Noometry

Model comparison

GPT-4.1 mini vs Olmo 3 32b Think

Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 33.6 on the Noometry Index.

Last verified . 14 shared benchmarks.

GPT-4.1 mini OpenAI

33.6

Rank #240 Confirmed

Olmo 3 32b Think Allen Institute for AI (Ai2)

38.7

Rank #183 Confirmed

Summary

  • They share 14 benchmarks with published results for both. GPT-4.1 mini scores higher in 2 categories and Olmo 3 32b Think in 6 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Olmo 3 32b Think leads 25.9 to 10.8.
  • Olmo 3 32b Think has downloadable open weights; the other is API-only.

Side by side

GPT-4.1 miniOlmo 3 32b Think
ProviderOpenAIAllen Institute for AI (Ai2)
Noometry Index33.638.7
Released2025-04-14—
WeightsProprietaryOpen
Context window1.05M—
Max output33K—
Input $ / M tokens$0.40—
Output $ / M tokens$1.60—
Results tracked4714

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

Category by category

Coding Olmo 3 32b Think leads

GPT-4.1 mini: 30.6 (#293), Olmo 3 32b Think: 38.6 (#172)

BenchmarkGPT-4.1 miniOlmo 3 32b Think
LMArena Coding13671319
SWE-bench Verified (bash only)23.9%—
Aider Polyglot32.4%—
SciCode40.4%—
WeirdML37.6%—
BigCodeBench Instruct48.9%—
CadEval16%—

Agentic & Tool Use Not comparable

GPT-4.1 mini: 33.3 (#55), Olmo 3 32b Think: —

BenchmarkGPT-4.1 miniOlmo 3 32b Think
Berkeley Function Calling Leaderboard50.5%—

Reasoning Olmo 3 32b Think leads

GPT-4.1 mini: 10.8 (#340), Olmo 3 32b Think: 25.9 (#140)

BenchmarkGPT-4.1 miniOlmo 3 32b Think
LMArena Hard Prompts13491302
ARC-AGI-20%—
Kagi LLM Benchmark48.6%—
ARC-AGI-13.5%—
CritPt0%—
Chess Puzzles7%—
Mystery Game Puzzles7%—
DTBench68.8%—
LMCA21.1%—
Epoch Capabilities Index135.01—

Math Olmo 3 32b Think leads

GPT-4.1 mini: 24.1 (#270), Olmo 3 32b Think: 36.5 (#165)

BenchmarkGPT-4.1 miniOlmo 3 32b Think
LMArena Math13431316
FrontierMath (Tiers 1-3)6.7%—
OTIS Mock AIME 2024-202544.7%—
Omni-MATH49.1%—
MATH Level 587.3%—
FrontierMath (Feb 2025 set)4.5%—

Knowledge Too close to call

GPT-4.1 mini: 34.7 (#194), Olmo 3 32b Think: 35.0 (#190)

BenchmarkGPT-4.1 miniOlmo 3 32b Think
LMArena Expert13381273
GPQA Diamond65.8%—
SimpleQA Verified12.7%—
MMLU-Pro78.3%—
GPQA (HELM)61.4%—

Multimodal Not comparable

GPT-4.1 mini: 35.8 (#82), Olmo 3 32b Think: —

BenchmarkGPT-4.1 miniOlmo 3 32b Think
LMArena Vision1181—

Multilingual GPT-4.1 mini leads

GPT-4.1 mini: 45.7 (#166), Olmo 3 32b Think: 41.2 (#210)

BenchmarkGPT-4.1 miniOlmo 3 32b Think
LMArena Non-English13181255
LMArena Chinese13291300
LMArena French13581291
LMArena German13511290
LMArena Russian13241254
LMArena Japanese1290—
LMArena Korean1298—
LMArena Spanish1319—

Instruction Following GPT-4.1 mini leads

GPT-4.1 mini: 73.7 (#118), Olmo 3 32b Think: 67.2 (#198)

BenchmarkGPT-4.1 miniOlmo 3 32b Think
LMArena Instruction Following13331275
IFEval90.4%—

Long Context Olmo 3 32b Think leads

GPT-4.1 mini: 31.8 (#275), Olmo 3 32b Think: 39.4 (#182)

BenchmarkGPT-4.1 miniOlmo 3 32b Think
LMArena Longer Query13441296
Fiction.LiveBench44.4%—

Writing & Preference Too close to call

GPT-4.1 mini: 48.6 (#199), Olmo 3 32b Think: 49.1 (#193)

BenchmarkGPT-4.1 miniOlmo 3 32b Think
LMArena Text13401300
LMArena Creative Writing13001256
LMArena Multi-Turn13541290
EQ-Bench Creative Writing1147—
WildBench83.8%—

Frequently asked questions

Is GPT-4.1 mini better than Olmo 3 32b Think?

Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 33.6 on the Noometry Index.

Is GPT-4.1 mini or Olmo 3 32b Think better for coding?

Olmo 3 32b Think scores higher on coding benchmarks: 38.6 versus 30.6 in the Noometry coding category.

How many benchmarks do GPT-4.1 mini and Olmo 3 32b Think share?

14 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and Olmo 3 32b Think has 14.

Related comparisons

Go deeper