Noometry

Model comparison

Claude 3 Haiku vs GPT-4.5

GPT-4.5 is the stronger model overall, scoring 37.2 to 25.9 on the Noometry Index.

Last verified . 25 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Claude 3 Haiku scores higher in 1 category and GPT-4.5 in 8 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GPT-4.5 leads 56.9 to 29.7.
  • The biggest single-benchmark swing is MATH Level 5: 14.9% for Claude 3 Haiku and 78.6% for GPT-4.5.

Side by side

Claude 3 HaikuGPT-4.5
ProviderAnthropicOpenAI
Noometry Index25.937.2
Released2024-03-072025-02-27
WeightsProprietaryProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3742

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

Category by category

Coding GPT-4.5 leads

Claude 3 Haiku: 26.4 (#325), GPT-4.5: 42.2 (#109)

BenchmarkClaude 3 HaikuGPT-4.5
WeirdML9.8%39.4%
LMArena Coding11991396
Aider Polyglot—44.9%
BigCodeBench Instruct39.4%—
LiveBench Coding—75.2%
BigCodeBench Complete50.1%—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Agentic & Tool Use Not comparable

Claude 3 Haiku: —, GPT-4.5: 27.9 (#97)

BenchmarkClaude 3 HaikuGPT-4.5
Cybench—17.5%

Reasoning Claude 3 Haiku leads

Claude 3 Haiku: 16.3 (#307), GPT-4.5: 13.9 (#330)

BenchmarkClaude 3 HaikuGPT-4.5
LMArena Hard Prompts11741403
Epoch Capabilities Index118.35136.74
ForecastBench53.261.7
ARC-AGI-2—0.8%
SimpleBench—34.5%
Kagi LLM Benchmark34.2%—
ARC-AGI-1—10.3%
EnigmaEval—3.2%
LiveBench Reasoning—71.1%
DTBench50.1%—
LiveBench Data Analysis—64.3%
LMCA8.8%—
LiveBench—69%
WinoGrande74.2%—

Math GPT-4.5 leads

Claude 3 Haiku: 9.8 (#319), GPT-4.5: 32.6 (#211)

BenchmarkClaude 3 HaikuGPT-4.5
OTIS Mock AIME 2024-20251.8%37.8%
LMArena Math11881412
MATH Level 514.9%78.6%
LiveBench Math—69.3%

Knowledge GPT-4.5 leads

Claude 3 Haiku: 17.3 (#285), GPT-4.5: 32.5 (#211)

BenchmarkClaude 3 HaikuGPT-4.5
GPQA Diamond36.3%68.7%
Confabulations34.2%13.6%
LMArena Expert11481394
Humanity's Last Exam—5.4%
MMLU73.8%—

Multimodal GPT-4.5 leads

Claude 3 Haiku: 23.6 (#128), GPT-4.5: 37.6 (#71)

BenchmarkClaude 3 HaikuGPT-4.5
LMArena Vision9501195
VPCT—45%
ScienceQA72%—

Multilingual GPT-4.5 leads

Claude 3 Haiku: 36.0 (#243), GPT-4.5: 52.5 (#83)

BenchmarkClaude 3 HaikuGPT-4.5
LMArena Non-English11781413
LMArena Chinese11551421
LMArena French11951418
LMArena German11741457
LMArena Japanese11021416
LMArena Korean11091392
LMArena Russian12041419
LMArena Spanish1166—

Instruction Following GPT-4.5 leads

Claude 3 Haiku: 61.3 (#247), GPT-4.5: 72.6 (#134)

BenchmarkClaude 3 HaikuGPT-4.5
LMArena Instruction Following11731404
LiveBench Instruction Following—72.3%

Long Context GPT-4.5 leads

Claude 3 Haiku: 36.1 (#237), GPT-4.5: 40.4 (#155)

BenchmarkClaude 3 HaikuGPT-4.5
LMArena Longer Query11901406
Fiction.LiveBench—63.9%

Writing & Preference GPT-4.5 leads

Claude 3 Haiku: 29.7 (#291), GPT-4.5: 56.9 (#134)

BenchmarkClaude 3 HaikuGPT-4.5
LMArena Text11951417
LMArena Creative Writing11571394
EQ-Bench Creative Writing7171258
LMArena Multi-Turn11901444
Short-Story Creative Writing—75.6%
LiveBench Language—61.5%

Frequently asked questions

Is Claude 3 Haiku better than GPT-4.5?

GPT-4.5 is the stronger model overall, scoring 37.2 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or GPT-4.5 better for coding?

GPT-4.5 scores higher on coding benchmarks: 42.2 versus 26.4 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and GPT-4.5 share?

25 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and GPT-4.5 has 42.

Related comparisons

Go deeper