Noometry

Model comparison

Gemini 2.5 Flash-Lite vs Tulu 3 (Tülu 3) 70B

Gemini 2.5 Flash-Lite is the stronger model overall, scoring 36.4 to 32.6 on the Noometry Index.

Last verified . 11 shared benchmarks.

Gemini 2.5 Flash-Lite Google

36.4

Rank #208 Confirmed

Tulu 3 (Tülu 3) 70B Allen Institute for AI (Ai2)

32.6

Rank #242 Confirmed

Summary

  • They share 11 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 6 categories and Tulu 3 (Tülu 3) 70B in 2 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Gemini 2.5 Flash-Lite leads 35.5 to 13.3.
  • Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.

Side by side

Gemini 2.5 Flash-LiteTulu 3 (Tülu 3) 70B
ProviderGoogleAllen Institute for AI (Ai2)
Noometry Index36.432.6
Released2025-06-172024-11-21
WeightsProprietaryOpen
Context window1.05M—
Max output66K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.40—
Results tracked3314

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

Category by category

Coding Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 38.0 (#167), Tulu 3 (Tülu 3) 70B: 35.4 (#211)

BenchmarkGemini 2.5 Flash-LiteTulu 3 (Tülu 3) 70B
LMArena Coding13731236
WeirdML35.2%—
ALE-Bench325.9—

Agentic & Tool Use Not comparable

Gemini 2.5 Flash-Lite: 27.8 (#89), Tulu 3 (Tülu 3) 70B: —

BenchmarkGemini 2.5 Flash-LiteTulu 3 (Tülu 3) 70B
Berkeley Function Calling Leaderboard36.9%—

Reasoning Tulu 3 (Tülu 3) 70B leads

Gemini 2.5 Flash-Lite: 21.5 (#196), Tulu 3 (Tülu 3) 70B: 22.9 (#172)

BenchmarkGemini 2.5 Flash-LiteTulu 3 (Tülu 3) 70B
LMArena Hard Prompts13771220
Kagi LLM Benchmark40.5%—
DTBench62.8%—
LMCA18.1%—
Epoch Capabilities Index133.93—

Math Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 35.5 (#144), Tulu 3 (Tülu 3) 70B: 13.3 (#297)

BenchmarkGemini 2.5 Flash-LiteTulu 3 (Tülu 3) 70B
LMArena Math13731242
OTIS Mock AIME 2024-2025—4.4%
Omni-MATH48%—
MATH Level 5—42.7%

Knowledge Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 32.1 (#206), Tulu 3 (Tülu 3) 70B: 25.1 (#257)

BenchmarkGemini 2.5 Flash-LiteTulu 3 (Tülu 3) 70B
GPQA Diamond—46.3%
MMLU-Pro53.7%—
Vectara Hallucination Rate3.3%—
GPQA (HELM)30.9%—
LMArena Expert1373—

Multimodal Not comparable

Gemini 2.5 Flash-Lite: 28.6 (#109), Tulu 3 (Tülu 3) 70B: —

BenchmarkGemini 2.5 Flash-LiteTulu 3 (Tülu 3) 70B
LMArena Vision1198—
VPCT30%—

Multilingual Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 49.5 (#129), Tulu 3 (Tülu 3) 70B: 40.1 (#217)

BenchmarkGemini 2.5 Flash-LiteTulu 3 (Tülu 3) 70B
LMArena Non-English13691236
LMArena Chinese14041249
LMArena Russian13731246
LMArena French1388—
LMArena German1390—
LMArena Japanese1359—
LMArena Korean1358—
LMArena Spanish1396—

Instruction Following Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 70.2 (#163), Tulu 3 (Tülu 3) 70B: 65.0 (#222)

BenchmarkGemini 2.5 Flash-LiteTulu 3 (Tülu 3) 70B
LMArena Instruction Following13661233
IFEval81%—

Long Context Tulu 3 (Tülu 3) 70B leads

Gemini 2.5 Flash-Lite: 33.3 (#257), Tulu 3 (Tülu 3) 70B: 37.1 (#217)

BenchmarkGemini 2.5 Flash-LiteTulu 3 (Tülu 3) 70B
LMArena Longer Query13731224
Fiction.LiveBench47.2%—

Writing & Preference Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 57.0 (#130), Tulu 3 (Tülu 3) 70B: 45.8 (#218)

BenchmarkGemini 2.5 Flash-LiteTulu 3 (Tülu 3) 70B
LMArena Text13791256
LMArena Creative Writing13661231
LMArena Multi-Turn13671252
WildBench81.8%—

Frequently asked questions

Is Gemini 2.5 Flash-Lite better than Tulu 3 (Tülu 3) 70B?

Gemini 2.5 Flash-Lite is the stronger model overall, scoring 36.4 to 32.6 on the Noometry Index.

Is Gemini 2.5 Flash-Lite or Tulu 3 (Tülu 3) 70B better for coding?

Gemini 2.5 Flash-Lite scores higher on coding benchmarks: 38.0 versus 35.4 in the Noometry coding category.

How many benchmarks do Gemini 2.5 Flash-Lite and Tulu 3 (Tülu 3) 70B share?

11 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.

Related comparisons

Go deeper