█

AI/TLDR

Buy me a coffee
Buy me a coffee
PROMOTE YOUR WEBSITE IN JUST $20

Model comparison

Claude 3 Haiku vs Gemini 1.5 Pro

AnthropicClaude 3 Haiku
Input
$0.25
Output
$1.25
Context
200K tokens
Released
2024-03-13
Full model page →GoogleGemini 1.5 Pro
Input
$1.25 / 1M tokens (prompts ≤128K); $2.50 / 1M tokens (prompts >128K)
Output
$5.00 / 1M tokens (prompts ≤128K); $10.00 / 1M tokens (prompts >128K)
Context
Up to 2,097,152 tokens (2M) at general availability; launched at 1M tokens in Feb 2024, with a 128K standard tier at first
Released
2024-02-15
Full model page →
Short answer

Gemini 1.5 Pro scores higher on 3 of the 3 benchmarks both models report; Claude 3 Haiku is cheaper on input tokens ($0.3 vs $1.3 per 1M, 5×); Gemini 1.5 Pro has the larger context window (2.097152M vs 200K).

Specs and pricing side by side

SpecClaude 3 HaikuGemini 1.5 Pro
MakerAnthropicGoogle
Released2024-03-132024-02-15
Context window200K tokensUp to 2,097,152 tokens (2M) at general availability; launched at 1M tokens in Feb 2024, with a 128K standard tier at first
Max output4,096 tokens8,192 tokens
Input price$0.25$1.25 / 1M tokens (prompts ≤128K); $2.50 / 1M tokens (prompts >128K)
Output price$1.25$5.00 / 1M tokens (prompts ≤128K); $10.00 / 1M tokens (prompts >128K)
ParametersUndisclosedNot publicly disclosed
LicenseProprietaryProprietary (Google). Available only as a hosted API; not redistributable.
WeightsAPI onlyAPI onlysame
ModalitiesText, Visiontext, image, audio, video, code
Knowledge cutoffAugust 2023November 2023

Benchmarks both models report

BenchmarkClaude 3 HaikuGemini 1.5 Pro
MMLU75.2%85.9%
HumanEval75.9%89%
MATH38.9%82.9%

Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.

Which one should you pick?

Pick Claude 3 Haiku if…

  • Cost matters: input tokens cost 5× less ($0.3 vs $1.3 per 1M).
  • You need Text / Vision input, which Gemini 1.5 Pro lacks.
  • Your use case is: high-volume, cost-sensitive tasks like classification, tagging, and content moderation.

Pick Gemini 1.5 Pro if…

  • You care about MMLU, HumanEval, MATH (it scores higher on 3 shared benchmarks).
  • You need the longer context (2.097152M vs 200K).
  • You need text / image / audio / video / code input, which Claude 3 Haiku lacks.
  • Your use case is: analyzing very long documents, contracts, or research-paper bundles in one pass.

FAQ

Which is better, Claude 3 Haiku or Gemini 1.5 Pro?

Gemini 1.5 Pro scores higher on 3 of the 3 benchmarks both models report; Claude 3 Haiku is cheaper on input tokens ($0.3 vs $1.3 per 1M, 5×); Gemini 1.5 Pro has the larger context window (2.097152M vs 200K). The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.

How much cheaper is Claude 3 Haiku?

Claude 3 Haiku: $0.25 input, $1.25 output. Gemini 1.5 Pro: $1.25 / 1M tokens (prompts ≤128K); $2.50 / 1M tokens (prompts >128K) input, $5.00 / 1M tokens (prompts ≤128K); $10.00 / 1M tokens (prompts >128K) output (list API prices as published by each maker).

What are the context windows of Claude 3 Haiku and Gemini 1.5 Pro?

Claude 3 Haiku offers 200K tokens with up to 4,096 tokens output; Gemini 1.5 Pro offers Up to 2,097,152 tokens (2M) at general availability; launched at 1M tokens in Feb 2024, with a 128K standard tier at first with up to 8,192 tokens output.

Is Claude 3 Haiku newer than Gemini 1.5 Pro?

Claude 3 Haiku was released 2024-03-13; Gemini 1.5 Pro was released 2024-02-15.

Go deeper