Noometry

Model comparison

o1 vs Tulu 3 (Tülu 3) 70B

o1 is the stronger model overall, scoring 40.9 to 33.0 on the Noometry Index.

Last verified . 14 shared benchmarks.

o1 OpenAI

40.9

Rank #143 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. o1 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 o1 leads 36.1 to 14.2.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 73.3% for o1 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

o1Tulu 3 (Tülu 3) 70B
ProviderOpenAIAllen Institute for AI (Ai2)
Noometry Index40.933.0
Released2024-09-122024-11-21
WeightsProprietaryOpen
Context window200K—
Max output100K—
Input $ / M tokens$15—
Output $ / M tokens$60—
Results tracked5214

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

Category by category

Coding o1 leads

o1: 46.1 (#70), Tulu 3 (Tülu 3) 70B: 36.0 (#214)

Benchmarko1Tulu 3 (Tülu 3) 70B
LMArena Coding13671235
Aider Polyglot61.7%—
WeirdML47.6%—
LiveBench Coding69.7%—
CadEval56%—
HumanEval+89%—
MBPP+80.2%—

Agentic & Tool Use Not comparable

o1: 24.6 (#117), Tulu 3 (Tülu 3) 70B: —

Benchmarko1Tulu 3 (Tülu 3) 70B
Cybench10%—
METR Time Horizons51.1%—

Reasoning o1 leads

o1: 27.9 (#111), Tulu 3 (Tülu 3) 70B: 23.9 (#169)

Benchmarko1Tulu 3 (Tülu 3) 70B
LMArena Hard Prompts13711220
SimpleBench41.7%—
ARC-AGI-130.7%—
Chess Puzzles15%—
EnigmaEval5.7%—
LiveBench Reasoning91.6%—
DTBench74.7%—
LiveBench Data Analysis65.5%—
LMCA22.3%—
Epoch Capabilities Index141.91—
LiveBench75.7%—

Math o1 leads

o1: 36.1 (#175), Tulu 3 (Tülu 3) 70B: 14.2 (#303)

Benchmarko1Tulu 3 (Tülu 3) 70B
OTIS Mock AIME 2024-202573.3%4.4%
LMArena Math13881242
MATH Level 594.7%42.7%
FrontierMath (Tiers 1-3)14.7%—
LiveBench Math80.3%—
FrontierMath (Feb 2025 set)9.3%—

Knowledge o1 leads

o1: 41.5 (#110), Tulu 3 (Tülu 3) 70B: 25.0 (#264)

Benchmarko1Tulu 3 (Tülu 3) 70B
GPQA Diamond76.8%46.3%
Humanity's Last Exam8%—
SimpleQA Verified41.1%—
Confabulations11.7%—
LMArena Expert1361—

Multimodal Not comparable

o1: 34.2 (#93), Tulu 3 (Tülu 3) 70B: —

Benchmarko1Tulu 3 (Tülu 3) 70B
LMArena Vision1168—
GeoBench80%—
VPCT37%—
SpatialViz-Bench41.4%—

Multilingual o1 leads

o1: 48.6 (#142), Tulu 3 (Tülu 3) 70B: 39.9 (#222)

Benchmarko1Tulu 3 (Tülu 3) 70B
LMArena Non-English13581236
LMArena Chinese13941249
LMArena Russian13561246
LMArena French1344—
LMArena German1337—
LMArena Japanese1346—
LMArena Korean1396—
LMArena Spanish1345—

Instruction Following o1 leads

o1: 74.8 (#86), Tulu 3 (Tülu 3) 70B: 64.8 (#227)

Benchmarko1Tulu 3 (Tülu 3) 70B
LMArena Instruction Following13671233
LiveBench Instruction Following81.5%—

Long Context o1 leads

o1: 50.3 (#9), Tulu 3 (Tülu 3) 70B: 37.1 (#222)

Benchmarko1Tulu 3 (Tülu 3) 70B
LMArena Longer Query13781224
Fiction.LiveBench83.3%—

Writing & Preference o1 leads

o1: 55.6 (#144), Tulu 3 (Tülu 3) 70B: 45.6 (#223)

Benchmarko1Tulu 3 (Tülu 3) 70B
LMArena Text13661256
LMArena Creative Writing13481231
LMArena Multi-Turn13691252
Short-Story Creative Writing70.2%—
LiveBench Language65.4%—

Frequently asked questions

Is o1 better than Tulu 3 (Tülu 3) 70B?

o1 is the stronger model overall, scoring 40.9 to 33.0 on the Noometry Index.

Is o1 or Tulu 3 (Tülu 3) 70B better for coding?

o1 scores higher on coding benchmarks: 46.1 versus 36.0 in the Noometry coding category.

How many benchmarks do o1 and Tulu 3 (Tülu 3) 70B share?

14 benchmarks have published results for both models. o1 has 52 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.

Related comparisons

Go deeper