Noometry

Model comparison

Gemini 3.1 Flash Lite vs Olmo 3 32b Think

Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.8 to 38.7 on the Noometry Index.

Last verified . 14 shared benchmarks.

Gemini 3.1 Flash Lite Google

40.8

Rank #144 Confirmed

Olmo 3 32b Think Allen Institute for AI (Ai2)

38.7

Rank #183 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 6 categories and Olmo 3 32b Think in 2 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Gemini 3.1 Flash Lite leads 60.9 to 49.1.
  • Olmo 3 32b Think has downloadable open weights; the other is API-only.

Side by side

Gemini 3.1 Flash LiteOlmo 3 32b Think
ProviderGoogleAllen Institute for AI (Ai2)
Noometry Index40.838.7
Released2026-03-03—
WeightsProprietaryOpen
Context window1.05M—
Max output66K—
Input $ / M tokens$0.25—
Output $ / M tokens$1.50—
Results tracked3814

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

Category by category

Coding Too close to call

Gemini 3.1 Flash Lite: 37.8 (#188), Olmo 3 32b Think: 38.6 (#172)

BenchmarkGemini 3.1 Flash LiteOlmo 3 32b Think
LMArena Coding14001319
LMArena WebDev1256—
SciCode41.9%—
WeirdML52.2%—
ALE-Bench797.73—

Agentic & Tool Use Not comparable

Gemini 3.1 Flash Lite: 30.2 (#79), Olmo 3 32b Think: —

BenchmarkGemini 3.1 Flash LiteOlmo 3 32b Think
DeepResearch Bench37.3%—

Reasoning Olmo 3 32b Think leads

Gemini 3.1 Flash Lite: 22.9 (#186), Olmo 3 32b Think: 25.9 (#140)

BenchmarkGemini 3.1 Flash LiteOlmo 3 32b Think
LMArena Hard Prompts14071302
Kagi LLM Benchmark67.2%—
NYT Connections (extended)8.2%—
CritPt1.1%—
Chess Puzzles25%—
EnigmaEval3%—
Thematic Generalization63.3%—
DTBench76.8%—
LMCA35%—
Epoch Capabilities Index144.47—
ForecastBench54.4—

Math Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 40.7 (#90), Olmo 3 32b Think: 36.5 (#165)

BenchmarkGemini 3.1 Flash LiteOlmo 3 32b Think
LMArena Math14281316
FrontierMath (Tiers 1-3)27.7%—
OTIS Mock AIME 2024-202580%—

Knowledge Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 41.9 (#104), Olmo 3 32b Think: 35.0 (#190)

BenchmarkGemini 3.1 Flash LiteOlmo 3 32b Think
LMArena Expert13981273
GPQA Diamond81.8%—
Humanity's Last Exam8.6%—
Vectara Hallucination Rate8.2%—

Multimodal Not comparable

Gemini 3.1 Flash Lite: 39.4 (#60), Olmo 3 32b Think: —

BenchmarkGemini 3.1 Flash LiteOlmo 3 32b Think
LMArena Vision1240—

Multilingual Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 52.3 (#86), Olmo 3 32b Think: 41.2 (#210)

BenchmarkGemini 3.1 Flash LiteOlmo 3 32b Think
LMArena Non-English14111255
LMArena Chinese14611300
LMArena French14241291
LMArena German14291290
LMArena Russian14201254
LMArena Japanese1413—
LMArena Korean1392—
LMArena Spanish1421—

Instruction Following Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 72.7 (#131), Olmo 3 32b Think: 67.2 (#198)

BenchmarkGemini 3.1 Flash LiteOlmo 3 32b Think
LMArena Instruction Following13771275

Long Context Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 42.5 (#122), Olmo 3 32b Think: 39.4 (#182)

BenchmarkGemini 3.1 Flash LiteOlmo 3 32b Think
LMArena Longer Query13941296

Writing & Preference Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 60.9 (#94), Olmo 3 32b Think: 49.1 (#193)

BenchmarkGemini 3.1 Flash LiteOlmo 3 32b Think
LMArena Text14161300
LMArena Creative Writing14011256
LMArena Multi-Turn14171290

Frequently asked questions

Is Gemini 3.1 Flash Lite better than Olmo 3 32b Think?

Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.8 to 38.7 on the Noometry Index.

Is Gemini 3.1 Flash Lite or Olmo 3 32b Think better for coding?

They score almost the same on coding (37.8 vs 38.6); test both on your own repository before choosing.

How many benchmarks do Gemini 3.1 Flash Lite and Olmo 3 32b Think share?

14 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and Olmo 3 32b Think has 14.

Related comparisons

Go deeper