Noometry

Model comparison

Grok 4.20 Multi-Agent vs Tulu 3 (Tülu 3) 70B

Grok 4.20 Multi-Agent is the stronger model overall, scoring 45.5 to 32.6 on the Noometry Index.

Last verified . 11 shared benchmarks.

Grok 4.20 Multi-Agent xAI

45.5

Rank #62 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. Grok 4.20 Multi-Agent 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 Grok 4.20 Multi-Agent leads 36.6 to 13.3.
  • Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.

Side by side

Grok 4.20 Multi-AgentTulu 3 (Tülu 3) 70B
ProviderxAIAllen Institute for AI (Ai2)
Noometry Index45.532.6
Released2026-03-092024-11-21
WeightsProprietaryOpen
Context window1M—
Max output30K—
Input $ / M tokens$1.25—
Output $ / M tokens$2.50—
Results tracked2014

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

Category by category

Coding Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 42.4 (#91), Tulu 3 (Tülu 3) 70B: 35.4 (#211)

BenchmarkGrok 4.20 Multi-AgentTulu 3 (Tülu 3) 70B
LMArena Coding14581236

Agentic & Tool Use Not comparable

Grok 4.20 Multi-Agent: —, Tulu 3 (Tülu 3) 70B: —

BenchmarkGrok 4.20 Multi-AgentTulu 3 (Tülu 3) 70B
LMArena Search1204—

Reasoning Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 42.4 (#44), Tulu 3 (Tülu 3) 70B: 22.9 (#172)

BenchmarkGrok 4.20 Multi-AgentTulu 3 (Tülu 3) 70B
LMArena Hard Prompts14481220
NYT Connections (extended)89.6%—

Math Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 36.6 (#106), Tulu 3 (Tülu 3) 70B: 13.3 (#297)

BenchmarkGrok 4.20 Multi-AgentTulu 3 (Tülu 3) 70B
LMArena Math14411242
OTIS Mock AIME 2024-2025—4.4%
MATH Level 5—42.7%

Knowledge Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 39.7 (#116), Tulu 3 (Tülu 3) 70B: 25.1 (#257)

BenchmarkGrok 4.20 Multi-AgentTulu 3 (Tülu 3) 70B
GPQA Diamond—46.3%
LMArena Expert1445—

Multimodal Not comparable

Grok 4.20 Multi-Agent: 39.8 (#44), Tulu 3 (Tülu 3) 70B: —

BenchmarkGrok 4.20 Multi-AgentTulu 3 (Tülu 3) 70B
LMArena Vision1259—

Multilingual Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 54.6 (#40), Tulu 3 (Tülu 3) 70B: 40.1 (#217)

BenchmarkGrok 4.20 Multi-AgentTulu 3 (Tülu 3) 70B
LMArena Non-English14401236
LMArena Chinese14751249
LMArena Russian14571246
LMArena French1467—
LMArena German1456—
LMArena Japanese1405—
LMArena Korean1416—
LMArena Spanish1447—

Instruction Following Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 75.0 (#80), Tulu 3 (Tülu 3) 70B: 65.0 (#222)

BenchmarkGrok 4.20 Multi-AgentTulu 3 (Tülu 3) 70B
LMArena Instruction Following14201233

Long Context Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 43.7 (#84), Tulu 3 (Tülu 3) 70B: 37.1 (#217)

BenchmarkGrok 4.20 Multi-AgentTulu 3 (Tülu 3) 70B
LMArena Longer Query14301224

Writing & Preference Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 64.1 (#57), Tulu 3 (Tülu 3) 70B: 45.8 (#218)

BenchmarkGrok 4.20 Multi-AgentTulu 3 (Tülu 3) 70B
LMArena Text14501256
LMArena Creative Writing14351231
LMArena Multi-Turn14511252

Frequently asked questions

Is Grok 4.20 Multi-Agent better than Tulu 3 (Tülu 3) 70B?

Grok 4.20 Multi-Agent is the stronger model overall, scoring 45.5 to 32.6 on the Noometry Index.

Is Grok 4.20 Multi-Agent or Tulu 3 (Tülu 3) 70B better for coding?

Grok 4.20 Multi-Agent scores higher on coding benchmarks: 42.4 versus 35.4 in the Noometry coding category.

How many benchmarks do Grok 4.20 Multi-Agent and Tulu 3 (Tülu 3) 70B share?

11 benchmarks have published results for both models. Grok 4.20 Multi-Agent has 20 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.

Related comparisons

Go deeper