Noometry

Model comparison

Claude Sonnet 4.6 vs Qwen2.5 72B Instruct

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 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 4.6's lead doesn't matter for your workload.

Last verified . 24 shared benchmarks.

Claude Sonnet 4.6 Anthropic

50.3

Rank #50 Confirmed

Qwen2.5 72B Instruct Alibaba (Qwen)

31.9

Rank #267 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 9 categories and Qwen2.5 72B Instruct in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Sonnet 4.6 leads 52.9 to 19.3.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 85.8% for Claude Sonnet 4.6 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 4.6.
  • Claude Sonnet 4.6 accepts more context: 1M tokens versus 131K.
  • Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4.6Qwen2.5 72B Instruct
ProviderAnthropicAlibaba (Qwen)
Noometry Index50.331.9
Released2026-02-172024-09
WeightsProprietaryOpen
Context window1M131K
Max output128K8K
Input $ / M tokens$3$1.40
Output $ / M tokens$15$5.60
Results tracked5743

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

Category by category

Coding Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.3 (#67), Qwen2.5 72B Instruct: 33.2 (#260)

BenchmarkClaude Sonnet 4.6Qwen2.5 72B Instruct
WeirdML66.1%16%
LMArena Coding15041292
SWE-bench Verified75.2%—
DeepSWE29.9%—
FrontierCode24.3%—
LMArena WebDev1522—
SciCode46.8%—
BigCodeBench Instruct—45.8%
BigCodeBench Complete—55.9%
ALE-Bench1,327—

Agentic & Tool Use Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 39.1 (#28), Qwen2.5 72B Instruct: 22.1 (#133)

BenchmarkClaude Sonnet 4.6Qwen2.5 72B Instruct
Terminal-Bench53.4%—
APEX-Agents43%—
OSWorld 2.09.3%—
TheAgentCompany—5.7%
DeepResearch Bench54.9%—
OSWorld72.1%—
BALROG—16.2%
ExploitBench23.6%—
GBAEval48.8%—
GDP.pdf18%—
LMArena Search1221—
METR Time Horizons—35.8%
Vending-Bench 27,204—

Reasoning Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.1 (#45), Qwen2.5 72B Instruct: 22.3 (#199)

BenchmarkClaude Sonnet 4.6Qwen2.5 72B Instruct
LMArena Hard Prompts14841271
DTBench89.9%62.9%
LMCA46.5%13.4%
Epoch Capabilities Index152.24129
ForecastBench6257.5
ARC-AGI-260.4%—
NYT Connections (extended)80.9%—
ARC-AGI-186.5%—
CritPt3.1%—
Chess Puzzles13%—
Thematic Generalization76.3%—
Mystery Game Puzzles16%—
BIG-Bench Hard—79.8%
HellaSwag—84.8%
PIQA—82.6%
WinoGrande—82.3%

Math Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 52.9 (#49), Qwen2.5 72B Instruct: 19.3 (#287)

BenchmarkClaude Sonnet 4.6Qwen2.5 72B Instruct
OTIS Mock AIME 2024-202585.8%8.1%
LMArena Math14621283
ProofBench45%—
Omni-MATH—33%
MATH Level 5—63.2%
FrontierMath (Feb 2025 set)32.4%—
FrontierMath Tier 4 (v1)8.3%—

Knowledge Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 51.7 (#65), Qwen2.5 72B Instruct: 27.0 (#253)

BenchmarkClaude Sonnet 4.6Qwen2.5 72B Instruct
GPQA Diamond87.4%49.1%
LMArena Expert15001245
SimpleQA Verified35.5%—
MMLU-Pro—63.1%
Confabulations—19.1%
Vectara Hallucination Rate10.6%—
GPQA (HELM)—42.6%
ARC (AI2) Challenge—94.5%
MMLU—85.3%
TriviaQA—71.9%

Multimodal Not comparable

Claude Sonnet 4.6: 38.0 (#68), Qwen2.5 72B Instruct: —

BenchmarkClaude Sonnet 4.6Qwen2.5 72B Instruct
LMArena Vision1283—
Blueprint-Bench 26.7%—
LMArena Document1482—

Multilingual Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 54.4 (#41), Qwen2.5 72B Instruct: 41.0 (#213)

BenchmarkClaude Sonnet 4.6Qwen2.5 72B Instruct
LMArena Non-English14401252
LMArena Chinese14911272
LMArena French14651280
LMArena German14281234
LMArena Japanese14201180
LMArena Korean14111188
LMArena Russian14401264
LMArena Spanish14641256

Instruction Following Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 77.4 (#25), Qwen2.5 72B Instruct: 65.5 (#221)

BenchmarkClaude Sonnet 4.6Qwen2.5 72B Instruct
LMArena Instruction Following14751254
IFEval—80.6%

Long Context Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 45.3 (#44), Qwen2.5 72B Instruct: 38.9 (#188)

BenchmarkClaude Sonnet 4.6Qwen2.5 72B Instruct
LMArena Longer Query14791282

Writing & Preference Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 70.2 (#22), Qwen2.5 72B Instruct: 46.7 (#215)

BenchmarkClaude Sonnet 4.6Qwen2.5 72B Instruct
LMArena Text14581269
LMArena Creative Writing14351221
LMArena Multi-Turn14641272
EQ-Bench Creative Writing1810—
WildBench—80.2%
EQ-Bench 41207—

Frequently asked questions

Is Claude Sonnet 4.6 better than Qwen2.5 72B Instruct?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 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 4.6's lead doesn't matter for your workload.

Which is cheaper, Claude Sonnet 4.6 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 4.6 lists at $3 and $15.

Is Claude Sonnet 4.6 or Qwen2.5 72B Instruct better for coding?

Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 33.2 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 4.6 does, with 1M tokens against 131K.

How many benchmarks do Claude Sonnet 4.6 and Qwen2.5 72B Instruct share?

24 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Qwen2.5 72B Instruct has 43.

Related comparisons

Go deeper