Noometry

Model comparison

GPT-4 Turbo vs Olmo 3.1 32b Think

Olmo 3.1 32b Think is the stronger model overall, scoring 37.9 to 30.5 on the Noometry Index.

Last verified . 15 shared benchmarks.

GPT-4 Turbo OpenAI

30.5

Rank #292 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-4 Turbo scores higher in 3 categories and Olmo 3.1 32b Think in 5 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where Olmo 3.1 32b Think leads 36.3 to 9.0.
  • Olmo 3.1 32b Think has downloadable open weights; the other is API-only.

Side by side

GPT-4 TurboOlmo 3.1 32b Think
ProviderOpenAIAllen Institute for AI (Ai2)
Noometry Index30.537.9
Released2023-11-06—
WeightsProprietaryOpen
Context window128K—
Max output4K—
Input $ / M tokens$10—
Output $ / M tokens$30—
Results tracked3615

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

Category by category

Coding Olmo 3.1 32b Think leads

GPT-4 Turbo: 33.8 (#249), Olmo 3.1 32b Think: 37.7 (#189)

BenchmarkGPT-4 TurboOlmo 3.1 32b Think
LMArena Coding12681291
WeirdML18%—
BigCodeBench Instruct48.2%—
BigCodeBench Complete58.2%—
HumanEval+86.6%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, Olmo 3.1 32b Think: —

BenchmarkGPT-4 TurboOlmo 3.1 32b Think
METR Time Horizons36.7%—

Reasoning Olmo 3.1 32b Think leads

GPT-4 Turbo: 15.3 (#317), Olmo 3.1 32b Think: 25.2 (#150)

BenchmarkGPT-4 TurboOlmo 3.1 32b Think
LMArena Hard Prompts12511272
SimpleBench25.1%—
Chess Puzzles6%—
DTBench61.6%—
LMCA9.8%—
Epoch Capabilities Index127.25—
ForecastBench59.4—

Math Olmo 3.1 32b Think leads

GPT-4 Turbo: 9.0 (#322), Olmo 3.1 32b Think: 36.3 (#168)

BenchmarkGPT-4 TurboOlmo 3.1 32b Think
LMArena Math12721305
FrontierMath (Tiers 1-3)0.7%—
OTIS Mock AIME 2024-20256.7%—
MATH Level 546.7%—

Knowledge Olmo 3.1 32b Think leads

GPT-4 Turbo: 24.3 (#268), Olmo 3.1 32b Think: 35.7 (#181)

BenchmarkGPT-4 TurboOlmo 3.1 32b Think
LMArena Expert12231295
GPQA Diamond46.6%—
Confabulations28.4%—
MMLU81.3%—

Multimodal Not comparable

GPT-4 Turbo: 30.6 (#110), Olmo 3.1 32b Think: —

BenchmarkGPT-4 TurboOlmo 3.1 32b Think
LMArena Vision1090—

Multilingual GPT-4 Turbo leads

GPT-4 Turbo: 40.5 (#216), Olmo 3.1 32b Think: 38.1 (#231)

BenchmarkGPT-4 TurboOlmo 3.1 32b Think
LMArena Non-English12451209
LMArena Chinese12421242
LMArena French12761260
LMArena German12591262
LMArena Russian12591193
LMArena Spanish12601289
LMArena Japanese1194—
LMArena Korean1187—

Instruction Following Too close to call

GPT-4 Turbo: 65.8 (#216), Olmo 3.1 32b Think: 65.6 (#218)

BenchmarkGPT-4 TurboOlmo 3.1 32b Think
LMArena Instruction Following12491247

Long Context Too close to call

GPT-4 Turbo: 38.0 (#206), Olmo 3.1 32b Think: 38.6 (#195)

BenchmarkGPT-4 TurboOlmo 3.1 32b Think
LMArena Longer Query12541272

Writing & Preference GPT-4 Turbo leads

GPT-4 Turbo: 47.7 (#206), Olmo 3.1 32b Think: 46.2 (#220)

BenchmarkGPT-4 TurboOlmo 3.1 32b Think
LMArena Text12721272
LMArena Creative Writing12691226
LMArena Multi-Turn12671252

Frequently asked questions

Is GPT-4 Turbo better than Olmo 3.1 32b Think?

Olmo 3.1 32b Think is the stronger model overall, scoring 37.9 to 30.5 on the Noometry Index.

Is GPT-4 Turbo or Olmo 3.1 32b Think better for coding?

Olmo 3.1 32b Think scores higher on coding benchmarks: 37.7 versus 33.8 in the Noometry coding category.

How many benchmarks do GPT-4 Turbo and Olmo 3.1 32b Think share?

15 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Olmo 3.1 32b Think has 15.

Related comparisons

Go deeper