Noometry

Model comparison

GPT-5 Nano vs Olmo 3.1 32b Think

Olmo 3.1 32b Think is the stronger model overall, scoring 37.9 to 33.5 on the Noometry Index.

Last verified . 14 shared benchmarks.

GPT-5 Nano OpenAI

33.5

Rank #241 Confirmed

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

37.9

Rank #191 Confirmed

Summary

  • They share 14 benchmarks with published results for both. GPT-5 Nano scores higher in 3 categories and Olmo 3.1 32b Think in 5 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in instruction following, where GPT-5 Nano leads 75.0 to 65.6.
  • Olmo 3.1 32b Think has downloadable open weights; the other is API-only.

Side by side

GPT-5 NanoOlmo 3.1 32b Think
ProviderOpenAIAllen Institute for AI (Ai2)
Noometry Index33.537.9
Released2025-08-07—
WeightsProprietaryOpen
Context window400K—
Max output128K—
Input $ / M tokens$0.05—
Output $ / M tokens$0.40—
Results tracked4915

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

Category by category

Coding Olmo 3.1 32b Think leads

GPT-5 Nano: 33.6 (#254), Olmo 3.1 32b Think: 37.7 (#189)

BenchmarkGPT-5 NanoOlmo 3.1 32b Think
LMArena Coding13511291
SWE-bench Verified (bash only)34.8%—
WeirdML38.1%—
ALE-Bench718.67—

Agentic & Tool Use Not comparable

GPT-5 Nano: 25.8 (#106), Olmo 3.1 32b Think: —

BenchmarkGPT-5 NanoOlmo 3.1 32b Think
Terminal-Bench21.8%—
Berkeley Function Calling Leaderboard51.5%—

Reasoning Olmo 3.1 32b Think leads

GPT-5 Nano: 16.3 (#306), Olmo 3.1 32b Think: 25.2 (#150)

BenchmarkGPT-5 NanoOlmo 3.1 32b Think
LMArena Hard Prompts13281272
ARC-AGI-22.6%—
Kagi LLM Benchmark62.2%—
ARC-AGI-120.7%—
Chess Puzzles27%—
Mystery Game Puzzles9%—
DTBench62.7%—
LMCA7.9%—
Epoch Capabilities Index139.38—
ForecastBench59.1—

Math Olmo 3.1 32b Think leads

GPT-5 Nano: 29.4 (#241), Olmo 3.1 32b Think: 36.3 (#168)

BenchmarkGPT-5 NanoOlmo 3.1 32b Think
LMArena Math13171305
FrontierMath (Tiers 1-3)20%—
FrontierMath Tier 42.4%—
OTIS Mock AIME 2024-202581.1%—
ProofBench12%—
Omni-MATH54.6%—
MATH Level 595.2%—
FrontierMath (Feb 2025 set)8.3%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge Too close to call

GPT-5 Nano: 35.9 (#178), Olmo 3.1 32b Think: 35.7 (#181)

BenchmarkGPT-5 NanoOlmo 3.1 32b Think
LMArena Expert13211295
GPQA Diamond69.4%—
SimpleQA Verified11.7%—
MMLU-Pro77.8%—
Vectara Hallucination Rate10.5%—
GPQA (HELM)67.9%—

Multimodal Not comparable

GPT-5 Nano: 31.3 (#108), Olmo 3.1 32b Think: —

BenchmarkGPT-5 NanoOlmo 3.1 32b Think
LMArena Vision1159—
VPCT37.2%—

Multilingual GPT-5 Nano leads

GPT-5 Nano: 45.3 (#172), Olmo 3.1 32b Think: 38.1 (#231)

BenchmarkGPT-5 NanoOlmo 3.1 32b Think
LMArena Non-English13131209
LMArena Chinese13561242
LMArena German13271262
LMArena Russian12961193
LMArena Spanish13601289
LMArena French—1260
LMArena Japanese1226—
LMArena Korean1269—

Instruction Following GPT-5 Nano leads

GPT-5 Nano: 75.0 (#79), Olmo 3.1 32b Think: 65.6 (#218)

BenchmarkGPT-5 NanoOlmo 3.1 32b Think
LMArena Instruction Following13061247
IFEval93.2%—

Long Context Olmo 3.1 32b Think leads

GPT-5 Nano: 31.3 (#281), Olmo 3.1 32b Think: 38.6 (#195)

BenchmarkGPT-5 NanoOlmo 3.1 32b Think
LMArena Longer Query13121272
Fiction.LiveBench44.4%—

Writing & Preference Olmo 3.1 32b Think leads

GPT-5 Nano: 39.1 (#249), Olmo 3.1 32b Think: 46.2 (#220)

BenchmarkGPT-5 NanoOlmo 3.1 32b Think
LMArena Text13201272
LMArena Creative Writing12491226
LMArena Multi-Turn13111252
EQ-Bench Creative Writing705—
WildBench80.6%—

Frequently asked questions

Is GPT-5 Nano better than Olmo 3.1 32b Think?

Olmo 3.1 32b Think is the stronger model overall, scoring 37.9 to 33.5 on the Noometry Index.

Is GPT-5 Nano or Olmo 3.1 32b Think better for coding?

Olmo 3.1 32b Think scores higher on coding benchmarks: 37.7 versus 33.6 in the Noometry coding category.

How many benchmarks do GPT-5 Nano and Olmo 3.1 32b Think share?

14 benchmarks have published results for both models. GPT-5 Nano has 49 scored results on Noometry and Olmo 3.1 32b Think has 15.

Related comparisons

Go deeper