Noometry

Model comparison

Claude Opus 4.5 vs Qwen2.5 72B Instruct

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 31.9 on the Noometry Index. Qwen2.5 72B Instruct costs 4.1× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

Last verified . 26 shared benchmarks.

Claude Opus 4.5 Anthropic

50.5

Rank #47 Confirmed

Qwen2.5 72B Instruct Alibaba (Qwen)

31.9

Rank #267 Confirmed

Summary

  • They share 26 benchmarks with published results for both. Claude Opus 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 Opus 4.5 leads 56.5 to 27.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 86.1% for Claude Opus 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 $5 / $25 for Claude Opus 4.5.
  • Claude Opus 4.5 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 4.5Qwen2.5 72B Instruct
ProviderAnthropicAlibaba (Qwen)
Noometry Index50.531.9
Released2025-11-012024-09
WeightsProprietaryOpen
Context window200K131K
Max output64K8K
Input $ / M tokens$5$1.40
Output $ / M tokens$25$5.60
Results tracked6943

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

Category by category

Coding Claude Opus 4.5 leads

Claude Opus 4.5: 54.8 (#27), Qwen2.5 72B Instruct: 33.2 (#260)

BenchmarkClaude Opus 4.5Qwen2.5 72B Instruct
WeirdML63.7%16%
LMArena Coding15041292
SWE-bench Verified76.7%—
SWE-bench Verified (bash only)76.8%—
LMArena WebDev1494—
SWE-bench Multilingual70.7%—
GSO26.5%—
BigCodeBench Instruct—45.8%
BigCodeBench Complete—55.9%
ALE-Bench1,025—
AlgoTune1.77—

Agentic & Tool Use Claude Opus 4.5 leads

Claude Opus 4.5: 47.3 (#12), Qwen2.5 72B Instruct: 22.1 (#133)

BenchmarkClaude Opus 4.5Qwen2.5 72B Instruct
BALROG43.5%16.2%
METR Time Horizons75%35.8%
Terminal-Bench63.1%—
Berkeley Function Calling Leaderboard77.5%—
GDPval45.5%—
Remote Labor Index3.8%—
TheAgentCompany—5.7%
τ²-bench Airline84%—
τ²-bench Banking24.7%—
τ²-bench Retail79.6%—
τ²-bench Telecom92.3%—
Cybench82%—
DeepResearch Bench54.8%—
OSWorld66.3%—
LMArena Search1180—
Vending-Bench 24,967—

Reasoning Claude Opus 4.5 leads

Claude Opus 4.5: 42.6 (#51), Qwen2.5 72B Instruct: 22.3 (#199)

BenchmarkClaude Opus 4.5Qwen2.5 72B Instruct
LMArena Hard Prompts14761271
DTBench89.9%62.9%
LMCA44.5%13.4%
Epoch Capabilities Index150.09129
ForecastBench60.757.5
ARC-AGI-237.6%—
SimpleBench62%—
Kagi LLM Benchmark80.2%—
NYT Connections (extended)52.5%—
ARC-AGI-180%—
Chess Puzzles12%—
EnigmaEval11.9%—
EBR-Bench14.3%—
Mystery Game Puzzles22%—
BIG-Bench Hard—79.8%
HellaSwag—84.8%
PIQA—82.6%
WinoGrande—82.3%

Math Claude Opus 4.5 leads

Claude Opus 4.5: 38.6 (#132), Qwen2.5 72B Instruct: 19.3 (#287)

BenchmarkClaude Opus 4.5Qwen2.5 72B Instruct
OTIS Mock AIME 2024-202586.1%8.1%
LMArena Math14631283
FrontierMath (Tiers 1-3)34.4%—
FrontierMath Tier 44.9%—
ProofBench36%—
Omni-MATH—33%
MATH Level 5—63.2%
FrontierMath (Feb 2025 set)20.7%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Claude Opus 4.5 leads

Claude Opus 4.5: 56.5 (#44), Qwen2.5 72B Instruct: 27.0 (#253)

BenchmarkClaude Opus 4.5Qwen2.5 72B Instruct
GPQA Diamond86%49.1%
LMArena Expert14871245
Humanity's Last Exam25.2%—
SimpleQA Verified45.7%—
MMLU-Pro—63.1%
Confabulations—19.1%
Vectara Hallucination Rate10.9%—
GPQA (HELM)—42.6%
ARC (AI2) Challenge—94.5%
MMLU—85.3%
TriviaQA—71.9%

Multimodal Not comparable

Claude Opus 4.5: 31.4 (#107), Qwen2.5 72B Instruct: —

BenchmarkClaude Opus 4.5Qwen2.5 72B Instruct
GeoBench75%—
VPCT40%—
Furniture Assembly28.3%—
LMArena Document1462—

Multilingual Claude Opus 4.5 leads

Claude Opus 4.5: 54.3 (#47), Qwen2.5 72B Instruct: 41.0 (#213)

BenchmarkClaude Opus 4.5Qwen2.5 72B Instruct
LMArena Non-English14381252
LMArena Chinese14701272
LMArena French14711280
LMArena German14491234
LMArena Japanese14161180
LMArena Korean14241188
LMArena Russian14471264
LMArena Spanish14581256

Instruction Following Claude Opus 4.5 leads

Claude Opus 4.5: 77.5 (#19), Qwen2.5 72B Instruct: 65.5 (#221)

BenchmarkClaude Opus 4.5Qwen2.5 72B Instruct
LMArena Instruction Following14781254
IFEval—80.6%

Long Context Claude Opus 4.5 leads

Claude Opus 4.5: 46.5 (#22), Qwen2.5 72B Instruct: 38.9 (#188)

BenchmarkClaude Opus 4.5Qwen2.5 72B Instruct
LMArena Longer Query14801282
CL-bench21.1%—

Writing & Preference Claude Opus 4.5 leads

Claude Opus 4.5: 68.1 (#28), Qwen2.5 72B Instruct: 46.7 (#215)

BenchmarkClaude Opus 4.5Qwen2.5 72B Instruct
LMArena Text14511269
LMArena Creative Writing14451221
LMArena Multi-Turn14661272
EQ-Bench Creative Writing1687—
WildBench—80.2%

Frequently asked questions

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

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 31.9 on the Noometry Index. Qwen2.5 72B Instruct costs 4.1× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 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 Opus 4.5 lists at $5 and $25.

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

Claude Opus 4.5 scores higher on coding benchmarks: 54.8 versus 33.2 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 4.5 does, with 200K tokens against 131K.

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

26 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and Qwen2.5 72B Instruct has 43.

Related comparisons

Go deeper