Noometry

Model comparison

Claude Opus 5 vs Qwen2.5 72B Instruct

Claude Opus 5 is the stronger model overall, scoring 67.8 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 5's lead doesn't matter for your workload.

Last verified . 24 shared benchmarks.

Claude Opus 5 Anthropic

67.8

Rank #4 Confirmed

Qwen2.5 72B Instruct Alibaba (Qwen)

31.9

Rank #267 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Claude Opus 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 math, where Claude Opus 5 leads 86.2 to 19.3.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.9% for Claude Opus 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 5.
  • Claude Opus 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 Opus 5Qwen2.5 72B Instruct
ProviderAnthropicAlibaba (Qwen)
Noometry Index67.831.9
Released2026-07-242024-09
WeightsProprietaryOpen
Context window1M131K
Max output128K8K
Input $ / M tokens$5$1.40
Output $ / M tokens$25$5.60
Results tracked5743

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

Category by category

Coding Claude Opus 5 leads

Claude Opus 5: 67.5 (#5), Qwen2.5 72B Instruct: 33.2 (#260)

BenchmarkClaude Opus 5Qwen2.5 72B Instruct
WeirdML91.8%16%
LMArena Coding15341292
DeepSWE73.6%—
FrontierCode53.4%—
CursorBench46.6%—
LMArena WebDev1691—
FrontierSWE52%—
SciCode56.4%—
BigCodeBench Instruct—45.8%
BigCodeBench Complete—55.9%
ALE-Bench2,165—

Agentic & Tool Use Claude Opus 5 leads

Claude Opus 5: 55.6 (#1), Qwen2.5 72B Instruct: 22.1 (#133)

BenchmarkClaude Opus 5Qwen2.5 72B Instruct
BALROG63.4%16.2%
APEX-Agents65.8%—
OSWorld 2.031.4%—
TheAgentCompany—5.7%
τ²-bench Banking48.7%—
PostTrainBench35%—
GBAEval79.6%—
GDP.pdf24%—
METR Time Horizons—35.8%
Vending-Bench 211,182—

Reasoning Claude Opus 5 leads

Claude Opus 5: 77.2 (#4), Qwen2.5 72B Instruct: 22.3 (#199)

BenchmarkClaude Opus 5Qwen2.5 72B Instruct
LMArena Hard Prompts15261271
DTBench97.9%62.9%
LMCA64.5%13.4%
Epoch Capabilities Index162.78129
ARC-AGI-290.4%—
SimpleBench80.6%—
NYT Connections (extended)94.3%—
ARC-AGI-197.5%—
CritPt29.1%—
Chess Puzzles42%—
EBR-Bench45.7%—
Mystery Game Puzzles59%—
Bench to the Future 30.12—
BIG-Bench Hard—79.8%
ForecastBench—57.5
HellaSwag—84.8%
PIQA—82.6%
WinoGrande—82.3%

Math Claude Opus 5 leads

Claude Opus 5: 86.2 (#8), Qwen2.5 72B Instruct: 19.3 (#287)

BenchmarkClaude Opus 5Qwen2.5 72B Instruct
OTIS Mock AIME 2024-202598.9%8.1%
LMArena Math15311283
FrontierMath (Tiers 1-3)85.6%—
FrontierMath Tier 473.2%—
ProofBench99%—
Omni-MATH—33%
MATH Level 5—63.2%

Knowledge Claude Opus 5 leads

Claude Opus 5: 66.8 (#9), Qwen2.5 72B Instruct: 27.0 (#253)

BenchmarkClaude Opus 5Qwen2.5 72B Instruct
GPQA Diamond93.9%49.1%
LMArena Expert15571245
SimpleQA Verified59.9%—
MMLU-Pro—63.1%
Confabulations—19.1%
GPQA (HELM)—42.6%
ARC (AI2) Challenge—94.5%
MMLU—85.3%
TriviaQA—71.9%

Multimodal Not comparable

Claude Opus 5: 50.8 (#8), Qwen2.5 72B Instruct: —

BenchmarkClaude Opus 5Qwen2.5 72B Instruct
LMArena Vision1319—
Blueprint-Bench 230.4%—
Furniture Assembly60.8%—
LMArena Document1516—

Multilingual Claude Opus 5 leads

Claude Opus 5: 58.8 (#4), Qwen2.5 72B Instruct: 41.0 (#213)

BenchmarkClaude Opus 5Qwen2.5 72B Instruct
LMArena Non-English15011252
LMArena Chinese15741272
LMArena French15191280
LMArena German15241234
LMArena Japanese15161180
LMArena Korean15211188
LMArena Russian15071264
LMArena Spanish15191256

Instruction Following Claude Opus 5 leads

Claude Opus 5: 79.2 (#7), Qwen2.5 72B Instruct: 65.5 (#221)

BenchmarkClaude Opus 5Qwen2.5 72B Instruct
LMArena Instruction Following15171254
IFEval—80.6%

Long Context Claude Opus 5 leads

Claude Opus 5: 46.5 (#21), Qwen2.5 72B Instruct: 38.9 (#188)

BenchmarkClaude Opus 5Qwen2.5 72B Instruct
LMArena Longer Query15151282

Writing & Preference Claude Opus 5 leads

Claude Opus 5: 79.2 (#1), Qwen2.5 72B Instruct: 46.7 (#215)

BenchmarkClaude Opus 5Qwen2.5 72B Instruct
LMArena Text15071269
LMArena Creative Writing14911221
LMArena Multi-Turn14991272
EQ-Bench Creative Writing2133—
WildBench—80.2%
EQ-Bench 41385—

Frequently asked questions

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

Claude Opus 5 is the stronger model overall, scoring 67.8 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 5's lead doesn't matter for your workload.

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

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

Claude Opus 5 scores higher on coding benchmarks: 67.5 versus 33.2 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 5 does, with 1M tokens against 131K.

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

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

Related comparisons

Go deeper