Noometry

Model comparison

Claude 3 Opus vs Llama 3.2 90B

Claude 3 Opus is the stronger model overall, scoring 29.3 to 27.1 on the Noometry Index.

Last verified . 7 shared benchmarks.

Claude 3 Opus Anthropic

29.3

Rank #300 Confirmed

Llama 3.2 90B Meta

27.1

Rank #326 Confirmed

Summary

  • They share 7 benchmarks with published results for both. Claude 3 Opus scores higher in 3 categories and Llama 3.2 90B in 2 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Llama 3.2 90B leads 20.9 to 14.2.
  • The biggest single-benchmark swing is GPQA Diamond: 47.2% for Claude 3 Opus and 41% for Llama 3.2 90B.
  • Llama 3.2 90B has downloadable open weights; the other is API-only.

Side by side

Claude 3 OpusLlama 3.2 90B
ProviderAnthropicMeta
Noometry Index29.327.1
Released2024-02-292024-09-24
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked469

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

Category by category

Coding Not comparable

Claude 3 Opus: 32.4 (#261), Llama 3.2 90B: —

BenchmarkClaude 3 OpusLlama 3.2 90B
WeirdML19.2%—
BigCodeBench Instruct45.5%—
LiveBench Coding38.6%—
LMArena Coding1264—
BigCodeBench Complete57.4%—
HumanEval+77.4%—
MBPP+73.3%—

Agentic & Tool Use Llama 3.2 90B leads

Claude 3 Opus: 24.3 (#110), Llama 3.2 90B: 29.7 (#73)

BenchmarkClaude 3 OpusLlama 3.2 90B
Cybench10%—
BALROG—27.3%
METR Time Horizons29.5%—

Reasoning Llama 3.2 90B leads

Claude 3 Opus: 14.2 (#318), Llama 3.2 90B: 20.9 (#207)

BenchmarkClaude 3 OpusLlama 3.2 90B
EnigmaEval0.8%0.4%
Epoch Capabilities Index126.91125.5
SimpleBench23.5%—
Chess Puzzles5%—
LiveBench Reasoning40.6%—
LMArena Hard Prompts1246—
DTBench61.6%—
LiveBench Data Analysis57.9%—
LMCA17%—
ForecastBench58.4—
LiveBench49.2%—
WinoGrande88.5%—

Math Claude 3 Opus leads

Claude 3 Opus: 13.9 (#293), Llama 3.2 90B: 10.4 (#302)

BenchmarkClaude 3 OpusLlama 3.2 90B
OTIS Mock AIME 2024-20254.7%2.6%
MATH Level 537.5%39.4%
LiveBench Math43.6%—
LMArena Math1273—

Knowledge Claude 3 Opus leads

Claude 3 Opus: 24.5 (#262), Llama 3.2 90B: 21.7 (#269)

BenchmarkClaude 3 OpusLlama 3.2 90B
GPQA Diamond47.2%41%
MMLU84.6%80.3%
SimpleQA Verified12.6%—
Confabulations22.7%—
LMArena Expert1223—

Multimodal Claude 3 Opus leads

Claude 3 Opus: 26.6 (#112), Llama 3.2 90B: 24.9 (#119)

BenchmarkClaude 3 OpusLlama 3.2 90B
LMArena Vision10231000
GeoBench—52%

Multilingual Not comparable

Claude 3 Opus: 41.6 (#202), Llama 3.2 90B: —

BenchmarkClaude 3 OpusLlama 3.2 90B
LMArena Non-English1258—
LMArena Chinese1248—
LMArena French1274—
LMArena German1258—
LMArena Japanese1204—
LMArena Korean1187—
LMArena Russian1280—
LMArena Spanish1246—

Instruction Following Not comparable

Claude 3 Opus: 64.3 (#223), Llama 3.2 90B: —

BenchmarkClaude 3 OpusLlama 3.2 90B
LiveBench Instruction Following63.9%—
LMArena Instruction Following1248—

Long Context Not comparable

Claude 3 Opus: 38.2 (#197), Llama 3.2 90B: —

BenchmarkClaude 3 OpusLlama 3.2 90B
LMArena Longer Query1259—

Writing & Preference Not comparable

Claude 3 Opus: 47.4 (#208), Llama 3.2 90B: —

BenchmarkClaude 3 OpusLlama 3.2 90B
LMArena Text1262—
LMArena Creative Writing1235—
LMArena Multi-Turn1275—
LiveBench Language50.4%—

Frequently asked questions

Is Claude 3 Opus better than Llama 3.2 90B?

Claude 3 Opus is the stronger model overall, scoring 29.3 to 27.1 on the Noometry Index.

How many benchmarks do Claude 3 Opus and Llama 3.2 90B share?

7 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Llama 3.2 90B has 9.

Related comparisons

Go deeper