Noometry

Model comparison

Claude 3.5 Haiku vs Gemini 1.0 Pro

Claude 3.5 Haiku is the stronger model overall, scoring 29.2 to 27.3 on the Noometry Index.

Last verified . 22 shared benchmarks.

Claude 3.5 Haiku Anthropic

29.2

Rank #315 Confirmed

Gemini 1.0 Pro Google

27.3

Rank #332 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 8 categories and Gemini 1.0 Pro in 0 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Claude 3.5 Haiku leads 42.7 to 36.0.
  • The biggest single-benchmark swing is MATH Level 5: 46.4% for Claude 3.5 Haiku and 11.2% for Gemini 1.0 Pro.

Side by side

Claude 3.5 HaikuGemini 1.0 Pro
ProviderAnthropicGoogle
Noometry Index29.227.3
Released2024-10-222023-12-13
WeightsProprietaryProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4924

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

Category by category

Coding Too close to call

Claude 3.5 Haiku: 32.9 (#265), Gemini 1.0 Pro: 32.2 (#275)

BenchmarkClaude 3.5 HaikuGemini 1.0 Pro
LMArena Coding12861108
Aider Polyglot28%—
SciCode27.4%—
WeirdML30.7%—
BigCodeBench Instruct46.1%—
LiveBench Coding51.4%—
BigCodeBench Complete59%—
CadEval32%—
HumanEval+—55.5%
MBPP+—61.4%

Agentic & Tool Use Not comparable

Claude 3.5 Haiku: 28.0 (#95), Gemini 1.0 Pro: —

BenchmarkClaude 3.5 HaikuGemini 1.0 Pro
BALROG19.3%—

Reasoning Too close to call

Claude 3.5 Haiku: 17.7 (#290), Gemini 1.0 Pro: 17.1 (#296)

BenchmarkClaude 3.5 HaikuGemini 1.0 Pro
LMArena Hard Prompts12511109
DTBench56.7%45.9%
Epoch Capabilities Index127.15117.04
CritPt0%—
LiveBench Reasoning28.1%—
LiveBench Data Analysis48.5%—
LiveBench43.5%—

Math Claude 3.5 Haiku leads

Claude 3.5 Haiku: 14.7 (#300), Gemini 1.0 Pro: 9.3 (#321)

BenchmarkClaude 3.5 HaikuGemini 1.0 Pro
OTIS Mock AIME 2024-20254.3%1.1%
LMArena Math12441132
MATH Level 546.4%11.2%
Omni-MATH22.4%—
LiveBench Math35.5%—
FrontierMath (Feb 2025 set)0.3%—

Knowledge Claude 3.5 Haiku leads

Claude 3.5 Haiku: 18.7 (#281), Gemini 1.0 Pro: 15.6 (#291)

BenchmarkClaude 3.5 HaikuGemini 1.0 Pro
GPQA Diamond38.1%34%
LMArena Expert12081059
MMLU74.3%70%
MMLU-Pro60.5%—
Confabulations36.7%—
GPQA (HELM)36.3%—

Multimodal Not comparable

Claude 3.5 Haiku: 26.8 (#117), Gemini 1.0 Pro: —

BenchmarkClaude 3.5 HaikuGemini 1.0 Pro
LMArena Vision1092—
GeoBench34%—

Multilingual Claude 3.5 Haiku leads

Claude 3.5 Haiku: 40.0 (#218), Gemini 1.0 Pro: 33.4 (#252)

BenchmarkClaude 3.5 HaikuGemini 1.0 Pro
LMArena Non-English12381138
LMArena Chinese12291124
LMArena French12641145
LMArena German12371125
LMArena Japanese11751023
LMArena Russian12531186
LMArena Spanish12611119
LMArena Korean1173—

Instruction Following Claude 3.5 Haiku leads

Claude 3.5 Haiku: 62.9 (#234), Gemini 1.0 Pro: 57.6 (#267)

BenchmarkClaude 3.5 HaikuGemini 1.0 Pro
LMArena Instruction Following12411114
LiveBench Instruction Following61.9%—
IFEval79.2%—

Long Context Claude 3.5 Haiku leads

Claude 3.5 Haiku: 38.3 (#200), Gemini 1.0 Pro: 34.3 (#249)

BenchmarkClaude 3.5 HaikuGemini 1.0 Pro
LMArena Longer Query12611132

Writing & Preference Claude 3.5 Haiku leads

Claude 3.5 Haiku: 42.7 (#234), Gemini 1.0 Pro: 36.0 (#264)

BenchmarkClaude 3.5 HaikuGemini 1.0 Pro
LMArena Text12551149
LMArena Creative Writing12331131
LMArena Multi-Turn12651139
Short-Story Creative Writing73.5%—
EQ-Bench Creative Writing1146—
WildBench76%—
LiveBench Language35.4%—

Frequently asked questions

Is Claude 3.5 Haiku better than Gemini 1.0 Pro?

Claude 3.5 Haiku is the stronger model overall, scoring 29.2 to 27.3 on the Noometry Index.

Is Claude 3.5 Haiku or Gemini 1.0 Pro better for coding?

They score almost the same on coding (32.9 vs 32.2); test both on your own repository before choosing.

How many benchmarks do Claude 3.5 Haiku and Gemini 1.0 Pro share?

22 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Gemini 1.0 Pro has 24.

Related comparisons

Go deeper