Noometry

Model comparison

Claude Sonnet 4.5 vs Qwen2.5 72B Instruct

Claude Sonnet 4.5 is the stronger model overall, scoring 44.0 to 31.5 on the Noometry Index. Qwen2.5 72B Instruct costs 2.4× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

Last verified . 31 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.0

Rank #76 Confirmed

Qwen2.5 72B Instruct Alibaba (Qwen)

31.5

Rank #259 Confirmed

Summary

  • They share 31 benchmarks with published results for both. Claude Sonnet 4.5 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 knowledge, where Claude Sonnet 4.5 leads 48.4 to 26.9.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Claude Sonnet 4.5 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 4.5.
  • Claude Sonnet 4.5 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 4.5Qwen2.5 72B Instruct
ProviderAnthropicAlibaba (Qwen)
Noometry Index44.031.5
Released2025-09-292024-09
WeightsProprietaryOpen
Context window1M131K
Max output64K8K
Input $ / M tokens$3$1.40
Output $ / M tokens$15$5.60
Results tracked7343

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

Category by category

Coding Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 47.8 (#54), Qwen2.5 72B Instruct: 32.8 (#256)

BenchmarkClaude Sonnet 4.5Qwen2.5 72B Instruct
WeirdML47.7%16%
LMArena Coding14891293
SWE-bench Verified71.3%—
SWE-bench Verified (bash only)71.4%—
LMArena WebDev1393—
SWE-bench Multilingual67%—
SciCode44.7%—
GSO14.7%—
BigCodeBench Instruct—45.8%
BigCodeBench Complete—55.9%
ALE-Bench796.15—
AlgoTune1.52—

Agentic & Tool Use Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 38.1 (#30), Qwen2.5 72B Instruct: 22.0 (#124)

BenchmarkClaude Sonnet 4.5Qwen2.5 72B Instruct
METR Time Horizons67.4%35.8%
Terminal-Bench46.5%—
Berkeley Function Calling Leaderboard73.2%—
GDPval42.5%—
Remote Labor Index2.1%—
TheAgentCompany—5.7%
τ²-bench Airline72%—
τ²-bench Banking25.3%—
τ²-bench Retail72.4%—
τ²-bench Telecom84.9%—
Cybench60%—
DeepResearch Bench52.6%—
OSWorld62.9%—
BALROG—16.2%
LMArena Search1159—
Vending-Bench 23,839—

Reasoning Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 26.9 (#113), Qwen2.5 72B Instruct: 21.4 (#197)

BenchmarkClaude Sonnet 4.5Qwen2.5 72B Instruct
LMArena Hard Prompts14621271
DTBench83.2%62.9%
LMCA38.8%13.4%
Epoch Capabilities Index146.84129.01
ForecastBench61.957.5
ARC-AGI-213.6%—
SimpleBench54.3%—
Kagi LLM Benchmark57.9%—
NYT Connections (extended)37.3%—
ARC-AGI-163.7%—
CritPt1.1%—
Chess Puzzles12%—
EnigmaEval6%—
EBR-Bench2.4%—
Mystery Game Puzzles17%—
BIG-Bench Hard—79.8%
HellaSwag—84.8%
PIQA—82.6%
WinoGrande—82.3%

Math Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 31.9 (#190), Qwen2.5 72B Instruct: 18.1 (#281)

BenchmarkClaude Sonnet 4.5Qwen2.5 72B Instruct
OTIS Mock AIME 2024-202577.8%8.1%
Omni-MATH55.3%33%
LMArena Math14481283
MATH Level 597.7%63.2%
FrontierMath (Tiers 1-3)23.9%—
FrontierMath Tier 42.4%—
ProofBench19%—
FrontierMath (Feb 2025 set)15.2%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 48.4 (#70), Qwen2.5 72B Instruct: 26.9 (#247)

BenchmarkClaude Sonnet 4.5Qwen2.5 72B Instruct
GPQA Diamond82.3%49.1%
MMLU-Pro86.9%63.1%
GPQA (HELM)68.6%42.6%
LMArena Expert14831245
Humanity's Last Exam13.7%—
SimpleQA Verified30.7%—
Confabulations—19.1%
Vectara Hallucination Rate12%—
ARC (AI2) Challenge—94.5%
MMLU—85.3%
TriviaQA—71.9%

Multimodal Not comparable

Claude Sonnet 4.5: 34.1 (#84), Qwen2.5 72B Instruct: —

BenchmarkClaude Sonnet 4.5Qwen2.5 72B Instruct
VPCT39.8%—
LMArena Document1450—

Multilingual Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 53.6 (#65), Qwen2.5 72B Instruct: 41.2 (#208)

BenchmarkClaude Sonnet 4.5Qwen2.5 72B Instruct
LMArena Non-English14251252
LMArena Chinese14591272
LMArena French14591279
LMArena German14271234
LMArena Japanese13901180
LMArena Korean14031188
LMArena Russian14361264
LMArena Spanish14571255

Instruction Following Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 75.2 (#74), Qwen2.5 72B Instruct: 65.7 (#216)

BenchmarkClaude Sonnet 4.5Qwen2.5 72B Instruct
IFEval85%80.6%
LMArena Instruction Following14591254

Long Context Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 45.2 (#45), Qwen2.5 72B Instruct: 38.9 (#183)

BenchmarkClaude Sonnet 4.5Qwen2.5 72B Instruct
LMArena Longer Query14761282

Writing & Preference Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 66.7 (#33), Qwen2.5 72B Instruct: 46.9 (#210)

BenchmarkClaude Sonnet 4.5Qwen2.5 72B Instruct
LMArena Text14391269
LMArena Creative Writing14421221
WildBench85.4%80.2%
LMArena Multi-Turn14651272
EQ-Bench Creative Writing1678—

Frequently asked questions

Is Claude Sonnet 4.5 better than Qwen2.5 72B Instruct?

Claude Sonnet 4.5 is the stronger model overall, scoring 44.0 to 31.5 on the Noometry Index. Qwen2.5 72B Instruct costs 2.4× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

Which is cheaper, Claude Sonnet 4.5 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 4.5 lists at $3 and $15.

Is Claude Sonnet 4.5 or Qwen2.5 72B Instruct better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.8 versus 32.8 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 4.5 does, with 1M tokens against 131K.

How many benchmarks do Claude Sonnet 4.5 and Qwen2.5 72B Instruct share?

31 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Qwen2.5 72B Instruct has 43.

Related comparisons

Go deeper