RankingIA v0.6.1
EN

Claude Haiku 5.5

Anthropic

67.0#54 of 427 overall
Input / output
US$ 0,10 / US$ 0,50
US$ per 1M tokens
Context
1M
tokens
Release
10/07/2026
release date
Weights
Closed
 
Speed
235 tok/s
first token in 243.62 s

Family history

The 4 versions of this family, from first to newest, by release date. Click a point to open that version.

See the data as a table
ModelReleasedScoreRankAA Intel.Elo Arena
Claude 3 Haiku03/04/202415.4#423—1195
Claude 3.5 Haiku10/22/202416.4#419—1255
Claude Haiku 4.510/15/202537.9#280—1397
Claude Haiku 5.510/07/202667.0#5436.21401

Scores by source

Scores by sourcepercentile = % of ranked models it beats
MetricValuePercentileSource
LiveBench weight 3 69.9 65% LiveBench
AA Intelligence Index weight 3 36.2 72% Artificial Analysis
Arena text (Elo) weight 2 1401 46% LMArena
Arena WebDev (Elo) weight 1 1589 75% LMArena
Humanity's Last Exam weight 1 44.4 94% Artificial Analysis
Terminal-Bench weight 1 32.8 84% Artificial Analysis
Long-context reasoning 82.7 94% Artificial Analysis
LiveBench long agentic 40.0 68% LiveBench
LiveBench reasoning 82.4 32% LiveBench
LiveBench coding 91.4 74% LiveBench
LiveBench browser 69.5 58% LiveBench
LiveBench data analysis 53.1 0% LiveBench
LiveBench research 81.9 71% LiveBench
LiveBench design 83.1 87% LiveBench

By category

CategoryScoreRankMetrics
Agentic67.2#19LiveBench long agentic, Terminal-Bench
Coding66.4#17LiveBench coding, Arena WebDev (Elo)
Reasoning58.8#156LiveBench reasoning, Humanity's Last Exam
Data analysis25.0#32LiveBench data analysis
Research71.7#20LiveBench research, Long-context reasoning
Design70.7#12LiveBench design, Arena WebDev (Elo)
Browser use54.0#14LiveBench browser
Chat47.8#107Arena text (Elo)

History

RankingIA score on each collection day (hover to see the rank).

Daily collection started on 10/30/2026. The chart appears from the second day the model is ranked.

Compare with other models

At the sources