OnlySOTA

Claude Haiku 5.5

Anthropic closed

New

Executioner

Claude Haiku 5.5 is the executioner: 65 models cost more and score no higher.

Score
43.4
Artificial Analysis Intelligence Index
Best rank
#30
Arena — Code
Price
$0.20
Blended Price, USD per 1M tokens (3:1 input:output)
Best effort
max
Artificial Analysis LLM Leaderboard

Every score this model has on the boards we track, one board at a time. Nothing is averaged across boards.

Scores on each board

Scores at each effort setting

Artificial Analysis LLM Leaderboardbest at max

  1. low29.5
  2. medium34.5
  3. high37.8
  4. xhigh41.2
  5. max43.4

Artificial Analysis Coding Agents · Claude Codebest at xhigh

  1. low0.282
  2. medium0.336
  3. high0.351
  4. xhigh0.414
  5. max0.365

Tested at one setting only

  • Epoch AI Benchmarking Hubmax75.1%
  • Arena — Codehigh1587

Value: where it sits on the kill line

The executioner is the best value on the board: every model that costs more and scores no higher is killed.

Artificial Analysis Intelligence Index · starts at 02040600$0.05$1.00$5.00$20.0043.4$0.20ExecutionerClaude Haiku 5.543.4 · $0.20SOTALow-costKilledBlended Price, USD per 1M tokens (3:1 input:output) · log10
starts at 02040600$0.05$0.50$5.00$20.0043.4$0.20ExecutionerClaude Haiku 5.5Low-costKilledBlended Price, USD per 1M tokens (3:1 input:output) · log10

Compare on the home page chart → How the kill line is drawn →

Other Claude Haiku models

Price, and the Artificial Analysis Intelligence Index score from Artificial Analysis LLM Leaderboard.

Compare with another SOTA model

Details
Family
Claude → Claude Haiku
Blended Price, USD per 1M tokens (3:1 input:output)
$0.20
First seen here
2026-10-07
Sources
4 boards ·12 scores ·10 settings
Also written as
Claude Haiku 5.5claude-haiku-5-5claude-haiku-5.5Haiku 5.5