Noometry

Model comparison

o1-mini vs Tulu 3 (Tülu 3) 70B

o1-mini is the stronger model overall, scoring 34.0 to 33.0 on the Noometry Index.

Last verified . 14 shared benchmarks.

o1-mini OpenAI

34.0

Rank #235 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-mini scores higher in 6 categories and Tulu 3 (Tülu 3) 70B in 2 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where o1-mini leads 35.4 to 14.2.
  • The biggest single-benchmark swing is MATH Level 5: 89.2% for o1-mini 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

o1-miniTulu 3 (Tülu 3) 70B
ProviderOpenAIAllen Institute for AI (Ai2)
Noometry Index34.033.0
Released2024-09-122024-11-21
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3914

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

Category by category

Coding Too close to call

o1-mini: 35.5 (#224), Tulu 3 (Tülu 3) 70B: 36.0 (#214)

Benchmarko1-miniTulu 3 (Tülu 3) 70B
LMArena Coding13621235
Aider Polyglot32.9%—
WeirdML36.3%—
LiveBench Coding48%—
HumanEval+89%—
MBPP+78.8%—

Agentic & Tool Use Not comparable

o1-mini: 24.6 (#118), Tulu 3 (Tülu 3) 70B: —

Benchmarko1-miniTulu 3 (Tülu 3) 70B
Cybench10%—

Reasoning Tulu 3 (Tülu 3) 70B leads

o1-mini: 8.8 (#346), Tulu 3 (Tülu 3) 70B: 23.9 (#169)

Benchmarko1-miniTulu 3 (Tülu 3) 70B
LMArena Hard Prompts13331220
ARC-AGI-20.8%—
SimpleBench18.1%—
ARC-AGI-114%—
LiveBench Reasoning72.3%—
LiveBench Data Analysis57.9%—
Epoch Capabilities Index135.82—
LiveBench57.8%—

Math o1-mini leads

o1-mini: 35.4 (#186), Tulu 3 (Tülu 3) 70B: 14.2 (#303)

Benchmarko1-miniTulu 3 (Tülu 3) 70B
OTIS Mock AIME 2024-202546.9%4.4%
LMArena Math13581242
MATH Level 589.2%42.7%
LiveBench Math62%—
FrontierMath (Feb 2025 set)1.7%—

Knowledge o1-mini leads

o1-mini: 34.9 (#192), Tulu 3 (Tülu 3) 70B: 25.0 (#264)

Benchmarko1-miniTulu 3 (Tülu 3) 70B
GPQA Diamond62.4%46.3%
Confabulations18.6%—
LMArena Expert1316—

Multilingual o1-mini leads

o1-mini: 43.6 (#182), Tulu 3 (Tülu 3) 70B: 39.9 (#222)

Benchmarko1-miniTulu 3 (Tülu 3) 70B
LMArena Non-English12891236
LMArena Chinese13141249
LMArena Russian12831246
LMArena French1293—
LMArena German1278—
LMArena Japanese1245—
LMArena Korean1223—
LMArena Spanish1303—

Instruction Following o1-mini leads

o1-mini: 66.7 (#206), Tulu 3 (Tülu 3) 70B: 64.8 (#227)

Benchmarko1-miniTulu 3 (Tülu 3) 70B
LMArena Instruction Following13041233
LiveBench Instruction Following65.4%—

Long Context o1-mini leads

o1-mini: 40.1 (#161), Tulu 3 (Tülu 3) 70B: 37.1 (#222)

Benchmarko1-miniTulu 3 (Tülu 3) 70B
LMArena Longer Query13201224

Writing & Preference o1-mini leads

o1-mini: 48.4 (#202), Tulu 3 (Tülu 3) 70B: 45.6 (#223)

Benchmarko1-miniTulu 3 (Tülu 3) 70B
LMArena Text13171256
LMArena Creative Writing12441231
LMArena Multi-Turn13141252
Short-Story Creative Writing64.9%—
LiveBench Language40.9%—

Frequently asked questions

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

o1-mini is the stronger model overall, scoring 34.0 to 33.0 on the Noometry Index.

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

They score almost the same on coding (35.5 vs 36.0); test both on your own repository before choosing.

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

14 benchmarks have published results for both models. o1-mini has 39 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.

Related comparisons

Go deeper