Noometry

Model comparison

Claude 3 Haiku vs Olmo 3 32b Think

Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 25.9 on the Noometry Index.

Last verified . 14 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

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

38.7

Rank #183 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Olmo 3 32b Think in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Olmo 3 32b Think leads 36.5 to 9.8.
  • Olmo 3 32b Think has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuOlmo 3 32b Think
ProviderAnthropicAllen Institute for AI (Ai2)
Noometry Index25.938.7
Released2024-03-07—
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3714

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

Category by category

Coding Olmo 3 32b Think leads

Claude 3 Haiku: 26.4 (#325), Olmo 3 32b Think: 38.6 (#172)

BenchmarkClaude 3 HaikuOlmo 3 32b Think
LMArena Coding11991319
WeirdML9.8%—
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Reasoning Olmo 3 32b Think leads

Claude 3 Haiku: 16.3 (#307), Olmo 3 32b Think: 25.9 (#140)

BenchmarkClaude 3 HaikuOlmo 3 32b Think
LMArena Hard Prompts11741302
Kagi LLM Benchmark34.2%—
DTBench50.1%—
LMCA8.8%—
Epoch Capabilities Index118.35—
ForecastBench53.2—
WinoGrande74.2%—

Math Olmo 3 32b Think leads

Claude 3 Haiku: 9.8 (#319), Olmo 3 32b Think: 36.5 (#165)

BenchmarkClaude 3 HaikuOlmo 3 32b Think
LMArena Math11881316
OTIS Mock AIME 2024-20251.8%—
MATH Level 514.9%—

Knowledge Olmo 3 32b Think leads

Claude 3 Haiku: 17.3 (#285), Olmo 3 32b Think: 35.0 (#190)

BenchmarkClaude 3 HaikuOlmo 3 32b Think
LMArena Expert11481273
GPQA Diamond36.3%—
Confabulations34.2%—
MMLU73.8%—

Multimodal Not comparable

Claude 3 Haiku: 23.6 (#128), Olmo 3 32b Think: —

BenchmarkClaude 3 HaikuOlmo 3 32b Think
LMArena Vision950—
ScienceQA72%—

Multilingual Olmo 3 32b Think leads

Claude 3 Haiku: 36.0 (#243), Olmo 3 32b Think: 41.2 (#210)

BenchmarkClaude 3 HaikuOlmo 3 32b Think
LMArena Non-English11781255
LMArena Chinese11551300
LMArena French11951291
LMArena German11741290
LMArena Russian12041254
LMArena Japanese1102—
LMArena Korean1109—
LMArena Spanish1166—

Instruction Following Olmo 3 32b Think leads

Claude 3 Haiku: 61.3 (#247), Olmo 3 32b Think: 67.2 (#198)

BenchmarkClaude 3 HaikuOlmo 3 32b Think
LMArena Instruction Following11731275

Long Context Olmo 3 32b Think leads

Claude 3 Haiku: 36.1 (#237), Olmo 3 32b Think: 39.4 (#182)

BenchmarkClaude 3 HaikuOlmo 3 32b Think
LMArena Longer Query11901296

Writing & Preference Olmo 3 32b Think leads

Claude 3 Haiku: 29.7 (#291), Olmo 3 32b Think: 49.1 (#193)

BenchmarkClaude 3 HaikuOlmo 3 32b Think
LMArena Text11951300
LMArena Creative Writing11571256
LMArena Multi-Turn11901290
EQ-Bench Creative Writing717—

Frequently asked questions

Is Claude 3 Haiku better than Olmo 3 32b Think?

Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or Olmo 3 32b Think better for coding?

Olmo 3 32b Think scores higher on coding benchmarks: 38.6 versus 26.4 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and Olmo 3 32b Think share?

14 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Olmo 3 32b Think has 14.

Related comparisons

Go deeper