Noometry

Model comparison

o1-mini vs Phi 3 Small 8k Instruct

o1-mini is the stronger model overall, scoring 34.0 to 29.3 on the Noometry Index.

Last verified . 24 shared benchmarks.

o1-mini OpenAI

34.0

Rank #235 Confirmed

Phi 3 Small 8k Instruct Microsoft

29.3

Rank #314 Confirmed

Summary

  • They share 24 benchmarks with published results for both. o1-mini scores higher in 7 categories and Phi 3 Small 8k Instruct in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where o1-mini leads 48.4 to 31.1.
  • The biggest single-benchmark swing is LiveBench Reasoning: 72.3% for o1-mini and 15.9% for Phi 3 Small 8k Instruct.
  • Phi 3 Small 8k Instruct has downloadable open weights; the other is API-only.

Side by side

o1-miniPhi 3 Small 8k Instruct
ProviderOpenAIMicrosoft
Noometry Index34.029.3
Released2024-09-122024-04-23
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3932

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

Category by category

Coding o1-mini leads

o1-mini: 35.5 (#224), Phi 3 Small 8k Instruct: 27.9 (#318)

Benchmarko1-miniPhi 3 Small 8k Instruct
LiveBench Coding48%20.3%
LMArena Coding13621101
Aider Polyglot32.9%—
WeirdML36.3%—
HumanEval+89%—
MBPP+78.8%—

Agentic & Tool Use Not comparable

o1-mini: 24.6 (#118), Phi 3 Small 8k Instruct: —

Benchmarko1-miniPhi 3 Small 8k Instruct
Cybench10%—

Reasoning Phi 3 Small 8k Instruct leads

o1-mini: 8.8 (#346), Phi 3 Small 8k Instruct: 14.8 (#323)

Benchmarko1-miniPhi 3 Small 8k Instruct
LiveBench Reasoning72.3%15.9%
LMArena Hard Prompts13331100
LiveBench Data Analysis57.9%30.3%
LiveBench57.8%24%
ARC-AGI-20.8%—
SimpleBench18.1%—
ARC-AGI-114%—
Adversarial NLI—58.1%
BIG-Bench Hard—79.1%
Epoch Capabilities Index135.82—
HellaSwag—77%
WinoGrande—81.5%

Math o1-mini leads

o1-mini: 35.4 (#186), Phi 3 Small 8k Instruct: 27.6 (#248)

Benchmarko1-miniPhi 3 Small 8k Instruct
LiveBench Math62%17.6%
LMArena Math13581151
OTIS Mock AIME 2024-202546.9%—
MATH Level 589.2%—
FrontierMath (Feb 2025 set)1.7%—

Knowledge o1-mini leads

o1-mini: 34.9 (#192), Phi 3 Small 8k Instruct: 29.1 (#240)

Benchmarko1-miniPhi 3 Small 8k Instruct
LMArena Expert13161067
GPQA Diamond62.4%—
Confabulations18.6%—
ARC (AI2) Challenge—90.7%
MMLU—75.7%
OpenBookQA—88%
TriviaQA—58.1%

Multilingual o1-mini leads

o1-mini: 43.6 (#182), Phi 3 Small 8k Instruct: 28.5 (#272)

Benchmarko1-miniPhi 3 Small 8k Instruct
LMArena Non-English12891058
LMArena Chinese13141061
LMArena French12931135
LMArena German12781080
LMArena Japanese1245966
LMArena Korean1223894
LMArena Russian12831111
LMArena Spanish13031111

Instruction Following o1-mini leads

o1-mini: 66.7 (#206), Phi 3 Small 8k Instruct: 51.9 (#292)

Benchmarko1-miniPhi 3 Small 8k Instruct
LiveBench Instruction Following65.4%47.2%
LMArena Instruction Following13041087

Long Context o1-mini leads

o1-mini: 40.1 (#161), Phi 3 Small 8k Instruct: 33.0 (#267)

Benchmarko1-miniPhi 3 Small 8k Instruct
LMArena Longer Query13201088

Writing & Preference o1-mini leads

o1-mini: 48.4 (#202), Phi 3 Small 8k Instruct: 31.1 (#284)

Benchmarko1-miniPhi 3 Small 8k Instruct
LMArena Text13171110
LMArena Creative Writing12441083
LMArena Multi-Turn13141068
LiveBench Language40.9%12.9%
Short-Story Creative Writing64.9%—

Frequently asked questions

Is o1-mini better than Phi 3 Small 8k Instruct?

o1-mini is the stronger model overall, scoring 34.0 to 29.3 on the Noometry Index.

Is o1-mini or Phi 3 Small 8k Instruct better for coding?

o1-mini scores higher on coding benchmarks: 35.5 versus 27.9 in the Noometry coding category.

How many benchmarks do o1-mini and Phi 3 Small 8k Instruct share?

24 benchmarks have published results for both models. o1-mini has 39 scored results on Noometry and Phi 3 Small 8k Instruct has 32.

Related comparisons

Go deeper