Noometry

Model comparison

Claude Opus 5 vs Qwen1.5-72B

Claude Opus 5 is the stronger model overall, scoring 67.7 to 30.3 on the Noometry Index.

Last verified . 18 shared benchmarks.

Claude Opus 5 Anthropic

67.7

Rank #4 Confirmed

Qwen1.5-72B Alibaba (Qwen)

30.3

Rank #282 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Claude Opus 5 scores higher in 8 categories and Qwen1.5-72B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Opus 5 leads 77.1 to 21.2.
  • The biggest single-benchmark swing is GPQA Diamond: 93.9% for Claude Opus 5 and 28.8% for Qwen1.5-72B.
  • Qwen1.5-72B has downloadable open weights; the other is API-only.

Side by side

Claude Opus 5Qwen1.5-72B
ProviderAnthropicAlibaba (Qwen)
Noometry Index67.730.3
Released2026-07-242024-02-04
WeightsProprietaryOpen
Context window1M—
Max output128K—
Input $ / M tokens$5—
Output $ / M tokens$25—
Results tracked5722

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

Category by category

Coding Claude Opus 5 leads

Claude Opus 5: 67.0 (#5), Qwen1.5-72B: 31.4 (#272)

BenchmarkClaude Opus 5Qwen1.5-72B
LMArena Coding15331166
DeepSWE73.6%—
FrontierCode53.4%—
CursorBench46.6%—
LMArena WebDev1694—
FrontierSWE52%—
SciCode56.4%—
WeirdML91.8%—
BigCodeBench Instruct—33.2%
BigCodeBench Complete—40.3%
ALE-Bench2,165—
HumanEval+—59.1%
MBPP+—61.6%

Agentic & Tool Use Not comparable

Claude Opus 5: 55.5 (#1), Qwen1.5-72B: —

BenchmarkClaude Opus 5Qwen1.5-72B
APEX-Agents65.8%—
OSWorld 2.031.4%—
τ²-bench Banking48.7%—
PostTrainBench35%—
BALROG63.4%—
GBAEval79.6%—
GDP.pdf24%—
Vending-Bench 211,182—

Reasoning Claude Opus 5 leads

Claude Opus 5: 77.1 (#3), Qwen1.5-72B: 21.2 (#201)

BenchmarkClaude Opus 5Qwen1.5-72B
LMArena Hard Prompts15251148
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%—
DTBench97.9%—
LMCA64.5%—
Bench to the Future 30.12—
Epoch Capabilities Index162.67—

Math Claude Opus 5 leads

Claude Opus 5: 86.1 (#6), Qwen1.5-72B: 30.7 (#205)

BenchmarkClaude Opus 5Qwen1.5-72B
LMArena Math15331164
FrontierMath (Tiers 1-3)85.6%—
FrontierMath Tier 473.2%—
OTIS Mock AIME 2024-202598.9%—
ProofBench99%—

Knowledge Claude Opus 5 leads

Claude Opus 5: 66.8 (#8), Qwen1.5-72B: 11.5 (#295)

BenchmarkClaude Opus 5Qwen1.5-72B
GPQA Diamond93.9%28.8%
LMArena Expert15581136
SimpleQA Verified59.9%—

Multimodal Not comparable

Claude Opus 5: 51.1 (#6), Qwen1.5-72B: —

BenchmarkClaude Opus 5Qwen1.5-72B
LMArena Vision1321—
Blueprint-Bench 230.4%—
Furniture Assembly60.8%—
LMArena Document1516—

Multilingual Claude Opus 5 leads

Claude Opus 5: 58.8 (#3), Qwen1.5-72B: 33.4 (#248)

BenchmarkClaude Opus 5Qwen1.5-72B
LMArena Non-English15001135
LMArena Chinese15751186
LMArena French15221158
LMArena German15221084
LMArena Japanese15101061
LMArena Korean15261049
LMArena Russian15071104
LMArena Spanish15191110

Instruction Following Claude Opus 5 leads

Claude Opus 5: 79.3 (#5), Qwen1.5-72B: 59.6 (#251)

BenchmarkClaude Opus 5Qwen1.5-72B
LMArena Instruction Following15161142

Long Context Claude Opus 5 leads

Claude Opus 5: 46.5 (#20), Qwen1.5-72B: 35.0 (#238)

BenchmarkClaude Opus 5Qwen1.5-72B
LMArena Longer Query15161157

Writing & Preference Claude Opus 5 leads

Claude Opus 5: 79.3 (#2), Qwen1.5-72B: 37.4 (#253)

BenchmarkClaude Opus 5Qwen1.5-72B
LMArena Text15061166
LMArena Creative Writing14911137
LMArena Multi-Turn14961160
EQ-Bench Creative Writing2133—
EQ-Bench 41385—

Frequently asked questions

Is Claude Opus 5 better than Qwen1.5-72B?

Claude Opus 5 is the stronger model overall, scoring 67.7 to 30.3 on the Noometry Index.

Is Claude Opus 5 or Qwen1.5-72B better for coding?

Claude Opus 5 scores higher on coding benchmarks: 67.0 versus 31.4 in the Noometry coding category.

How many benchmarks do Claude Opus 5 and Qwen1.5-72B share?

18 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and Qwen1.5-72B has 22.

Related comparisons

Go deeper