Noometry

Model comparison

GPT-4.1 vs Tulu 3 (Tülu 3) 70B

GPT-4.1 is the stronger model overall, scoring 35.7 to 32.6 on the Noometry Index.

Last verified . 14 shared benchmarks.

GPT-4.1 OpenAI

35.7

Rank #215 Confirmed

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

32.6

Rank #242 Confirmed

Summary

  • They share 14 benchmarks with published results for both. GPT-4.1 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 writing & preference, where GPT-4.1 leads 57.8 to 45.8.
  • The biggest single-benchmark swing is MATH Level 5: 83% for GPT-4.1 and 42.7% for Tulu 3 (Tülu 3) 70B.
  • Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.

Side by side

GPT-4.1Tulu 3 (Tülu 3) 70B
ProviderOpenAIAllen Institute for AI (Ai2)
Noometry Index35.732.6
Released2025-04-142024-11-21
WeightsProprietaryOpen
Context window1.05M—
Max output33K—
Input $ / M tokens$2—
Output $ / M tokens$8—
Results tracked5214

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

Category by category

Coding Tulu 3 (Tülu 3) 70B leads

GPT-4.1: 34.2 (#228), Tulu 3 (Tülu 3) 70B: 35.4 (#211)

BenchmarkGPT-4.1Tulu 3 (Tülu 3) 70B
LMArena Coding13911236
SWE-bench Verified48.5%—
SWE-bench Verified (bash only)39.6%—
Aider Polyglot52.4%—
WeirdML39%—
CadEval42%—
ALE-Bench558.1—

Agentic & Tool Use Not comparable

GPT-4.1: 34.4 (#40), Tulu 3 (Tülu 3) 70B: —

BenchmarkGPT-4.1Tulu 3 (Tülu 3) 70B
Berkeley Function Calling Leaderboard54%—

Reasoning Tulu 3 (Tülu 3) 70B leads

GPT-4.1: 11.7 (#334), Tulu 3 (Tülu 3) 70B: 22.9 (#172)

BenchmarkGPT-4.1Tulu 3 (Tülu 3) 70B
LMArena Hard Prompts13841220
ARC-AGI-20.4%—
SimpleBench27%—
Kagi LLM Benchmark52.3%—
ARC-AGI-15.5%—
Chess Puzzles6%—
EnigmaEval2.2%—
DTBench68.3%—
LMCA25.6%—
Epoch Capabilities Index136.79—
ForecastBench61.5—

Math GPT-4.1 leads

GPT-4.1: 21.4 (#269), Tulu 3 (Tülu 3) 70B: 13.3 (#297)

BenchmarkGPT-4.1Tulu 3 (Tülu 3) 70B
OTIS Mock AIME 2024-202538.3%4.4%
LMArena Math13691242
MATH Level 583%42.7%
FrontierMath (Tiers 1-3)6%—
Omni-MATH47.1%—
FrontierMath (Feb 2025 set)5.5%—
FrontierMath Tier 4 (v1)0%—

Knowledge GPT-4.1 leads

GPT-4.1: 37.0 (#152), Tulu 3 (Tülu 3) 70B: 25.1 (#257)

BenchmarkGPT-4.1Tulu 3 (Tülu 3) 70B
GPQA Diamond66.9%46.3%
Humanity's Last Exam5.4%—
SimpleQA Verified31.1%—
MMLU-Pro81.1%—
Vectara Hallucination Rate5.6%—
GPQA (HELM)65.9%—
LMArena Expert1364—

Multimodal Not comparable

GPT-4.1: 37.5 (#66), Tulu 3 (Tülu 3) 70B: —

BenchmarkGPT-4.1Tulu 3 (Tülu 3) 70B
LMArena Vision1210—
GeoBench72%—

Multilingual GPT-4.1 leads

GPT-4.1: 49.6 (#128), Tulu 3 (Tülu 3) 70B: 40.1 (#217)

BenchmarkGPT-4.1Tulu 3 (Tülu 3) 70B
LMArena Non-English13701236
LMArena Chinese13821249
LMArena Russian13771246
LMArena French1383—
LMArena German1380—
LMArena Japanese1320—
LMArena Korean1339—
LMArena Spanish1375—

Instruction Following GPT-4.1 leads

GPT-4.1: 71.5 (#148), Tulu 3 (Tülu 3) 70B: 65.0 (#222)

BenchmarkGPT-4.1Tulu 3 (Tülu 3) 70B
LMArena Instruction Following13671233
IFEval83.8%—

Long Context GPT-4.1 leads

GPT-4.1: 40.0 (#158), Tulu 3 (Tülu 3) 70B: 37.1 (#217)

BenchmarkGPT-4.1Tulu 3 (Tülu 3) 70B
LMArena Longer Query13851224
Fiction.LiveBench63.9%—

Writing & Preference GPT-4.1 leads

GPT-4.1: 57.8 (#120), Tulu 3 (Tülu 3) 70B: 45.8 (#218)

BenchmarkGPT-4.1Tulu 3 (Tülu 3) 70B
LMArena Text13831256
LMArena Creative Writing13631231
LMArena Multi-Turn13981252
EQ-Bench Creative Writing1420—
WildBench85.4%—

Frequently asked questions

Is GPT-4.1 better than Tulu 3 (Tülu 3) 70B?

GPT-4.1 is the stronger model overall, scoring 35.7 to 32.6 on the Noometry Index.

Is GPT-4.1 or Tulu 3 (Tülu 3) 70B better for coding?

Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 35.4 versus 34.2 in the Noometry coding category.

How many benchmarks do GPT-4.1 and Tulu 3 (Tülu 3) 70B share?

14 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.

Related comparisons

Go deeper