RankingIA v0.6.1
EN

Claude Opus 5

Anthropic

89.1#4 of 427 overall
Input / output
US$ 5,00 / US$ 25,00
US$ per 1M tokens
Context
1M
tokens
Release
07/24/2026
release date
Weights
Closed
 
Speed
0 tok/s
first token in 0.00 s

Family history

The 9 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 Opus03/04/202414.9#424—1262
Claude 4 Opus05/22/202543.8#210—1377
Claude Opus 4.108/05/202549.7#150—1419
Claude Opus 4.511/24/202568.1#49—1451
Claude Opus 4.602/04/202681.3#14—1502
Claude Opus 4.704/16/202681.2#15—1490
Claude Opus 4.805/27/202677.1#20—1461
Claude Opus 507/24/202689.1#4—1508
Claude Opus 5.509/22/202693.5#158.41516

Scores by source

Scores by sourcepercentile = % of ranked models it beats
MetricValuePercentileSource
Arena text (Elo) weight 2 1508 98% LMArena
Arena WebDev (Elo) weight 1 1691 93% LMArena
Arena vision (Elo) weight 0.5 1320 98% LMArena
Humanity's Last Exam weight 1 54.9 99% Artificial Analysis
Terminal-Bench weight 1 49.0 92% Artificial Analysis
GPQA Diamond 93.2 98% Artificial Analysis
Long-context reasoning 79.3 84% Artificial Analysis

By category

CategoryScoreRankMetrics
Agentic71.2#12Terminal-Bench
Coding71.5#10Arena WebDev (Elo)
Reasoning82.1#5Humanity's Last Exam, GPQA Diamond
Research67.0#46Long-context reasoning
Design71.5#10Arena WebDev (Elo)
Chat74.0#5Arena text (Elo)
Vision74.0#3Arena vision (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