Noometry

Model comparison

Claude 3 Opus vs Qwen1.5-72B

Qwen1.5-72B is the stronger model overall, scoring 30.8 to 29.5 on the Noometry Index.

Last verified . 22 shared benchmarks.

Claude 3 Opus Anthropic

29.5

Rank #310 Confirmed

Qwen1.5-72B Alibaba (Qwen)

30.8

Rank #285 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Claude 3 Opus scores higher in 6 categories and Qwen1.5-72B in 2 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen1.5-72B leads 33.2 to 14.8.
  • The biggest single-benchmark swing is GPQA Diamond: 47.2% for Claude 3 Opus and 28.8% for Qwen1.5-72B.
  • Qwen1.5-72B has downloadable open weights; the other is API-only.

Side by side

Claude 3 OpusQwen1.5-72B
ProviderAnthropicAlibaba (Qwen)
Noometry Index29.530.8
Released2024-02-292024-02-04
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4622

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

Category by category

Coding Too close to call

Claude 3 Opus: 32.9 (#267), Qwen1.5-72B: 31.9 (#277)

BenchmarkClaude 3 OpusQwen1.5-72B
BigCodeBench Instruct45.5%33.2%
LMArena Coding12641165
BigCodeBench Complete57.4%40.3%
HumanEval+77.4%59.1%
MBPP+73.3%61.6%
WeirdML19.2%—
LiveBench Coding38.6%—

Agentic & Tool Use Not comparable

Claude 3 Opus: 24.6 (#116), Qwen1.5-72B: —

BenchmarkClaude 3 OpusQwen1.5-72B
Cybench10%—
METR Time Horizons29.5%—

Reasoning Qwen1.5-72B leads

Claude 3 Opus: 14.6 (#324), Qwen1.5-72B: 22.2 (#203)

BenchmarkClaude 3 OpusQwen1.5-72B
LMArena Hard Prompts12451148
SimpleBench23.5%—
Chess Puzzles5%—
EnigmaEval0.8%—
LiveBench Reasoning40.6%—
DTBench61.6%—
LiveBench Data Analysis57.9%—
LMCA17%—
Epoch Capabilities Index126.91—
ForecastBench58.4—
LiveBench49.2%—
WinoGrande88.5%—

Math Qwen1.5-72B leads

Claude 3 Opus: 14.8 (#299), Qwen1.5-72B: 33.2 (#205)

BenchmarkClaude 3 OpusQwen1.5-72B
LMArena Math12731164
OTIS Mock AIME 2024-20254.7%—
LiveBench Math43.6%—
MATH Level 537.5%—

Knowledge Claude 3 Opus leads

Claude 3 Opus: 24.5 (#267), Qwen1.5-72B: 11.5 (#300)

BenchmarkClaude 3 OpusQwen1.5-72B
GPQA Diamond47.2%28.8%
LMArena Expert12231136
SimpleQA Verified12.6%—
Confabulations22.7%—
MMLU84.6%—

Multimodal Not comparable

Claude 3 Opus: 27.1 (#116), Qwen1.5-72B: —

BenchmarkClaude 3 OpusQwen1.5-72B
LMArena Vision1023—

Multilingual Claude 3 Opus leads

Claude 3 Opus: 41.4 (#207), Qwen1.5-72B: 33.2 (#253)

BenchmarkClaude 3 OpusQwen1.5-72B
LMArena Non-English12581135
LMArena Chinese12481186
LMArena French12751159
LMArena German12581084
LMArena Japanese12041061
LMArena Korean11871050
LMArena Russian12801104
LMArena Spanish12461110

Instruction Following Claude 3 Opus leads

Claude 3 Opus: 64.1 (#228), Qwen1.5-72B: 59.3 (#256)

BenchmarkClaude 3 OpusQwen1.5-72B
LMArena Instruction Following12481141
LiveBench Instruction Following63.9%—

Long Context Claude 3 Opus leads

Claude 3 Opus: 38.2 (#202), Qwen1.5-72B: 35.1 (#243)

BenchmarkClaude 3 OpusQwen1.5-72B
LMArena Longer Query12591157

Writing & Preference Claude 3 Opus leads

Claude 3 Opus: 47.2 (#213), Qwen1.5-72B: 37.3 (#258)

BenchmarkClaude 3 OpusQwen1.5-72B
LMArena Text12621166
LMArena Creative Writing12351137
LMArena Multi-Turn12751160
LiveBench Language50.4%—

Frequently asked questions

Is Claude 3 Opus better than Qwen1.5-72B?

Qwen1.5-72B is the stronger model overall, scoring 30.8 to 29.5 on the Noometry Index.

Is Claude 3 Opus or Qwen1.5-72B better for coding?

They score almost the same on coding (32.9 vs 31.9); test both on your own repository before choosing.

How many benchmarks do Claude 3 Opus and Qwen1.5-72B share?

22 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Qwen1.5-72B has 22.

Related comparisons

Go deeper