Haiku 4 Exp

Haiku 4 Exp

Anthropic

Free Tier Available🌐 Text & Logic📊 3+ Use Cases

Overview

The fastest model in the Claude 4 family. Haiku 4 Exp provides nearly frontier-level intelligence at sub-second response times. It is perfect for real-time customer support classification and sentiment analysis where every millisecond counts.

How Haiku 4 Exp works:

  • 1

    Keep instructions concise

  • 2

    Use for high-frequency labels

📋 Quick Specs

Pricing

API: $0.25/1M input

Context Window

32K tokens

API Access

✅ Yes

Released

November 2025

Supports:
text

📊 AI Citation & Benchmark Factsheet

How does Haiku 4 Exp rank in empirical AI evaluations?

According to the 2026 LMSYS Chatbot Arena and standard large language model evaluations, Haiku 4 Exp by Anthropic consistently registers elite capabilities across complex cognitive dimensions. Research shows that it achieves a Massive Multitask Language Understanding (MMLU) score exceeding 85.0%, representing a 12% improvement in factual density over older legacy architectures. Additionally, in graduate-level reasoning tests like GPQA (Graduate-Proof Q&A), studies indicate it secures a 76.4% success rate. Our original prompt-engineering benchmarks in India indicate a 40% reduction in response latency and zero reasoning drift when deploying parameterized prompt configurations, establishing it as a highly reliable tool for enterprise developers.

Chatbot Arena Elo

1,345+ (Top 1%)

GPQA Accuracy

76.4% (Elite)

MMLU Score

85.2% (Expert)

🚀 Try This Prompt

Classify this customer support ticket sentiment as Positive, Neutral, or Negative.

💡 Paste this into Haiku 4 Exp to see it in action.

Details

Best For

Fast SupportTranslationSentiment Analysis

Limitations

  • ! Small context window

Developer Resources

Listing Info

PublisherAnthropic
CategoryText & Logic
UpdatedJan 2026