Noometry

Model comparison

Claude 3 Haiku vs o3

o3 is the stronger model overall, scoring 47.5 to 25.9 on the Noometry Index.

Last verified . 30 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

o3 OpenAI

47.5

Rank #61 Confirmed

Summary

  • They share 30 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and o3 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where o3 leads 50.2 to 9.8.
  • The biggest single-benchmark swing is MATH Level 5: 14.9% for Claude 3 Haiku and 97.8% for o3.

Side by side

Claude 3 Haikuo3
ProviderAnthropicOpenAI
Noometry Index25.947.5
Released2024-03-072025-04-16
WeightsProprietaryProprietary
Context window—200K
Max output—100K
Input $ / M tokens—$2
Output $ / M tokens—$8
Results tracked3763

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

Category by category

Coding o3 leads

Claude 3 Haiku: 26.4 (#325), o3: 46.8 (#64)

BenchmarkClaude 3 Haikuo3
WeirdML9.8%52.4%
LMArena Coding11991408
CadEval12%74%
SWE-bench Verified—62.3%
SWE-bench Verified (bash only)—58.4%
Aider Polyglot—81.3%
GSO—8.8%
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
ALE-Bench—933.55
HumanEval+68.9%—
MBPP+68.8%—

Agentic & Tool Use Not comparable

Claude 3 Haiku: —, o3: 34.5 (#44)

BenchmarkClaude 3 Haikuo3
Berkeley Function Calling Leaderboard—63%
GDPval—30.8%
DeepResearch Bench—45.2%
OSWorld—23%
LMArena Search—1144
METR Time Horizons—65.4%

Reasoning o3 leads

Claude 3 Haiku: 16.3 (#307), o3: 32.0 (#78)

BenchmarkClaude 3 Haikuo3
Kagi LLM Benchmark34.2%67.6%
LMArena Hard Prompts11741402
DTBench50.1%84.8%
LMCA8.8%39.7%
Epoch Capabilities Index118.35146.86
ForecastBench53.262.5
ARC-AGI-2—6.5%
SimpleBench—53.1%
ARC-AGI-1—60.8%
CritPt—1.4%
Chess Puzzles—38%
EnigmaEval—13.1%
Mystery Game Puzzles—29%
WinoGrande74.2%—

Math o3 leads

Claude 3 Haiku: 9.8 (#319), o3: 50.2 (#58)

BenchmarkClaude 3 Haikuo3
OTIS Mock AIME 2024-20251.8%84.4%
LMArena Math11881426
MATH Level 514.9%97.8%
FrontierMath (Tiers 1-3)—33.3%
Omni-MATH—71.4%
FrontierMath (Feb 2025 set)—18.7%
FrontierMath Tier 4 (v1)—2.1%

Knowledge o3 leads

Claude 3 Haiku: 17.3 (#285), o3: 54.6 (#52)

BenchmarkClaude 3 Haikuo3
GPQA Diamond36.3%81.8%
Confabulations34.2%14.4%
LMArena Expert11481402
Humanity's Last Exam—20.3%
SimpleQA Verified—49.4%
MMLU-Pro—85.9%
GPQA (HELM)—75.3%
MMLU73.8%—

Multimodal o3 leads

Claude 3 Haiku: 23.6 (#128), o3: 41.4 (#36)

BenchmarkClaude 3 Haikuo3
LMArena Vision9501214
GeoBench—74%
VPCT—52%
ScienceQA72%—

Multilingual o3 leads

Claude 3 Haiku: 36.0 (#243), o3: 51.7 (#105)

BenchmarkClaude 3 Haikuo3
LMArena Non-English11781401
LMArena Chinese11551437
LMArena French11951430
LMArena German11741420
LMArena Japanese11021403
LMArena Korean11091370
LMArena Russian12041406
LMArena Spanish11661395

Instruction Following o3 leads

Claude 3 Haiku: 61.3 (#247), o3: 72.8 (#127)

BenchmarkClaude 3 Haikuo3
LMArena Instruction Following11731368
IFEval—86.9%

Long Context o3 leads

Claude 3 Haiku: 36.1 (#237), o3: 53.3 (#6)

BenchmarkClaude 3 Haikuo3
LMArena Longer Query11901372
Fiction.LiveBench—88.9%
CL-bench—17.8%

Writing & Preference o3 leads

Claude 3 Haiku: 29.7 (#291), o3: 63.5 (#64)

BenchmarkClaude 3 Haikuo3
LMArena Text11951410
LMArena Creative Writing11571359
EQ-Bench Creative Writing7171676
LMArena Multi-Turn11901405
Short-Story Creative Writing—83.9%
WildBench—86.1%

Frequently asked questions

Is Claude 3 Haiku better than o3?

o3 is the stronger model overall, scoring 47.5 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or o3 better for coding?

o3 scores higher on coding benchmarks: 46.8 versus 26.4 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and o3 share?

30 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and o3 has 63.

Related comparisons

Go deeper