Noometry

Model comparison

Gemini 1.5 Pro (May 2024) vs Llama 3.2 90B

Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 32.1 to 27.5 on the Noometry Index.

Last verified . 7 shared benchmarks.

Gemini 1.5 Pro (May 2024) Google

32.1

Rank #261 Confirmed

Llama 3.2 90B Meta

27.5

Rank #331 Confirmed

Summary

  • They share 7 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) 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 math, where Gemini 1.5 Pro (May 2024) leads 25.8 to 11.1.
  • The biggest single-benchmark swing is MATH Level 5: 70.4% for Gemini 1.5 Pro (May 2024) and 39.4% for Llama 3.2 90B.
  • Llama 3.2 90B has downloadable open weights; the other is API-only.

Side by side

Gemini 1.5 Pro (May 2024)Llama 3.2 90B
ProviderGoogleMeta
Noometry Index32.127.5
Released2024-02-152024-09-24
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked459

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

Category by category

Coding Not comparable

Gemini 1.5 Pro (May 2024): 34.2 (#241), Llama 3.2 90B: —

BenchmarkGemini 1.5 Pro (May 2024)Llama 3.2 90B
WeirdML22.2%—
BigCodeBench Instruct43.8%—
LMArena Coding1294—
BigCodeBench Complete57.5%—
CadEval34%—
HumanEval+79.3%—
MBPP+74.6%—

Agentic & Tool Use Llama 3.2 90B leads

Gemini 1.5 Pro (May 2024): 17.9 (#145), Llama 3.2 90B: 30.0 (#80)

BenchmarkGemini 1.5 Pro (May 2024)Llama 3.2 90B
BALROG21%27.3%
TheAgentCompany3.4%—
Cybench7.5%—

Reasoning Llama 3.2 90B leads

Gemini 1.5 Pro (May 2024): 12.3 (#338), Llama 3.2 90B: 21.7 (#217)

BenchmarkGemini 1.5 Pro (May 2024)Llama 3.2 90B
Epoch Capabilities Index131.73125.5
ARC-AGI-20.8%—
SimpleBench27.1%—
EnigmaEval—0.4%
LMArena Hard Prompts1296—
DTBench59%—
BIG-Bench Hard89.2%—
ForecastBench58.4—

Math Gemini 1.5 Pro (May 2024) leads

Gemini 1.5 Pro (May 2024): 25.8 (#266), Llama 3.2 90B: 11.1 (#308)

BenchmarkGemini 1.5 Pro (May 2024)Llama 3.2 90B
OTIS Mock AIME 2024-202523.1%2.6%
MATH Level 570.4%39.4%
Omni-MATH36.4%—
LMArena Math1315—

Knowledge Gemini 1.5 Pro (May 2024) leads

Gemini 1.5 Pro (May 2024): 29.4 (#239), Llama 3.2 90B: 21.7 (#274)

BenchmarkGemini 1.5 Pro (May 2024)Llama 3.2 90B
GPQA Diamond57.2%41%
MMLU86.9%80.3%
Humanity's Last Exam4.6%—
MMLU-Pro73.7%—
Confabulations13.5%—
GPQA (HELM)53.4%—
LMArena Expert1279—

Multimodal Gemini 1.5 Pro (May 2024) leads

Gemini 1.5 Pro (May 2024): 36.8 (#77), Llama 3.2 90B: 25.4 (#124)

BenchmarkGemini 1.5 Pro (May 2024)Llama 3.2 90B
LMArena Vision11611000
Video-MME75%—
GeoBench—52%

Multilingual Not comparable

Gemini 1.5 Pro (May 2024): 45.3 (#174), Llama 3.2 90B: —

BenchmarkGemini 1.5 Pro (May 2024)Llama 3.2 90B
LMArena Non-English1312—
LMArena Chinese1331—
LMArena French1302—
LMArena German1286—
LMArena Japanese1292—
LMArena Korean1298—
LMArena Russian1320—
LMArena Spanish1311—

Instruction Following Not comparable

Gemini 1.5 Pro (May 2024): 68.6 (#185), Llama 3.2 90B: —

BenchmarkGemini 1.5 Pro (May 2024)Llama 3.2 90B
IFEval83.7%—
LMArena Instruction Following1297—

Long Context Not comparable

Gemini 1.5 Pro (May 2024): 39.8 (#169), Llama 3.2 90B: —

BenchmarkGemini 1.5 Pro (May 2024)Llama 3.2 90B
LMArena Longer Query1308—

Writing & Preference Not comparable

Gemini 1.5 Pro (May 2024): 52.4 (#172), Llama 3.2 90B: —

BenchmarkGemini 1.5 Pro (May 2024)Llama 3.2 90B
LMArena Text1319—
LMArena Creative Writing1333—
WildBench81.3%—
LMArena Multi-Turn1296—

Frequently asked questions

Is Gemini 1.5 Pro (May 2024) better than Llama 3.2 90B?

Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 32.1 to 27.5 on the Noometry Index.

How many benchmarks do Gemini 1.5 Pro (May 2024) and Llama 3.2 90B share?

7 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Llama 3.2 90B has 9.

Related comparisons

Go deeper