Noometry

Model comparison

Claude 3 Haiku vs GPT-5.5 Instant

GPT-5.5 Instant is the stronger model overall, scoring 42.7 to 25.9 on the Noometry Index.

Last verified . 21 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

GPT-5.5 Instant OpenAI

42.7

Rank #110 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and GPT-5.5 Instant in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GPT-5.5 Instant leads 61.8 to 29.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 68.1% for GPT-5.5 Instant.

Side by side

Claude 3 HaikuGPT-5.5 Instant
ProviderAnthropicOpenAI
Noometry Index25.942.7
Released2024-03-072026-05-05
WeightsProprietaryProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3727

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

Category by category

Coding GPT-5.5 Instant leads

Claude 3 Haiku: 26.4 (#325), GPT-5.5 Instant: 44.3 (#74)

BenchmarkClaude 3 HaikuGPT-5.5 Instant
LMArena Coding11991433
SciCode—48.6%
WeirdML9.8%—
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Reasoning GPT-5.5 Instant leads

Claude 3 Haiku: 16.3 (#307), GPT-5.5 Instant: 24.9 (#155)

BenchmarkClaude 3 HaikuGPT-5.5 Instant
LMArena Hard Prompts11741426
Epoch Capabilities Index118.35142.52
Kagi LLM Benchmark34.2%—
CritPt—0%
Chess Puzzles—12%
DTBench50.1%—
LMCA8.8%—
ForecastBench53.2—
WinoGrande74.2%—

Math GPT-5.5 Instant leads

Claude 3 Haiku: 9.8 (#319), GPT-5.5 Instant: 26.5 (#259)

BenchmarkClaude 3 HaikuGPT-5.5 Instant
OTIS Mock AIME 2024-20251.8%68.1%
LMArena Math11881420
FrontierMath (Tiers 1-3)—26.3%
FrontierMath Tier 4—2.4%
MATH Level 514.9%—

Knowledge GPT-5.5 Instant leads

Claude 3 Haiku: 17.3 (#285), GPT-5.5 Instant: 48.9 (#74)

BenchmarkClaude 3 HaikuGPT-5.5 Instant
GPQA Diamond36.3%82.5%
LMArena Expert11481409
Confabulations34.2%—
MMLU73.8%—

Multimodal GPT-5.5 Instant leads

Claude 3 Haiku: 23.6 (#128), GPT-5.5 Instant: 40.0 (#52)

BenchmarkClaude 3 HaikuGPT-5.5 Instant
LMArena Vision9501250
LMArena Document—1403
ScienceQA72%—

Multilingual GPT-5.5 Instant leads

Claude 3 Haiku: 36.0 (#243), GPT-5.5 Instant: 52.8 (#80)

BenchmarkClaude 3 HaikuGPT-5.5 Instant
LMArena Non-English11781417
LMArena Chinese11551456
LMArena French11951428
LMArena German11741411
LMArena Japanese11021408
LMArena Korean11091392
LMArena Russian12041431
LMArena Spanish11661429

Instruction Following GPT-5.5 Instant leads

Claude 3 Haiku: 61.3 (#247), GPT-5.5 Instant: 74.2 (#100)

BenchmarkClaude 3 HaikuGPT-5.5 Instant
LMArena Instruction Following11731406

Long Context GPT-5.5 Instant leads

Claude 3 Haiku: 36.1 (#237), GPT-5.5 Instant: 43.4 (#96)

BenchmarkClaude 3 HaikuGPT-5.5 Instant
LMArena Longer Query11901422

Writing & Preference GPT-5.5 Instant leads

Claude 3 Haiku: 29.7 (#291), GPT-5.5 Instant: 61.8 (#85)

BenchmarkClaude 3 HaikuGPT-5.5 Instant
LMArena Text11951419
LMArena Creative Writing11571419
LMArena Multi-Turn11901433
EQ-Bench Creative Writing717—

Frequently asked questions

Is Claude 3 Haiku better than GPT-5.5 Instant?

GPT-5.5 Instant is the stronger model overall, scoring 42.7 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or GPT-5.5 Instant better for coding?

GPT-5.5 Instant scores higher on coding benchmarks: 44.3 versus 26.4 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and GPT-5.5 Instant share?

21 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and GPT-5.5 Instant has 27.

Related comparisons

Go deeper