Skip to content
MAR
Sign inRequest access

Language model rankings / Claude Haiku 4 5 20251001

Claude Haiku 4 5 20251001

Anthropic

Marsel score
—
Licence
ProprietaryProprietary
Context
—
Modalities
—

Measurements

Each figure is a measurement published by the named source on the named date. Where the source publishes its own page for this model, the date links to it so the figure can be checked at origin.

MetricValueSourceMeasuredIn score
Human preference (Elo)A rating derived from blind head-to-head votes by people. It measures which answer humans preferred — not correctness.1414LMArena2026-10-15 ↗yes

Human preference (Elo) over time

as of 2026-10-15
1412.514131413.514141414.508-1708-2909-1009-2110-0310-14DateHuman preference (Elo)Human preference (Elo) 08-12: 1413Human preference (Elo) 08-19: 1413Human preference (Elo) 08-21: 1413Human preference (Elo) 08-27: 1413Human preference (Elo) 09-01: 1413Human preference (Elo) 09-13: 1415Human preference (Elo) 09-25: 1414Human preference (Elo) 09-30: 1414Human preference (Elo) 10-02: 1414Human preference (Elo) 10-08: 1414Human preference (Elo) 10-13: 1414Human preference (Elo) 10-15: 1414

Points are real observations. Gaps are gaps — nothing is interpolated.

Showing 1 model.

Source: LMArena
View data
MeasuredHuman preference (Elo)
2026-08-121413
2026-08-191413
2026-08-211413
2026-08-271413
2026-09-011413
2026-09-131415
2026-09-251414
2026-09-301414
2026-10-021414
2026-10-081414
2026-10-131414
2026-10-151414