Noometry

Model comparison

Claude 3 Haiku vs o3-mini

o3-mini is the stronger model overall, scoring 36.7 to 25.9 on the Noometry Index.

Last verified . 27 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

o3-mini OpenAI

36.7

Rank #212 Confirmed

Summary

  • They share 27 benchmarks with published results for both. Claude 3 Haiku scores higher in 1 category and o3-mini in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where o3-mini leads 38.3 to 17.3.
  • The biggest single-benchmark swing is MATH Level 5: 14.9% for Claude 3 Haiku and 96.5% for o3-mini.

Side by side

Claude 3 Haikuo3-mini
ProviderAnthropicOpenAI
Noometry Index25.936.7
Released2024-03-072024-12-20
WeightsProprietaryProprietary
Context window—200K
Max output—100K
Input $ / M tokens—$1.10
Output $ / M tokens—$4.40
Results tracked3751

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

Category by category

Coding o3-mini leads

Claude 3 Haiku: 26.4 (#325), o3-mini: 40.8 (#132)

BenchmarkClaude 3 Haikuo3-mini
WeirdML9.8%43.7%
LMArena Coding11991378
CadEval12%54%
Aider Polyglot—60.4%
SciCode—39.8%
GSO—1.3%
BigCodeBench Instruct39.4%—
LiveBench Coding—82.7%
BigCodeBench Complete50.1%—
HumanEval+68.9%—
MBPP+68.8%—

Agentic & Tool Use Not comparable

Claude 3 Haiku: —, o3-mini: 29.6 (#84)

BenchmarkClaude 3 Haikuo3-mini
Cybench—22.5%

Reasoning Too close to call

Claude 3 Haiku: 16.3 (#307), o3-mini: 16.3 (#305)

BenchmarkClaude 3 Haikuo3-mini
LMArena Hard Prompts11741366
DTBench50.1%68.8%
LMCA8.8%19%
Epoch Capabilities Index118.35140.34
ForecastBench53.259.6
ARC-AGI-2—3%
SimpleBench—22.8%
Kagi LLM Benchmark34.2%—
ARC-AGI-1—34.5%
CritPt—0.3%
Chess Puzzles—17%
LiveBench Reasoning—89.6%
Mystery Game Puzzles—7%
LiveBench Data Analysis—70.6%
LiveBench—75.9%
WinoGrande74.2%—

Math o3-mini leads

Claude 3 Haiku: 9.8 (#319), o3-mini: 28.1 (#244)

BenchmarkClaude 3 Haikuo3-mini
OTIS Mock AIME 2024-20251.8%76.9%
LMArena Math11881396
MATH Level 514.9%96.5%
FrontierMath (Tiers 1-3)—18.6%
FrontierMath Tier 4—0%
LiveBench Math—77.3%
FrontierMath (Feb 2025 set)—12.4%
FrontierMath Tier 4 (v1)—4.2%

Knowledge o3-mini leads

Claude 3 Haiku: 17.3 (#285), o3-mini: 38.3 (#146)

BenchmarkClaude 3 Haikuo3-mini
GPQA Diamond36.3%77%
Confabulations34.2%17.9%
LMArena Expert11481364
SimpleQA Verified—15.3%
MMLU73.8%—

Multimodal Not comparable

Claude 3 Haiku: 23.6 (#128), o3-mini: —

BenchmarkClaude 3 Haikuo3-mini
LMArena Vision950—
ScienceQA72%—

Multilingual o3-mini leads

Claude 3 Haiku: 36.0 (#243), o3-mini: 45.7 (#164)

BenchmarkClaude 3 Haikuo3-mini
LMArena Non-English11781319
LMArena Chinese11551379
LMArena French11951334
LMArena German11741303
LMArena Japanese11021286
LMArena Korean11091314
LMArena Russian12041304
LMArena Spanish11661321

Instruction Following o3-mini leads

Claude 3 Haiku: 61.3 (#247), o3-mini: 75.1 (#72)

BenchmarkClaude 3 Haikuo3-mini
LMArena Instruction Following11731337
LiveBench Instruction Following—84.4%

Long Context Claude 3 Haiku leads

Claude 3 Haiku: 36.1 (#237), o3-mini: 33.8 (#256)

BenchmarkClaude 3 Haikuo3-mini
LMArena Longer Query11901343
Fiction.LiveBench—50%

Writing & Preference o3-mini leads

Claude 3 Haiku: 29.7 (#291), o3-mini: 50.3 (#182)

BenchmarkClaude 3 Haikuo3-mini
LMArena Text11951337
LMArena Creative Writing11571286
LMArena Multi-Turn11901320
Short-Story Creative Writing—61.7%
EQ-Bench Creative Writing717—
LiveBench Language—50.7%

Frequently asked questions

Is Claude 3 Haiku better than o3-mini?

o3-mini is the stronger model overall, scoring 36.7 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or o3-mini better for coding?

o3-mini scores higher on coding benchmarks: 40.8 versus 26.4 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and o3-mini share?

27 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and o3-mini has 51.

Related comparisons

Go deeper