Model comparison

o1-mini vs Step 5 Preview

Step 5 Preview is the stronger model overall, scoring 47.9 to 34.0 on the Noometry Index.

Last verified . 13 shared benchmarks.

o1-mini OpenAI

34.0

Rank #235 Confirmed

Step 5 Preview StepFun

47.9

Rank #58 Confirmed

Summary

  • They share 13 benchmarks with published results for both. o1-mini scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 8.8.

Side by side

o1-mini and Step 5 Preview specifications
o1-miniStep 5 Preview
ProviderOpenAIStepFun
Noometry Index34.047.9
Released2024-09-122026-09-16
WeightsProprietaryProprietary
Context window—1.02M
Max output—66K
Input $ / M tokens—$1
Output $ / M tokens—$2.70
Results tracked3918

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

Category by category

Coding Step 5 Preview leads

o1-mini: 35.5 (#224), Step 5 Preview: 51.8 (#36)

Coding benchmarks
Benchmarko1-miniStep 5 Preview
LMArena Coding13621480
Aider Polyglot32.9%—
LMArena WebDev—1564
SciCode—58.9%
WeirdML36.3%—
LiveBench Coding48%—
HumanEval+89%—
MBPP+78.8%—

Agentic & Tool Use Not comparable

o1-mini: 24.6 (#118), Step 5 Preview: —

Agentic & Tool Use benchmarks
Benchmarko1-miniStep 5 Preview
Cybench10%—

Reasoning Step 5 Preview leads

o1-mini: 8.8 (#346), Step 5 Preview: 40.0 (#57)

Reasoning benchmarks
Benchmarko1-miniStep 5 Preview
LMArena Hard Prompts13331465
ARC-AGI-20.8%—
SimpleBench18.1%—
ARC-AGI-114%—
CritPt—20.9%
LiveBench Reasoning72.3%—
LiveBench Data Analysis57.9%—
Epoch Capabilities Index135.82—
LiveBench57.8%—

Math Step 5 Preview leads

o1-mini: 35.4 (#186), Step 5 Preview: 46.1 (#72)

Math benchmarks
Benchmarko1-miniStep 5 Preview
LMArena Math13581470
OTIS Mock AIME 2024-202546.9%—
ProofBench—42%
LiveBench Math62%—
MATH Level 589.2%—
FrontierMath (Feb 2025 set)1.7%—

Knowledge Step 5 Preview leads

o1-mini: 34.9 (#192), Step 5 Preview: 41.2 (#112)

Knowledge benchmarks
Benchmarko1-miniStep 5 Preview
LMArena Expert13161470
GPQA Diamond62.4%—
Confabulations18.6%—

Multimodal Not comparable

o1-mini: —, Step 5 Preview: 41.0 (#41)

Multimodal benchmarks
Benchmarko1-miniStep 5 Preview
LMArena Vision—1267

Multilingual Step 5 Preview leads

o1-mini: 43.6 (#182), Step 5 Preview: 53.8 (#54)

Multilingual benchmarks
Benchmarko1-miniStep 5 Preview
LMArena Non-English12891432
LMArena Chinese13141519
LMArena Russian12831436
LMArena Spanish13031439
LMArena French1293—
LMArena German1278—
LMArena Japanese1245—
LMArena Korean1223—

Instruction Following Step 5 Preview leads

o1-mini: 66.7 (#206), Step 5 Preview: 76.0 (#50)

Instruction Following benchmarks
Benchmarko1-miniStep 5 Preview
LMArena Instruction Following13041444
LiveBench Instruction Following65.4%—

Long Context Step 5 Preview leads

o1-mini: 40.1 (#161), Step 5 Preview: 44.5 (#64)

Long Context benchmarks
Benchmarko1-miniStep 5 Preview
LMArena Longer Query13201455

Writing & Preference Step 5 Preview leads

o1-mini: 48.4 (#202), Step 5 Preview: 62.8 (#71)

Writing & Preference benchmarks
Benchmarko1-miniStep 5 Preview
LMArena Text13171442
LMArena Creative Writing12441410
LMArena Multi-Turn13141447
Short-Story Creative Writing64.9%—
LiveBench Language40.9%—

Frequently asked questions

Is o1-mini better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 34.0 on the Noometry Index.

Is o1-mini or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 35.5 in the Noometry coding category.

How many benchmarks do o1-mini and Step 5 Preview share?

13 benchmarks have published results for both models. o1-mini has 39 scored results on Noometry and Step 5 Preview has 18.

Related comparisons

Go deeper