Noometry

Model comparison

Gemini 3.8 Flash vs Llama 3.2 90B

Gemini 3.8 Flash is the stronger model overall, scoring 59.5 to 27.1 on the Noometry Index.

Last verified . 4 shared benchmarks.

Gemini 3.8 Flash Google

59.5

Rank #13 Confirmed

Llama 3.2 90B Meta

27.1

Rank #326 Confirmed

Summary

  • They share 4 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 5 categories and Llama 3.2 90B in 0 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in math, where Gemini 3.8 Flash leads 65.2 to 10.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.9% for Gemini 3.8 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 3.8 FlashLlama 3.2 90B
ProviderGoogleMeta
Noometry Index59.527.1
Released2026-09-022024-09-24
WeightsProprietaryOpen
Context window1.05M—
Max output66K—
Input $ / M tokens$0.75—
Output $ / M tokens$3.75—
Results tracked469

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

Category by category

Coding Not comparable

Gemini 3.8 Flash: 56.4 (#17), Llama 3.2 90B: —

BenchmarkGemini 3.8 FlashLlama 3.2 90B
DeepSWE73.8%—
FrontierCode41.2%—
CursorBench39.6%—
LMArena WebDev1581—
FrontierSWE19.6%—
SciCode56.6%—
LMArena Coding1512—
ALE-Bench1,270—

Agentic & Tool Use Gemini 3.8 Flash leads

Gemini 3.8 Flash: 40.3 (#22), Llama 3.2 90B: 29.7 (#73)

BenchmarkGemini 3.8 FlashLlama 3.2 90B
APEX-Agents64.3%—
BALROG—27.3%
GDP.pdf23.4%—
Vending-Bench 25,094—

Reasoning Gemini 3.8 Flash leads

Gemini 3.8 Flash: 64.7 (#13), Llama 3.2 90B: 20.9 (#207)

BenchmarkGemini 3.8 FlashLlama 3.2 90B
Epoch Capabilities Index157.13125.5
NYT Connections (extended)97.4%—
CritPt18.3%—
Chess Puzzles61%—
EnigmaEval—0.4%
LMArena Hard Prompts1506—
Mystery Game Puzzles47%—
DTBench95.7%—
LMCA52.9%—
Surface Evolver Bench76.9%—

Math Gemini 3.8 Flash leads

Gemini 3.8 Flash: 65.2 (#22), Llama 3.2 90B: 10.4 (#302)

BenchmarkGemini 3.8 FlashLlama 3.2 90B
OTIS Mock AIME 2024-202598.9%2.6%
FrontierMath (Tiers 1-3)68.4%—
FrontierMath Tier 422%—
ProofBench48%—
LMArena Math1528—
MATH Level 5—39.4%

Knowledge Gemini 3.8 Flash leads

Gemini 3.8 Flash: 74.9 (#2), Llama 3.2 90B: 21.7 (#269)

BenchmarkGemini 3.8 FlashLlama 3.2 90B
GPQA Diamond95.4%41%
Humanity's Last Exam44.5%—
SimpleQA Verified69.7%—
LMArena Expert1529—
MMLU—80.3%

Multimodal Gemini 3.8 Flash leads

Gemini 3.8 Flash: 40.9 (#33), Llama 3.2 90B: 24.9 (#119)

BenchmarkGemini 3.8 FlashLlama 3.2 90B
LMArena Vision13121000
GeoBench—52%
Blueprint-Bench 238.6%—
Furniture Assembly31.7%—

Multilingual Not comparable

Gemini 3.8 Flash: 57.9 (#5), Llama 3.2 90B: —

BenchmarkGemini 3.8 FlashLlama 3.2 90B
LMArena Non-English1486—
LMArena Chinese1547—
LMArena French1502—
LMArena German1470—
LMArena Japanese1505—
LMArena Korean1479—
LMArena Russian1507—
LMArena Spanish1492—

Instruction Following Not comparable

Gemini 3.8 Flash: 78.2 (#11), Llama 3.2 90B: —

BenchmarkGemini 3.8 FlashLlama 3.2 90B
LMArena Instruction Following1489—

Long Context Not comparable

Gemini 3.8 Flash: 46.2 (#23), Llama 3.2 90B: —

BenchmarkGemini 3.8 FlashLlama 3.2 90B
LMArena Longer Query1506—

Writing & Preference Not comparable

Gemini 3.8 Flash: 72.1 (#16), Llama 3.2 90B: —

BenchmarkGemini 3.8 FlashLlama 3.2 90B
LMArena Text1494—
LMArena Creative Writing1485—
EQ-Bench Creative Writing1748—
LMArena Multi-Turn1503—

Frequently asked questions

Is Gemini 3.8 Flash better than Llama 3.2 90B?

Gemini 3.8 Flash is the stronger model overall, scoring 59.5 to 27.1 on the Noometry Index.

How many benchmarks do Gemini 3.8 Flash and Llama 3.2 90B share?

4 benchmarks have published results for both models. Gemini 3.8 Flash has 46 scored results on Noometry and Llama 3.2 90B has 9.

Related comparisons

Go deeper