Noometry

Model comparison

GPT-6 Luna vs Olmo 3.1 32b Think

GPT-6 Luna is the stronger model overall, scoring 53.3 to 37.9 on the Noometry Index.

Last verified . 15 shared benchmarks.

GPT-6 Luna OpenAI

53.3

Rank #36 Confirmed

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

37.9

Rank #191 Confirmed

Summary

  • They share 15 benchmarks with published results for both. GPT-6 Luna scores higher in 8 categories and Olmo 3.1 32b Think in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Luna leads 76.1 to 36.3.
  • Olmo 3.1 32b Think has downloadable open weights; the other is API-only.

Side by side

GPT-6 LunaOlmo 3.1 32b Think
ProviderOpenAIAllen Institute for AI (Ai2)
Noometry Index53.337.9
Released2026-09-22—
WeightsProprietaryOpen
Context window1.05M—
Max output128K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.50—
Results tracked4215

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

Category by category

Coding GPT-6 Luna leads

GPT-6 Luna: 55.5 (#25), Olmo 3.1 32b Think: 37.7 (#189)

BenchmarkGPT-6 LunaOlmo 3.1 32b Think
LMArena Coding14391291
DeepSWE66.6%—
FrontierCode42.4%—
LMArena WebDev1581—
SciCode54.6%—
ALE-Bench1,577—

Agentic & Tool Use Not comparable

GPT-6 Luna: 33.3 (#54), Olmo 3.1 32b Think: —

BenchmarkGPT-6 LunaOlmo 3.1 32b Think
APEX-Agents44.3%—
GDP.pdf23%—

Reasoning GPT-6 Luna leads

GPT-6 Luna: 48.2 (#41), Olmo 3.1 32b Think: 25.2 (#150)

BenchmarkGPT-6 LunaOlmo 3.1 32b Think
LMArena Hard Prompts14111272
ARC-AGI-259.3%—
NYT Connections (extended)68.7%—
ARC-AGI-186.7%—
CritPt19.4%—
Chess Puzzles31%—
Mystery Game Puzzles7%—
DTBench90.1%—
LMCA44.5%—
Epoch Capabilities Index156.28—

Math GPT-6 Luna leads

GPT-6 Luna: 76.1 (#15), Olmo 3.1 32b Think: 36.3 (#168)

BenchmarkGPT-6 LunaOlmo 3.1 32b Think
LMArena Math14161305
FrontierMath (Tiers 1-3)78.9%—
FrontierMath Tier 456.1%—
OTIS Mock AIME 2024-202598.9%—
ProofBench64%—

Knowledge GPT-6 Luna leads

GPT-6 Luna: 57.0 (#41), Olmo 3.1 32b Think: 35.7 (#181)

BenchmarkGPT-6 LunaOlmo 3.1 32b Think
LMArena Expert14441295
GPQA Diamond90.5%—
SimpleQA Verified41.4%—

Multimodal Not comparable

GPT-6 Luna: 42.4 (#30), Olmo 3.1 32b Think: —

BenchmarkGPT-6 LunaOlmo 3.1 32b Think
LMArena Vision1217—
Blueprint-Bench 231.2%—
Furniture Assembly44.2%—

Multilingual GPT-6 Luna leads

GPT-6 Luna: 50.5 (#117), Olmo 3.1 32b Think: 38.1 (#231)

BenchmarkGPT-6 LunaOlmo 3.1 32b Think
LMArena Non-English13861209
LMArena Chinese14331242
LMArena French14201260
LMArena German13691262
LMArena Russian13941193
LMArena Spanish13931289
LMArena Japanese1369—
LMArena Korean1360—

Instruction Following GPT-6 Luna leads

GPT-6 Luna: 74.3 (#99), Olmo 3.1 32b Think: 65.6 (#218)

BenchmarkGPT-6 LunaOlmo 3.1 32b Think
LMArena Instruction Following14091247

Long Context GPT-6 Luna leads

GPT-6 Luna: 43.0 (#111), Olmo 3.1 32b Think: 38.6 (#195)

BenchmarkGPT-6 LunaOlmo 3.1 32b Think
LMArena Longer Query14091272

Writing & Preference GPT-6 Luna leads

GPT-6 Luna: 58.3 (#119), Olmo 3.1 32b Think: 46.2 (#220)

BenchmarkGPT-6 LunaOlmo 3.1 32b Think
LMArena Text13911272
LMArena Creative Writing13631226
LMArena Multi-Turn13961252

Frequently asked questions

Is GPT-6 Luna better than Olmo 3.1 32b Think?

GPT-6 Luna is the stronger model overall, scoring 53.3 to 37.9 on the Noometry Index.

Is GPT-6 Luna or Olmo 3.1 32b Think better for coding?

GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 37.7 in the Noometry coding category.

How many benchmarks do GPT-6 Luna and Olmo 3.1 32b Think share?

15 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and Olmo 3.1 32b Think has 15.

Related comparisons

Go deeper