โ† Back to Model Hub/SIDE-BY-SIDE REVIEW
SHARE THIS:

Anthropic Claude Haiku Latest vs Claude 3 Haiku

How do these models stack up? Below is an expert side-by-side comparison of specifications, context window capacity, live pricing per million tokens, and standardized benchmark scores for Anthropic Claude Haiku Latest and Claude 3 Haiku.

Anthropic

Anthropic Claude Haiku Latest

This model always redirects to the latest model in the Anthropic Claude Haiku family.

View Full Specs
Anthropic

Claude 3 Haiku

Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku) #multimodal

View Full Specs

Technical Specifications

SpecificationAnthropic Claude Haiku LatestClaude 3 Haiku
ProviderAnthropicAnthropic
Context Window200,000 tokens200,000 tokens
Agent SuitabilityN/AN/A
Time to First Token (TTFT)N/AN/A
Deployment Modelmanaged apimanaged api
Production Stabilitystablestable
API AvailableYesYes
Released Date2026-04-272024-03-13

API Pricing Comparison

Input Price per Million Tokens

Anthropic Claude Haiku Latest

$1.00

Claude 3 Haiku

$0.25

Output Price per Million Tokens

Anthropic Claude Haiku Latest

$5.00

Claude 3 Haiku

$1.25

Want to test both models live?

Run side-by-side prompt prompts in our dynamic Sandbox. Check execution speeds, latency metrics, and compute actual costs in real-time.

Benchmark Performance Metrics

Scores show the raw performance percentages verified across key evaluation suites. Higher bars indicate superior accuracy and capability in that domain.

MMLUGeneral knowledge & multi-task understanding
N/Avs7520.0%
Anthropic Claude Haiku Latest
Claude 3 Haiku
HumanEvalPython coding & logic synthesis
N/Avs7590.0%
Anthropic Claude Haiku Latest
Claude 3 Haiku
MATHComplex mathematical problem solving
N/Avs3890.0%
Anthropic Claude Haiku Latest
Claude 3 Haiku
GPQAGraduate-level expert reasoning
N/Avs3200.0%
Anthropic Claude Haiku Latest
Claude 3 Haiku
HellaSwagCommonsense reasoning and inference
N/Avs8810.0%
Anthropic Claude Haiku Latest
Claude 3 Haiku
MT-BenchMulti-turn conversation flow quality
N/Avs800.0%
Anthropic Claude Haiku Latest
Claude 3 Haiku

Anthropic Claude Haiku Latest Quirks & Gotchas

No developer gotchas reported.

Claude 3 Haiku Quirks & Gotchas

No developer gotchas reported.