Noometry

Model comparison

Claude Opus 4 vs Qwen2.5 72B Instruct

Claude Opus 4 is the stronger model overall, scoring 43.1 to 31.9 on the Noometry Index. Qwen2.5 72B Instruct costs 12× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.

Last verified . 32 shared benchmarks.

Claude Opus 4 Anthropic

43.1

Rank #100 Confirmed

Qwen2.5 72B Instruct Alibaba (Qwen)

31.9

Rank #267 Confirmed

Summary

  • They share 32 benchmarks with published results for both. Claude Opus 4 scores higher in 9 categories and Qwen2.5 72B Instruct in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Opus 4 leads 42.0 to 19.3.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 64.4% for Claude Opus 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 $15 / $75 for Claude Opus 4.
  • Claude Opus 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 Opus 4Qwen2.5 72B Instruct
ProviderAnthropicAlibaba (Qwen)
Noometry Index43.131.9
Released2025-05-222024-09
WeightsProprietaryOpen
Context window200K131K
Max output32K8K
Input $ / M tokens$15$1.40
Output $ / M tokens$75$5.60
Results tracked5643

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

Category by category

Coding Claude Opus 4 leads

Claude Opus 4: 47.2 (#62), Qwen2.5 72B Instruct: 33.2 (#260)

BenchmarkClaude Opus 4Qwen2.5 72B Instruct
WeirdML43.7%16%
LMArena Coding14421292
SWE-bench Verified70.7%—
SWE-bench Verified (bash only)67.6%—
Aider Polyglot72%—
GSO6.9%—
BigCodeBench Instruct—45.8%
BigCodeBench Complete—55.9%
AlgoTune1.33—

Agentic & Tool Use Claude Opus 4 leads

Claude Opus 4: 34.8 (#42), Qwen2.5 72B Instruct: 22.1 (#133)

BenchmarkClaude Opus 4Qwen2.5 72B Instruct
METR Time Horizons63.9%35.8%
TheAgentCompany—5.7%
Cybench38%—
DeepResearch Bench46.8%—
BALROG—16.2%
LMArena Search1127—

Reasoning Claude Opus 4 leads

Claude Opus 4: 27.3 (#121), Qwen2.5 72B Instruct: 22.3 (#199)

BenchmarkClaude Opus 4Qwen2.5 72B Instruct
LMArena Hard Prompts13991271
DTBench81.6%62.9%
LMCA37.4%13.4%
Epoch Capabilities Index142.67129
ForecastBench61.157.5
ARC-AGI-28.6%—
SimpleBench58.8%—
Kagi LLM Benchmark74.3%—
ARC-AGI-135.7%—
CritPt0.3%—
EnigmaEval5.6%—
BIG-Bench Hard—79.8%
HellaSwag—84.8%
PIQA—82.6%
WinoGrande—82.3%

Math Claude Opus 4 leads

Claude Opus 4: 42.0 (#86), Qwen2.5 72B Instruct: 19.3 (#287)

BenchmarkClaude Opus 4Qwen2.5 72B Instruct
OTIS Mock AIME 2024-202564.4%8.1%
Omni-MATH61.6%33%
LMArena Math13901283
MATH Level 585%63.2%
FrontierMath (Feb 2025 set)4.5%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Claude Opus 4 leads

Claude Opus 4: 44.0 (#88), Qwen2.5 72B Instruct: 27.0 (#253)

BenchmarkClaude Opus 4Qwen2.5 72B Instruct
GPQA Diamond76.3%49.1%
MMLU-Pro87.5%63.1%
Confabulations15.9%19.1%
GPQA (HELM)70.8%42.6%
LMArena Expert13861245
Humanity's Last Exam10.7%—
Vectara Hallucination Rate12%—
ARC (AI2) Challenge—94.5%
MMLU—85.3%
TriviaQA—71.9%

Multimodal Not comparable

Claude Opus 4: 31.5 (#106), Qwen2.5 72B Instruct: —

BenchmarkClaude Opus 4Qwen2.5 72B Instruct
LMArena Vision1192—
GeoBench49%—
VPCT38%—

Multilingual Claude Opus 4 leads

Claude Opus 4: 48.8 (#138), Qwen2.5 72B Instruct: 41.0 (#213)

BenchmarkClaude Opus 4Qwen2.5 72B Instruct
LMArena Non-English13621252
LMArena Chinese13861272
LMArena French13721280
LMArena German13911234
LMArena Japanese13311180
LMArena Korean13211188
LMArena Russian13921264
LMArena Spanish13891256

Instruction Following Claude Opus 4 leads

Claude Opus 4: 77.1 (#28), Qwen2.5 72B Instruct: 65.5 (#221)

BenchmarkClaude Opus 4Qwen2.5 72B Instruct
IFEval91.8%80.6%
LMArena Instruction Following14061254

Long Context Too close to call

Claude Opus 4: 39.6 (#172), Qwen2.5 72B Instruct: 38.9 (#188)

BenchmarkClaude Opus 4Qwen2.5 72B Instruct
LMArena Longer Query14221282
Fiction.LiveBench61.1%—

Writing & Preference Claude Opus 4 leads

Claude Opus 4: 61.2 (#89), Qwen2.5 72B Instruct: 46.7 (#215)

BenchmarkClaude Opus 4Qwen2.5 72B Instruct
LMArena Text13771269
LMArena Creative Writing13871221
WildBench85.2%80.2%
LMArena Multi-Turn13961272
Short-Story Creative Writing83.6%—
EQ-Bench Creative Writing1580—

Frequently asked questions

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

Claude Opus 4 is the stronger model overall, scoring 43.1 to 31.9 on the Noometry Index. Qwen2.5 72B Instruct costs 12× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 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 Opus 4 lists at $15 and $75.

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

Claude Opus 4 scores higher on coding benchmarks: 47.2 versus 33.2 in the Noometry coding category.

Which has the bigger context window?

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

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

32 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and Qwen2.5 72B Instruct has 43.

Related comparisons

Go deeper