Noometry

Model comparison

GPT-5.4 nano vs Tulu 3 (Tülu 3) 70B

GPT-5.4 nano is the stronger model overall, scoring 41.9 to 33.0 on the Noometry Index.

Last verified . 13 shared benchmarks.

GPT-5.4 nano OpenAI

41.9

Rank #125 Confirmed

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

33.0

Rank #251 Confirmed

Summary

  • They share 13 benchmarks with published results for both. GPT-5.4 nano scores higher in 7 categories and Tulu 3 (Tülu 3) 70B in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.4 nano leads 40.9 to 14.2.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 87.8% for GPT-5.4 nano 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

GPT-5.4 nanoTulu 3 (Tülu 3) 70B
ProviderOpenAIAllen Institute for AI (Ai2)
Noometry Index41.933.0
Released2026-03-172024-11-21
WeightsProprietaryOpen
Context window400K—
Max output128K—
Input $ / M tokens$0.20—
Output $ / M tokens$1.25—
Results tracked4014

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

Category by category

Coding GPT-5.4 nano leads

GPT-5.4 nano: 43.6 (#84), Tulu 3 (Tülu 3) 70B: 36.0 (#214)

BenchmarkGPT-5.4 nanoTulu 3 (Tülu 3) 70B
LMArena Coding14051235
SciCode46.9%—
WeirdML49.2%—
ALE-Bench1,005—

Reasoning Too close to call

GPT-5.4 nano: 23.7 (#173), Tulu 3 (Tülu 3) 70B: 23.9 (#169)

BenchmarkGPT-5.4 nanoTulu 3 (Tülu 3) 70B
LMArena Hard Prompts13811220
ARC-AGI-25.7%—
Kagi LLM Benchmark39.7%—
ARC-AGI-151.5%—
CritPt9.3%—
Chess Puzzles30%—
Mystery Game Puzzles9%—
DTBench80.3%—
LMCA36.9%—
Epoch Capabilities Index145.81—
ForecastBench57.3—

Math GPT-5.4 nano leads

GPT-5.4 nano: 40.9 (#88), Tulu 3 (Tülu 3) 70B: 14.2 (#303)

BenchmarkGPT-5.4 nanoTulu 3 (Tülu 3) 70B
OTIS Mock AIME 2024-202587.8%4.4%
LMArena Math14061242
FrontierMath (Tiers 1-3)44.9%—
FrontierMath Tier 412.2%—
ProofBench5%—
MATH Level 5—42.7%
FrontierMath (Feb 2025 set)25.9%—
FrontierMath Tier 4 (v1)6.3%—

Knowledge GPT-5.4 nano leads

GPT-5.4 nano: 41.9 (#103), Tulu 3 (Tülu 3) 70B: 25.0 (#264)

BenchmarkGPT-5.4 nanoTulu 3 (Tülu 3) 70B
GPQA Diamond78.5%46.3%
SimpleQA Verified11.7%—
Vectara Hallucination Rate3.1%—
LMArena Expert1396—

Multimodal Not comparable

GPT-5.4 nano: 36.7 (#78), Tulu 3 (Tülu 3) 70B: —

BenchmarkGPT-5.4 nanoTulu 3 (Tülu 3) 70B
LMArena Vision1196—

Multilingual GPT-5.4 nano leads

GPT-5.4 nano: 48.6 (#140), Tulu 3 (Tülu 3) 70B: 39.9 (#222)

BenchmarkGPT-5.4 nanoTulu 3 (Tülu 3) 70B
LMArena Non-English13591236
LMArena Chinese13921249
LMArena Russian13631246
LMArena French1396—
LMArena German1367—
LMArena Japanese1343—
LMArena Korean1320—
LMArena Spanish1371—

Instruction Following GPT-5.4 nano leads

GPT-5.4 nano: 71.9 (#144), Tulu 3 (Tülu 3) 70B: 64.8 (#227)

BenchmarkGPT-5.4 nanoTulu 3 (Tülu 3) 70B
LMArena Instruction Following13621233

Long Context GPT-5.4 nano leads

GPT-5.4 nano: 41.6 (#137), Tulu 3 (Tülu 3) 70B: 37.1 (#222)

BenchmarkGPT-5.4 nanoTulu 3 (Tülu 3) 70B
LMArena Longer Query13661224

Writing & Preference GPT-5.4 nano leads

GPT-5.4 nano: 55.7 (#142), Tulu 3 (Tülu 3) 70B: 45.6 (#223)

BenchmarkGPT-5.4 nanoTulu 3 (Tülu 3) 70B
LMArena Text13721256
LMArena Creative Writing13141231
LMArena Multi-Turn13821252

Frequently asked questions

Is GPT-5.4 nano better than Tulu 3 (Tülu 3) 70B?

GPT-5.4 nano is the stronger model overall, scoring 41.9 to 33.0 on the Noometry Index.

Is GPT-5.4 nano or Tulu 3 (Tülu 3) 70B better for coding?

GPT-5.4 nano scores higher on coding benchmarks: 43.6 versus 36.0 in the Noometry coding category.

How many benchmarks do GPT-5.4 nano and Tulu 3 (Tülu 3) 70B share?

13 benchmarks have published results for both models. GPT-5.4 nano has 40 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.

Related comparisons

Go deeper