Noometry

Model comparison

Gemini 3.5 Flash vs Llama 3.2 90B

Gemini 3.5 Flash is the stronger model overall, scoring 54.1 to 27.1 on the Noometry Index.

Last verified . 5 shared benchmarks.

Gemini 3.5 Flash Google

54.1

Rank #29 Confirmed

Llama 3.2 90B Meta

27.1

Rank #326 Confirmed

Summary

  • They share 5 benchmarks with published results for both. Gemini 3.5 Flash scores higher in 4 categories and Llama 3.2 90B in 1 category; 5 gaps are clear of the uncertainty.
  • The widest gap is in math, where Gemini 3.5 Flash leads 60.5 to 10.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Gemini 3.5 Flash and 2.6% for Llama 3.2 90B.
  • Llama 3.2 90B has downloadable open weights; the other is API-only.

Side by side

Gemini 3.5 FlashLlama 3.2 90B
ProviderGoogleMeta
Noometry Index54.127.1
Released2026-05-192024-09-24
WeightsProprietaryOpen
Context window1.05M—
Max output66K—
Input $ / M tokens$1.50—
Output $ / M tokens$9—
Results tracked549

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

Category by category

Coding Not comparable

Gemini 3.5 Flash: 49.1 (#46), Llama 3.2 90B: —

BenchmarkGemini 3.5 FlashLlama 3.2 90B
SWE-bench Verified79.3%—
DeepSWE37.4%—
LMArena WebDev1499—
SciCode53.1%—
WeirdML62.6%—
LMArena Coding1492—
ALE-Bench911.02—

Agentic & Tool Use Llama 3.2 90B leads

Gemini 3.5 Flash: 24.8 (#107), Llama 3.2 90B: 29.7 (#73)

BenchmarkGemini 3.5 FlashLlama 3.2 90B
APEX-Agents27.5%—
BALROG—27.3%
GBAEval6.7%—
GDP.pdf14%—
Vending-Bench 25,396—

Reasoning Gemini 3.5 Flash leads

Gemini 3.5 Flash: 62.7 (#16), Llama 3.2 90B: 20.9 (#207)

BenchmarkGemini 3.5 FlashLlama 3.2 90B
EnigmaEval25.4%0.4%
Epoch Capabilities Index154.55125.5
ARC-AGI-272.1%—
SimpleBench76.7%—
NYT Connections (extended)92.6%—
ARC-AGI-192.5%—
CritPt13.1%—
Chess Puzzles50%—
EBR-Bench4.8%—
LMArena Hard Prompts1488—
Mystery Game Puzzles32%—
DTBench94.7%—
LMCA47.1%—
Surface Evolver Bench58.1%—
ForecastBench59—

Math Gemini 3.5 Flash leads

Gemini 3.5 Flash: 60.5 (#30), Llama 3.2 90B: 10.4 (#302)

BenchmarkGemini 3.5 FlashLlama 3.2 90B
OTIS Mock AIME 2024-202595.6%2.6%
FrontierMath (Tiers 1-3)62.8%—
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions76.3%—
ProofBench31%—
LMArena Math1502—
MATH Level 5—39.4%
FrontierMath (Feb 2025 set)39%—
FrontierMath Tier 4 (v1)14.6%—

Knowledge Gemini 3.5 Flash leads

Gemini 3.5 Flash: 66.3 (#10), Llama 3.2 90B: 21.7 (#269)

BenchmarkGemini 3.5 FlashLlama 3.2 90B
GPQA Diamond92.8%41%
SimpleQA Verified66.2%—
LMArena Expert1493—
MMLU—80.3%

Multimodal Gemini 3.5 Flash leads

Gemini 3.5 Flash: 45.7 (#13), Llama 3.2 90B: 24.9 (#119)

BenchmarkGemini 3.5 FlashLlama 3.2 90B
LMArena Vision13111000
GeoBench—52%
Blueprint-Bench 233.6%—
LMArena Document1463—

Multilingual Not comparable

Gemini 3.5 Flash: 57.1 (#12), Llama 3.2 90B: —

BenchmarkGemini 3.5 FlashLlama 3.2 90B
LMArena Non-English1475—
LMArena Chinese1525—
LMArena French1490—
LMArena German1500—
LMArena Japanese1481—
LMArena Korean1453—
LMArena Russian1491—
LMArena Spanish1478—

Instruction Following Not comparable

Gemini 3.5 Flash: 77.2 (#29), Llama 3.2 90B: —

BenchmarkGemini 3.5 FlashLlama 3.2 90B
LMArena Instruction Following1466—

Long Context Not comparable

Gemini 3.5 Flash: 45.3 (#39), Llama 3.2 90B: —

BenchmarkGemini 3.5 FlashLlama 3.2 90B
LMArena Longer Query1481—

Writing & Preference Not comparable

Gemini 3.5 Flash: 65.5 (#46), Llama 3.2 90B: —

BenchmarkGemini 3.5 FlashLlama 3.2 90B
LMArena Text1481—
LMArena Creative Writing1467—
EQ-Bench 41087—
LMArena Multi-Turn1482—

Frequently asked questions

Is Gemini 3.5 Flash better than Llama 3.2 90B?

Gemini 3.5 Flash is the stronger model overall, scoring 54.1 to 27.1 on the Noometry Index.

How many benchmarks do Gemini 3.5 Flash and Llama 3.2 90B share?

5 benchmarks have published results for both models. Gemini 3.5 Flash has 54 scored results on Noometry and Llama 3.2 90B has 9.

Related comparisons

Go deeper