Noometry

Model comparison

Grok 3 vs Tulu 3 (Tülu 3) 70B

Grok 3 is the stronger model overall, scoring 39.9 to 33.0 on the Noometry Index.

Last verified . 14 shared benchmarks.

Grok 3 xAI

39.9

Rank #157 Confirmed

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

33.0

Rank #251 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Grok 3 scores higher in 7 categories and Tulu 3 (Tülu 3) 70B in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok 3 leads 38.0 to 14.2.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 55.6% for Grok 3 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

Grok 3Tulu 3 (Tülu 3) 70B
ProviderxAIAllen Institute for AI (Ai2)
Noometry Index39.933.0
Released2025-04-092024-11-21
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4014

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

Category by category

Coding Grok 3 leads

Grok 3: 41.9 (#115), Tulu 3 (Tülu 3) 70B: 36.0 (#214)

BenchmarkGrok 3Tulu 3 (Tülu 3) 70B
LMArena Coding14321235
Aider Polyglot53.3%—
WeirdML37.2%—

Agentic & Tool Use Not comparable

Grok 3: 30.5 (#76), Tulu 3 (Tülu 3) 70B: —

BenchmarkGrok 3Tulu 3 (Tülu 3) 70B
BALROG29.5%—

Reasoning Tulu 3 (Tülu 3) 70B leads

Grok 3: 13.7 (#333), Tulu 3 (Tülu 3) 70B: 23.9 (#169)

BenchmarkGrok 3Tulu 3 (Tülu 3) 70B
LMArena Hard Prompts14341220
ARC-AGI-20%—
SimpleBench36.1%—
Kagi LLM Benchmark61.3%—
ARC-AGI-15.5%—
Epoch Capabilities Index138.33—

Math Grok 3 leads

Grok 3: 38.0 (#145), Tulu 3 (Tülu 3) 70B: 14.2 (#303)

BenchmarkGrok 3Tulu 3 (Tülu 3) 70B
OTIS Mock AIME 2024-202555.6%4.4%
LMArena Math13911242
MATH Level 588.7%42.7%
Omni-MATH46.4%—
FrontierMath (Feb 2025 set)3.8%—
FrontierMath Tier 4 (v1)0%—

Knowledge Grok 3 leads

Grok 3: 46.2 (#82), Tulu 3 (Tülu 3) 70B: 25.0 (#264)

BenchmarkGrok 3Tulu 3 (Tülu 3) 70B
GPQA Diamond75.8%46.3%
MMLU-Pro78.8%—
Confabulations14.2%—
Vectara Hallucination Rate5.8%—
GPQA (HELM)65%—
LMArena Expert1421—

Multilingual Grok 3 leads

Grok 3: 52.3 (#87), Tulu 3 (Tülu 3) 70B: 39.9 (#222)

BenchmarkGrok 3Tulu 3 (Tülu 3) 70B
LMArena Non-English14101236
LMArena Chinese14481249
LMArena Russian14161246
LMArena French1460—
LMArena German1431—
LMArena Japanese1387—
LMArena Korean1373—
LMArena Spanish1417—

Instruction Following Grok 3 leads

Grok 3: 75.0 (#73), Tulu 3 (Tülu 3) 70B: 64.8 (#227)

BenchmarkGrok 3Tulu 3 (Tülu 3) 70B
LMArena Instruction Following14091233
IFEval88.4%—

Long Context Grok 3 leads

Grok 3: 38.7 (#192), Tulu 3 (Tülu 3) 70B: 37.1 (#222)

BenchmarkGrok 3Tulu 3 (Tülu 3) 70B
LMArena Longer Query14391224
Fiction.LiveBench58.3%—

Writing & Preference Grok 3 leads

Grok 3: 55.8 (#141), Tulu 3 (Tülu 3) 70B: 45.6 (#223)

BenchmarkGrok 3Tulu 3 (Tülu 3) 70B
LMArena Text14261256
LMArena Creative Writing14141231
LMArena Multi-Turn14251252
Short-Story Creative Writing76.4%—
EQ-Bench Creative Writing1186—
WildBench84.9%—

Frequently asked questions

Is Grok 3 better than Tulu 3 (Tülu 3) 70B?

Grok 3 is the stronger model overall, scoring 39.9 to 33.0 on the Noometry Index.

Is Grok 3 or Tulu 3 (Tülu 3) 70B better for coding?

Grok 3 scores higher on coding benchmarks: 41.9 versus 36.0 in the Noometry coding category.

How many benchmarks do Grok 3 and Tulu 3 (Tülu 3) 70B share?

14 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.

Related comparisons

Go deeper