Noometry

Model comparison

Claude Sonnet 4 vs Qwen2.5 72B Instruct

Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 31.9 on the Noometry Index. Qwen2.5 72B Instruct costs 2.4× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.

Last verified . 33 shared benchmarks.

Claude Sonnet 4 Anthropic

40.8

Rank #145 Confirmed

Qwen2.5 72B Instruct Alibaba (Qwen)

31.9

Rank #267 Confirmed

Summary

  • They share 33 benchmarks with published results for both. Claude Sonnet 4 scores higher in 8 categories and Qwen2.5 72B Instruct in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Sonnet 4 leads 43.3 to 19.3.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 71.1% for Claude Sonnet 4 and 8.1% for Qwen2.5 72B Instruct.
  • Qwen2.5 72B Instruct is cheaper at $1.40 / $5.60 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
  • Claude Sonnet 4 accepts more context: 200K tokens versus 131K.
  • Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4Qwen2.5 72B Instruct
ProviderAnthropicAlibaba (Qwen)
Noometry Index40.831.9
Released2025-05-222024-09
WeightsProprietaryOpen
Context window200K131K
Max output64K8K
Input $ / M tokens$3$1.40
Output $ / M tokens$15$5.60
Results tracked5843

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

Category by category

Coding Claude Sonnet 4 leads

Claude Sonnet 4: 43.5 (#88), Qwen2.5 72B Instruct: 33.2 (#260)

BenchmarkClaude Sonnet 4Qwen2.5 72B Instruct
WeirdML46.1%16%
LMArena Coding14141292
SWE-bench Verified (bash only)64.9%—
Aider Polyglot61.3%—
SciCode40%—
GSO4.9%—
BigCodeBench Instruct—45.8%
BigCodeBench Complete—55.9%
ALE-Bench655.35—

Agentic & Tool Use Claude Sonnet 4 leads

Claude Sonnet 4: 38.5 (#31), Qwen2.5 72B Instruct: 22.1 (#133)

BenchmarkClaude Sonnet 4Qwen2.5 72B Instruct
TheAgentCompany33.1%5.7%
METR Time Horizons62%35.8%
Cybench35%—
DeepResearch Bench46.6%—
OSWorld43.9%—
BALROG—16.2%

Reasoning Too close to call

Claude Sonnet 4: 22.9 (#187), Qwen2.5 72B Instruct: 22.3 (#199)

BenchmarkClaude Sonnet 4Qwen2.5 72B Instruct
LMArena Hard Prompts13721271
DTBench77.1%62.9%
LMCA29%13.4%
Epoch Capabilities Index141.69129
ForecastBench60.257.5
ARC-AGI-25.9%—
SimpleBench45.5%—
Kagi LLM Benchmark73%—
ARC-AGI-140%—
CritPt0.3%—
EnigmaEval3.1%—
BIG-Bench Hard—79.8%
HellaSwag—84.8%
PIQA—82.6%
WinoGrande—82.3%

Math Claude Sonnet 4 leads

Claude Sonnet 4: 43.3 (#80), Qwen2.5 72B Instruct: 19.3 (#287)

BenchmarkClaude Sonnet 4Qwen2.5 72B Instruct
OTIS Mock AIME 2024-202571.1%8.1%
Omni-MATH60.2%33%
LMArena Math13751283
MATH Level 584.4%63.2%
FrontierMath (Feb 2025 set)4.1%—
FrontierMath Tier 4 (v1)0%—

Knowledge Claude Sonnet 4 leads

Claude Sonnet 4: 41.8 (#108), Qwen2.5 72B Instruct: 27.0 (#253)

BenchmarkClaude Sonnet 4Qwen2.5 72B Instruct
GPQA Diamond79.2%49.1%
MMLU-Pro84.3%63.1%
Confabulations13.2%19.1%
GPQA (HELM)70.6%42.6%
LMArena Expert13721245
Humanity's Last Exam7.8%—
Vectara Hallucination Rate10.3%—
ARC (AI2) Challenge—94.5%
MMLU—85.3%
TriviaQA—71.9%

Multimodal Not comparable

Claude Sonnet 4: 26.2 (#121), Qwen2.5 72B Instruct: —

BenchmarkClaude Sonnet 4Qwen2.5 72B Instruct
LMArena Vision1191—
GeoBench37%—
VPCT34%—
MindCube44.8%—

Multilingual Claude Sonnet 4 leads

Claude Sonnet 4: 46.7 (#156), Qwen2.5 72B Instruct: 41.0 (#213)

BenchmarkClaude Sonnet 4Qwen2.5 72B Instruct
LMArena Non-English13331252
LMArena Chinese13501272
LMArena French13631280
LMArena German13311234
LMArena Japanese13021180
LMArena Korean12911188
LMArena Russian13551264
LMArena Spanish13571256

Instruction Following Claude Sonnet 4 leads

Claude Sonnet 4: 71.7 (#145), Qwen2.5 72B Instruct: 65.5 (#221)

BenchmarkClaude Sonnet 4Qwen2.5 72B Instruct
IFEval84%80.6%
LMArena Instruction Following13761254

Long Context Qwen2.5 72B Instruct leads

Claude Sonnet 4: 33.7 (#259), Qwen2.5 72B Instruct: 38.9 (#188)

BenchmarkClaude Sonnet 4Qwen2.5 72B Instruct
LMArena Longer Query13981282
Fiction.LiveBench46.9%—

Writing & Preference Claude Sonnet 4 leads

Claude Sonnet 4: 57.1 (#132), Qwen2.5 72B Instruct: 46.7 (#215)

BenchmarkClaude Sonnet 4Qwen2.5 72B Instruct
LMArena Text13511269
LMArena Creative Writing13451221
WildBench83.8%80.2%
LMArena Multi-Turn13761272
Short-Story Creative Writing81.4%—
EQ-Bench Creative Writing1483—

Frequently asked questions

Is Claude Sonnet 4 better than Qwen2.5 72B Instruct?

Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 31.9 on the Noometry Index. Qwen2.5 72B Instruct costs 2.4× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.

Which is cheaper, Claude Sonnet 4 or Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct is cheaper. It lists at $1.40 per million input tokens and $5.60 per million output tokens; Claude Sonnet 4 lists at $3 and $15.

Is Claude Sonnet 4 or Qwen2.5 72B Instruct better for coding?

Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 33.2 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 4 does, with 200K tokens against 131K.

How many benchmarks do Claude Sonnet 4 and Qwen2.5 72B Instruct share?

33 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Qwen2.5 72B Instruct has 43.

Related comparisons

Go deeper