Noometry

Model comparison

Claude 3 Opus vs Qwen2-72B

Claude 3 Opus and Qwen2-72B score almost the same on the Noometry Index (29.5 vs 30.0), so choose on price, context window or the category you care about most.

Last verified . 25 shared benchmarks.

Claude 3 Opus Anthropic

29.5

Rank #310 Confirmed

Qwen2-72B Alibaba (Qwen)

30.0

Rank #300 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Claude 3 Opus scores higher in 7 categories and Qwen2-72B in 2 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen2-72B leads 30.2 to 14.8.
  • The biggest single-benchmark swing is WeirdML: 19.2% for Claude 3 Opus and 11.3% for Qwen2-72B.
  • Qwen2-72B has downloadable open weights; the other is API-only.

Side by side

Claude 3 OpusQwen2-72B
ProviderAnthropicAlibaba (Qwen)
Noometry Index29.530.0
Released2024-02-292024-06-07
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4626

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

Category by category

Coding Claude 3 Opus leads

Claude 3 Opus: 32.9 (#267), Qwen2-72B: 29.1 (#310)

BenchmarkClaude 3 OpusQwen2-72B
WeirdML19.2%11.3%
BigCodeBench Instruct45.5%38.5%
LMArena Coding12641196
BigCodeBench Complete57.4%54%
LiveBench Coding38.6%—
HumanEval+77.4%—
MBPP+73.3%—

Agentic & Tool Use Claude 3 Opus leads

Claude 3 Opus: 24.6 (#116), Qwen2-72B: 17.0 (#146)

BenchmarkClaude 3 OpusQwen2-72B
METR Time Horizons29.5%29.9%
TheAgentCompany—1.1%
Cybench10%—

Reasoning Qwen2-72B leads

Claude 3 Opus: 14.6 (#324), Qwen2-72B: 23.2 (#181)

BenchmarkClaude 3 OpusQwen2-72B
LMArena Hard Prompts12451191
Epoch Capabilities Index126.91125.28
SimpleBench23.5%—
Chess Puzzles5%—
EnigmaEval0.8%—
LiveBench Reasoning40.6%—
DTBench61.6%—
LiveBench Data Analysis57.9%—
LMCA17%—
ForecastBench58.4—
LiveBench49.2%—
WinoGrande88.5%—

Math Qwen2-72B leads

Claude 3 Opus: 14.8 (#299), Qwen2-72B: 30.2 (#236)

BenchmarkClaude 3 OpusQwen2-72B
LMArena Math12731235
MATH Level 537.5%39.1%
OTIS Mock AIME 2024-20254.7%—
LiveBench Math43.6%—

Knowledge Claude 3 Opus leads

Claude 3 Opus: 24.5 (#267), Qwen2-72B: 21.2 (#275)

BenchmarkClaude 3 OpusQwen2-72B
GPQA Diamond47.2%40.8%
LMArena Expert12231171
MMLU84.6%82.4%
SimpleQA Verified12.6%—
Confabulations22.7%—

Multimodal Not comparable

Claude 3 Opus: 27.1 (#116), Qwen2-72B: —

BenchmarkClaude 3 OpusQwen2-72B
LMArena Vision1023—

Multilingual Claude 3 Opus leads

Claude 3 Opus: 41.4 (#207), Qwen2-72B: 35.9 (#244)

BenchmarkClaude 3 OpusQwen2-72B
LMArena Non-English12581176
LMArena Chinese12481240
LMArena French12751170
LMArena German12581151
LMArena Japanese12041111
LMArena Korean11871083
LMArena Russian12801169
LMArena Spanish12461169

Instruction Following Claude 3 Opus leads

Claude 3 Opus: 64.1 (#228), Qwen2-72B: 61.7 (#241)

BenchmarkClaude 3 OpusQwen2-72B
LMArena Instruction Following12481181
LiveBench Instruction Following63.9%—

Long Context Claude 3 Opus leads

Claude 3 Opus: 38.2 (#202), Qwen2-72B: 36.1 (#235)

BenchmarkClaude 3 OpusQwen2-72B
LMArena Longer Query12591192

Writing & Preference Claude 3 Opus leads

Claude 3 Opus: 47.2 (#213), Qwen2-72B: 40.8 (#241)

BenchmarkClaude 3 OpusQwen2-72B
LMArena Text12621203
LMArena Creative Writing12351181
LMArena Multi-Turn12751196
LiveBench Language50.4%—

Frequently asked questions

Is Claude 3 Opus better than Qwen2-72B?

Claude 3 Opus and Qwen2-72B score almost the same on the Noometry Index (29.5 vs 30.0), so choose on price, context window or the category you care about most.

Is Claude 3 Opus or Qwen2-72B better for coding?

Claude 3 Opus scores higher on coding benchmarks: 32.9 versus 29.1 in the Noometry coding category.

How many benchmarks do Claude 3 Opus and Qwen2-72B share?

25 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Qwen2-72B has 26.

Related comparisons

Go deeper