Model comparison

Gemini 3.8 Flash vs Tulu 3 (Tülu 3) 70B

Gemini 3.8 Flash is the stronger model overall, scoring 59.5 to 32.6 on the Noometry Index.

Last verified . 13 shared benchmarks.

Gemini 3.8 Flash Google

59.5

Rank #13 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 8 categories and Tulu 3 (Tülu 3) 70B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Gemini 3.8 Flash leads 65.2 to 13.3.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.9% for Gemini 3.8 Flash and 4.4% for Tulu 3 (Tülu 3) 70B.
  • Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.

Side by side

Gemini 3.8 Flash and Tulu 3 (Tülu 3) 70B specifications
Gemini 3.8 FlashTulu 3 (Tülu 3) 70B
ProviderGoogleAllen Institute for AI (Ai2)
Noometry Index59.532.6
Released2026-09-022024-11-21
WeightsProprietaryOpen
Context window1.05M—
Max output66K—
Input $ / M tokens$0.75—
Output $ / M tokens$3.75—
Results tracked4614

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

Category by category

Coding Gemini 3.8 Flash leads

Gemini 3.8 Flash: 56.4 (#17), Tulu 3 (Tülu 3) 70B: 35.4 (#211)

Coding benchmarks
BenchmarkGemini 3.8 FlashTulu 3 (Tülu 3) 70B
LMArena Coding15121236
DeepSWE73.8%—
FrontierCode41.2%—
CursorBench39.6%—
LMArena WebDev1581—
FrontierSWE19.6%—
SciCode56.6%—
ALE-Bench1,270—

Agentic & Tool Use Not comparable

Gemini 3.8 Flash: 40.3 (#22), Tulu 3 (Tülu 3) 70B: —

Agentic & Tool Use benchmarks
BenchmarkGemini 3.8 FlashTulu 3 (Tülu 3) 70B
APEX-Agents64.3%—
GDP.pdf23.4%—
Vending-Bench 25,094—

Reasoning Gemini 3.8 Flash leads

Gemini 3.8 Flash: 64.7 (#13), Tulu 3 (Tülu 3) 70B: 22.9 (#172)

Reasoning benchmarks
BenchmarkGemini 3.8 FlashTulu 3 (Tülu 3) 70B
LMArena Hard Prompts15061220
NYT Connections (extended)97.4%—
CritPt18.3%—
Chess Puzzles61%—
Mystery Game Puzzles47%—
DTBench95.7%—
LMCA52.9%—
Surface Evolver Bench76.9%—
Epoch Capabilities Index157.13—

Math Gemini 3.8 Flash leads

Gemini 3.8 Flash: 65.2 (#22), Tulu 3 (Tülu 3) 70B: 13.3 (#297)

Math benchmarks
BenchmarkGemini 3.8 FlashTulu 3 (Tülu 3) 70B
OTIS Mock AIME 2024-202598.9%4.4%
LMArena Math15281242
FrontierMath (Tiers 1-3)68.4%—
FrontierMath Tier 422%—
ProofBench48%—
MATH Level 5—42.7%

Knowledge Gemini 3.8 Flash leads

Gemini 3.8 Flash: 74.9 (#2), Tulu 3 (Tülu 3) 70B: 25.1 (#257)

Knowledge benchmarks
BenchmarkGemini 3.8 FlashTulu 3 (Tülu 3) 70B
GPQA Diamond95.4%46.3%
Humanity's Last Exam44.5%—
SimpleQA Verified69.7%—
LMArena Expert1529—

Multimodal Not comparable

Gemini 3.8 Flash: 40.9 (#33), Tulu 3 (Tülu 3) 70B: —

Multimodal benchmarks
BenchmarkGemini 3.8 FlashTulu 3 (Tülu 3) 70B
LMArena Vision1312—
Blueprint-Bench 238.6%—
Furniture Assembly31.7%—

Multilingual Gemini 3.8 Flash leads

Gemini 3.8 Flash: 57.9 (#5), Tulu 3 (Tülu 3) 70B: 40.1 (#217)

Multilingual benchmarks
BenchmarkGemini 3.8 FlashTulu 3 (Tülu 3) 70B
LMArena Non-English14861236
LMArena Chinese15471249
LMArena Russian15071246
LMArena French1502—
LMArena German1470—
LMArena Japanese1505—
LMArena Korean1479—
LMArena Spanish1492—

Instruction Following Gemini 3.8 Flash leads

Gemini 3.8 Flash: 78.2 (#11), Tulu 3 (Tülu 3) 70B: 65.0 (#222)

Instruction Following benchmarks
BenchmarkGemini 3.8 FlashTulu 3 (Tülu 3) 70B
LMArena Instruction Following14891233

Long Context Gemini 3.8 Flash leads

Gemini 3.8 Flash: 46.2 (#23), Tulu 3 (Tülu 3) 70B: 37.1 (#217)

Long Context benchmarks
BenchmarkGemini 3.8 FlashTulu 3 (Tülu 3) 70B
LMArena Longer Query15061224

Writing & Preference Gemini 3.8 Flash leads

Gemini 3.8 Flash: 72.1 (#16), Tulu 3 (Tülu 3) 70B: 45.8 (#218)

Writing & Preference benchmarks
BenchmarkGemini 3.8 FlashTulu 3 (Tülu 3) 70B
LMArena Text14941256
LMArena Creative Writing14851231
LMArena Multi-Turn15031252
EQ-Bench Creative Writing1748—

Frequently asked questions

Is Gemini 3.8 Flash better than Tulu 3 (Tülu 3) 70B?

Gemini 3.8 Flash is the stronger model overall, scoring 59.5 to 32.6 on the Noometry Index.

Is Gemini 3.8 Flash or Tulu 3 (Tülu 3) 70B better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 56.4 versus 35.4 in the Noometry coding category.

How many benchmarks do Gemini 3.8 Flash and Tulu 3 (Tülu 3) 70B share?

13 benchmarks have published results for both models. Gemini 3.8 Flash has 46 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.

Related comparisons

Go deeper