Noometry

Model comparison

GPT-5.4 nano vs Olmo 3 32b Think

GPT-5.4 nano is the stronger model overall, scoring 41.9 to 38.1 on the Noometry Index.

Last verified . 14 shared benchmarks.

GPT-5.4 nano OpenAI

41.9

Rank #111 Confirmed

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

38.1

Rank #182 Confirmed

Summary

  • They share 14 benchmarks with published results for both. GPT-5.4 nano scores higher in 7 categories and Olmo 3 32b Think in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-5.4 nano leads 41.8 to 34.4.
  • Olmo 3 32b Think has downloadable open weights; the other is API-only.

Side by side

GPT-5.4 nanoOlmo 3 32b Think
ProviderOpenAIAllen Institute for AI (Ai2)
Noometry Index41.938.1
Released2026-03-17—
WeightsProprietaryOpen
Context window400K—
Max output128K—
Input $ / M tokens$0.20—
Output $ / M tokens$1.25—
Results tracked4014

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

Category by category

Coding GPT-5.4 nano leads

GPT-5.4 nano: 43.1 (#82), Olmo 3 32b Think: 38.0 (#169)

BenchmarkGPT-5.4 nanoOlmo 3 32b Think
LMArena Coding14041318
SciCode46.9%—
WeirdML49.2%—
ALE-Bench1,005—

Reasoning Olmo 3 32b Think leads

GPT-5.4 nano: 23.8 (#159), Olmo 3 32b Think: 24.9 (#138)

BenchmarkGPT-5.4 nanoOlmo 3 32b Think
LMArena Hard Prompts13801302
ARC-AGI-25.7%—
Kagi LLM Benchmark39.7%—
ARC-AGI-151.5%—
CritPt9.3%—
Chess Puzzles30%—
Mystery Game Puzzles9%—
DTBench80.3%—
LMCA36.9%—
Epoch Capabilities Index145.78—
ForecastBench57.3—

Math GPT-5.4 nano leads

GPT-5.4 nano: 40.7 (#76), Olmo 3 32b Think: 33.8 (#165)

BenchmarkGPT-5.4 nanoOlmo 3 32b Think
LMArena Math14061315
FrontierMath (Tiers 1-3)44.9%—
FrontierMath Tier 412.2%—
OTIS Mock AIME 2024-202587.8%—
ProofBench5%—
FrontierMath (Feb 2025 set)25.9%—
FrontierMath Tier 4 (v1)6.3%—

Knowledge GPT-5.4 nano leads

GPT-5.4 nano: 41.8 (#94), Olmo 3 32b Think: 34.4 (#189)

BenchmarkGPT-5.4 nanoOlmo 3 32b Think
LMArena Expert13971272
GPQA Diamond78.5%—
SimpleQA Verified11.7%—
Vectara Hallucination Rate3.1%—

Multimodal Not comparable

GPT-5.4 nano: 36.0 (#73), Olmo 3 32b Think: —

BenchmarkGPT-5.4 nanoOlmo 3 32b Think
LMArena Vision1196—

Multilingual GPT-5.4 nano leads

GPT-5.4 nano: 48.8 (#136), Olmo 3 32b Think: 41.4 (#205)

BenchmarkGPT-5.4 nanoOlmo 3 32b Think
LMArena Non-English13591255
LMArena Chinese13911300
LMArena French13961291
LMArena German13681290
LMArena Russian13631255
LMArena Japanese1342—
LMArena Korean1321—
LMArena Spanish1368—

Instruction Following GPT-5.4 nano leads

GPT-5.4 nano: 72.1 (#139), Olmo 3 32b Think: 67.4 (#193)

BenchmarkGPT-5.4 nanoOlmo 3 32b Think
LMArena Instruction Following13621275

Long Context GPT-5.4 nano leads

GPT-5.4 nano: 41.6 (#131), Olmo 3 32b Think: 39.4 (#177)

BenchmarkGPT-5.4 nanoOlmo 3 32b Think
LMArena Longer Query13651296

Writing & Preference GPT-5.4 nano leads

GPT-5.4 nano: 55.9 (#137), Olmo 3 32b Think: 49.2 (#188)

BenchmarkGPT-5.4 nanoOlmo 3 32b Think
LMArena Text13721300
LMArena Creative Writing13131256
LMArena Multi-Turn13821289

Frequently asked questions

Is GPT-5.4 nano better than Olmo 3 32b Think?

GPT-5.4 nano is the stronger model overall, scoring 41.9 to 38.1 on the Noometry Index.

Is GPT-5.4 nano or Olmo 3 32b Think better for coding?

GPT-5.4 nano scores higher on coding benchmarks: 43.1 versus 38.0 in the Noometry coding category.

How many benchmarks do GPT-5.4 nano and Olmo 3 32b Think share?

14 benchmarks have published results for both models. GPT-5.4 nano has 40 scored results on Noometry and Olmo 3 32b Think has 14.

Related comparisons

Go deeper