Noometry

Model comparison

GPT-5.4 nano vs Olmo 3.1 32b Instruct

GPT-5.4 nano is the stronger model overall, scoring 41.9 to 39.4 on the Noometry Index.

Last verified . 16 shared benchmarks.

GPT-5.4 nano OpenAI

41.9

Rank #125 Confirmed

Olmo 3.1 32b Instruct Allen Institute for AI (Ai2)

39.4

Rank #168 Confirmed

Summary

  • They share 16 benchmarks with published results for both. GPT-5.4 nano scores higher in 7 categories and Olmo 3.1 32b Instruct in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in multilingual, where GPT-5.4 nano leads 48.6 to 42.6.
  • Olmo 3.1 32b Instruct has downloadable open weights; the other is API-only.

Side by side

GPT-5.4 nanoOlmo 3.1 32b Instruct
ProviderOpenAIAllen Institute for AI (Ai2)
Noometry Index41.939.4
Released2026-03-17—
WeightsProprietaryOpen
Context window400K—
Max output128K—
Input $ / M tokens$0.20—
Output $ / M tokens$1.25—
Results tracked4016

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: 43.6 (#84), Olmo 3.1 32b Instruct: 39.5 (#157)

BenchmarkGPT-5.4 nanoOlmo 3.1 32b Instruct
LMArena Coding14051347
SciCode46.9%—
WeirdML49.2%—
ALE-Bench1,005—

Reasoning Olmo 3.1 32b Instruct leads

GPT-5.4 nano: 23.7 (#173), Olmo 3.1 32b Instruct: 26.4 (#132)

BenchmarkGPT-5.4 nanoOlmo 3.1 32b Instruct
LMArena Hard Prompts13811322
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 Index145.81—
ForecastBench57.3—

Math GPT-5.4 nano leads

GPT-5.4 nano: 40.9 (#88), Olmo 3.1 32b Instruct: 36.3 (#167)

BenchmarkGPT-5.4 nanoOlmo 3.1 32b Instruct
LMArena Math14061305
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: 41.9 (#103), Olmo 3.1 32b Instruct: 36.1 (#175)

BenchmarkGPT-5.4 nanoOlmo 3.1 32b Instruct
LMArena Expert13961308
GPQA Diamond78.5%—
SimpleQA Verified11.7%—
Vectara Hallucination Rate3.1%—

Multimodal Not comparable

GPT-5.4 nano: 36.7 (#78), Olmo 3.1 32b Instruct: —

BenchmarkGPT-5.4 nanoOlmo 3.1 32b Instruct
LMArena Vision1196—

Multilingual GPT-5.4 nano leads

GPT-5.4 nano: 48.6 (#140), Olmo 3.1 32b Instruct: 42.6 (#191)

BenchmarkGPT-5.4 nanoOlmo 3.1 32b Instruct
LMArena Non-English13591275
LMArena Chinese13921304
LMArena French13961328
LMArena German13671282
LMArena Korean13201206
LMArena Russian13631268
LMArena Spanish13711336
LMArena Japanese1343—

Instruction Following GPT-5.4 nano leads

GPT-5.4 nano: 71.9 (#144), Olmo 3.1 32b Instruct: 68.6 (#187)

BenchmarkGPT-5.4 nanoOlmo 3.1 32b Instruct
LMArena Instruction Following13621299

Long Context GPT-5.4 nano leads

GPT-5.4 nano: 41.6 (#137), Olmo 3.1 32b Instruct: 39.9 (#166)

BenchmarkGPT-5.4 nanoOlmo 3.1 32b Instruct
LMArena Longer Query13661312

Writing & Preference GPT-5.4 nano leads

GPT-5.4 nano: 55.7 (#142), Olmo 3.1 32b Instruct: 50.2 (#185)

BenchmarkGPT-5.4 nanoOlmo 3.1 32b Instruct
LMArena Text13721311
LMArena Creative Writing13141264
LMArena Multi-Turn13821309

Frequently asked questions

Is GPT-5.4 nano better than Olmo 3.1 32b Instruct?

GPT-5.4 nano is the stronger model overall, scoring 41.9 to 39.4 on the Noometry Index.

Is GPT-5.4 nano or Olmo 3.1 32b Instruct better for coding?

GPT-5.4 nano scores higher on coding benchmarks: 43.6 versus 39.5 in the Noometry coding category.

How many benchmarks do GPT-5.4 nano and Olmo 3.1 32b Instruct share?

16 benchmarks have published results for both models. GPT-5.4 nano has 40 scored results on Noometry and Olmo 3.1 32b Instruct has 16.

Related comparisons

Go deeper