B: 30.2 (#236)

BenchmarkClaude 3 SonnetQwen2-72B
LMArena Math12131235
MATH Level 518.2%39.1%
OTIS Mock AIME 2024-20252.5%—

Knowledge Too close to call

Claude 3 Sonnet: 21.1 (#276), Qwen2-72B: 21.2 (#275)

BenchmarkClaude 3 SonnetQwen2-72B
GPQA Diamond40.6%40.8%
LMArena Expert11731171
MMLU75.9%82.4%

Multimodal Not comparable

Claude 3 Sonnet: 25.2 (#125), Qwen2-72B: —

BenchmarkClaude 3 SonnetQwen2-72B
LMArena Vision984—

Multilingual Claude 3 Sonnet leads

Claude 3 Sonnet: 37.8 (#234), Qwen2-72B: 35.9 (#244)

BenchmarkClaude 3 SonnetQwen2-72B
LMArena Non-English12051176
LMArena Chinese11891240
LMArena French12291170
LMArena German12041151
LMArena Japanese11311111
LMArena Korean11281083
LMArena Russian12271169
LMArena Spanish12041169

Instruction Following Claude 3 Sonnet leads

Claude 3 Sonnet: 62.8 (#235), Qwen2-72B: 61.7 (#241)

BenchmarkClaude 3 SonnetQwen2-72B
LMArena Instruction Following11991181

Long Context Too close to call

Claude 3 Sonnet: 36.7 (#228), Qwen2-72B: 36.1 (#235)

BenchmarkClaude 3 SonnetQwen2-72B
LMArena Longer Query12111192

Writing & Preference Claude 3 Sonnet leads

Claude 3 Sonnet: 42.1 (#238), Qwen2-72B: 40.8 (#241)

BenchmarkClaude 3 SonnetQwen2-72B
LMArena Text12181203
LMArena Creative Writing11861181
LMArena Multi-Turn12271196

Frequently asked questions

Is Claude 3 Sonnet better than Qwen2-72B?

Claude 3 Sonnet and Qwen2-72B score almost the same on the Noometry Index (29.0 vs 30.0), so choose on price, context window or the category you care about most.

Is Claude 3 Sonnet or Qwen2-72B better for coding?

They score almost the same on coding (29.6 vs 29.1); test both on your own repository before choosing.

How many benchmarks do Claude 3 Sonnet and Qwen2-72B share?

24 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Qwen2-72B has 26.

Related comparisons

Go deeper