Noometry

Model comparison

Claude 3.5 Haiku vs o1-mini

o1-mini is the stronger model overall, scoring 34.0 to 29.2 on the Noometry Index.

Last verified . 33 shared benchmarks.

Claude 3.5 Haiku Anthropic

29.2

Rank #315 Confirmed

o1-mini OpenAI

34.0

Rank #235 Confirmed

Summary

  • They share 33 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 2 categories and o1-mini in 7 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where o1-mini leads 35.4 to 14.7.
  • The biggest single-benchmark swing is LiveBench Reasoning: 28.1% for Claude 3.5 Haiku and 72.3% for o1-mini.

Side by side

Claude 3.5 Haikuo1-mini
ProviderAnthropicOpenAI
Noometry Index29.234.0
Released2024-10-222024-09-12
WeightsProprietaryProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4939

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

Category by category

Coding o1-mini leads

Claude 3.5 Haiku: 32.9 (#265), o1-mini: 35.5 (#224)

BenchmarkClaude 3.5 Haikuo1-mini
Aider Polyglot28%32.9%
WeirdML30.7%36.3%
LiveBench Coding51.4%48%
LMArena Coding12861362
SciCode27.4%—
BigCodeBench Instruct46.1%—
BigCodeBench Complete59%—
CadEval32%—
HumanEval+—89%
MBPP+—78.8%

Agentic & Tool Use Claude 3.5 Haiku leads

Claude 3.5 Haiku: 28.0 (#95), o1-mini: 24.6 (#118)

BenchmarkClaude 3.5 Haikuo1-mini
Cybench—10%
BALROG19.3%—

Reasoning Claude 3.5 Haiku leads

Claude 3.5 Haiku: 17.7 (#290), o1-mini: 8.8 (#346)

BenchmarkClaude 3.5 Haikuo1-mini
LiveBench Reasoning28.1%72.3%
LMArena Hard Prompts12511333
LiveBench Data Analysis48.5%57.9%
Epoch Capabilities Index127.15135.82
LiveBench43.5%57.8%
ARC-AGI-2—0.8%
SimpleBench—18.1%
ARC-AGI-1—14%
CritPt0%—
DTBench56.7%—

Math o1-mini leads

Claude 3.5 Haiku: 14.7 (#300), o1-mini: 35.4 (#186)

BenchmarkClaude 3.5 Haikuo1-mini
OTIS Mock AIME 2024-20254.3%46.9%
LiveBench Math35.5%62%
LMArena Math12441358
MATH Level 546.4%89.2%
FrontierMath (Feb 2025 set)0.3%1.7%
Omni-MATH22.4%—

Knowledge o1-mini leads

Claude 3.5 Haiku: 18.7 (#281), o1-mini: 34.9 (#192)

BenchmarkClaude 3.5 Haikuo1-mini
GPQA Diamond38.1%62.4%
Confabulations36.7%18.6%
LMArena Expert12081316
MMLU-Pro60.5%—
GPQA (HELM)36.3%—
MMLU74.3%—

Multimodal Not comparable

Claude 3.5 Haiku: 26.8 (#117), o1-mini: —

BenchmarkClaude 3.5 Haikuo1-mini
LMArena Vision1092—
GeoBench34%—

Multilingual o1-mini leads

Claude 3.5 Haiku: 40.0 (#218), o1-mini: 43.6 (#182)

BenchmarkClaude 3.5 Haikuo1-mini
LMArena Non-English12381289
LMArena Chinese12291314
LMArena French12641293
LMArena German12371278
LMArena Japanese11751245
LMArena Korean11731223
LMArena Russian12531283
LMArena Spanish12611303

Instruction Following o1-mini leads

Claude 3.5 Haiku: 62.9 (#234), o1-mini: 66.7 (#206)

BenchmarkClaude 3.5 Haikuo1-mini
LiveBench Instruction Following61.9%65.4%
LMArena Instruction Following12411304
IFEval79.2%—

Long Context o1-mini leads

Claude 3.5 Haiku: 38.3 (#200), o1-mini: 40.1 (#161)

BenchmarkClaude 3.5 Haikuo1-mini
LMArena Longer Query12611320

Writing & Preference o1-mini leads

Claude 3.5 Haiku: 42.7 (#234), o1-mini: 48.4 (#202)

BenchmarkClaude 3.5 Haikuo1-mini
LMArena Text12551317
LMArena Creative Writing12331244
Short-Story Creative Writing73.5%64.9%
LMArena Multi-Turn12651314
LiveBench Language35.4%40.9%
EQ-Bench Creative Writing1146—
WildBench76%—

Frequently asked questions

Is Claude 3.5 Haiku better than o1-mini?

o1-mini is the stronger model overall, scoring 34.0 to 29.2 on the Noometry Index.

Is Claude 3.5 Haiku or o1-mini better for coding?

o1-mini scores higher on coding benchmarks: 35.5 versus 32.9 in the Noometry coding category.

How many benchmarks do Claude 3.5 Haiku and o1-mini share?

33 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and o1-mini has 39.

Related comparisons

Go deeper