Noometry

Model comparison

Claude 3 Haiku vs Gemini 4 Argon

Gemini 4 Argon is the stronger model overall, scoring 56.5 to 25.9 on the Noometry Index.

Last verified . 13 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

Gemini 4 Argon Google

56.5

Rank #24 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Gemini 4 Argon in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Gemini 4 Argon leads 73.9 to 9.8.

Side by side

Claude 3 HaikuGemini 4 Argon
ProviderAnthropicGoogle
Noometry Index25.956.5
Released2024-03-072026-09-30
WeightsProprietaryProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3721

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

Category by category

Coding Gemini 4 Argon leads

Claude 3 Haiku: 26.4 (#325), Gemini 4 Argon: 62.0 (#9)

BenchmarkClaude 3 HaikuGemini 4 Argon
LMArena Coding11991550
LMArena WebDev—1678
FrontierSWE—55%
SciCode—61.8%
WeirdML9.8%—
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Agentic & Tool Use Not comparable

Claude 3 Haiku: —, Gemini 4 Argon: 49.2 (#8)

BenchmarkClaude 3 HaikuGemini 4 Argon
APEX-Agents—82.2%
Vending-Bench 2—13,718

Reasoning Gemini 4 Argon leads

Claude 3 Haiku: 16.3 (#307), Gemini 4 Argon: 44.2 (#47)

BenchmarkClaude 3 HaikuGemini 4 Argon
LMArena Hard Prompts11741548
Kagi LLM Benchmark34.2%—
CritPt—27.1%
DTBench50.1%—
LMCA8.8%—
Epoch Capabilities Index118.35—
ForecastBench53.2—
WinoGrande74.2%—

Math Gemini 4 Argon leads

Claude 3 Haiku: 9.8 (#319), Gemini 4 Argon: 73.9 (#17)

BenchmarkClaude 3 HaikuGemini 4 Argon
LMArena Math11881536
OTIS Mock AIME 2024-20251.8%—
ProofBench—99%
MATH Level 514.9%—

Knowledge Gemini 4 Argon leads

Claude 3 Haiku: 17.3 (#285), Gemini 4 Argon: 43.9 (#89)

BenchmarkClaude 3 HaikuGemini 4 Argon
LMArena Expert11481553
GPQA Diamond36.3%—
Confabulations34.2%—
MMLU73.8%—

Multimodal Gemini 4 Argon leads

Claude 3 Haiku: 23.6 (#128), Gemini 4 Argon: 46.5 (#14)

BenchmarkClaude 3 HaikuGemini 4 Argon
LMArena Vision950—
Blueprint-Bench 2—54.4%
ScienceQA72%—

Multilingual Gemini 4 Argon leads

Claude 3 Haiku: 36.0 (#243), Gemini 4 Argon: 60.3 (#1)

BenchmarkClaude 3 HaikuGemini 4 Argon
LMArena Non-English11781523
LMArena Chinese11551610
LMArena Russian12041537
LMArena Spanish11661497
LMArena French1195—
LMArena German1174—
LMArena Japanese1102—
LMArena Korean1109—

Instruction Following Gemini 4 Argon leads

Claude 3 Haiku: 61.3 (#247), Gemini 4 Argon: 80.1 (#2)

BenchmarkClaude 3 HaikuGemini 4 Argon
LMArena Instruction Following11731538

Long Context Gemini 4 Argon leads

Claude 3 Haiku: 36.1 (#237), Gemini 4 Argon: 47.6 (#15)

BenchmarkClaude 3 HaikuGemini 4 Argon
LMArena Longer Query11901549

Writing & Preference Gemini 4 Argon leads

Claude 3 Haiku: 29.7 (#291), Gemini 4 Argon: 71.4 (#19)

BenchmarkClaude 3 HaikuGemini 4 Argon
LMArena Text11951534
LMArena Creative Writing11571531
LMArena Multi-Turn11901557
EQ-Bench Creative Writing717—

Frequently asked questions

Is Claude 3 Haiku better than Gemini 4 Argon?

Gemini 4 Argon is the stronger model overall, scoring 56.5 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or Gemini 4 Argon better for coding?

Gemini 4 Argon scores higher on coding benchmarks: 62.0 versus 26.4 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and Gemini 4 Argon share?

13 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Gemini 4 Argon has 21.

Related comparisons

Go deeper