WhatsMyLLM 中文

Models · Claude

Claude Haiku 4.5

Asked for a few hundred random integers, Claude Haiku 4.5 does not pick evenly. This page is the shape of that preference, built from 36 recorded answers containing 9994 numbers, and it is what the identify tool compares a pasted reply against.

Check a chat that claims to be Claude Haiku 4.5

Bank id
claude-haiku-4-5-20251001
Family
Claude
Collected through
API
Collected on
Not recorded upstream
Status
Inherited from ModelTrace; serving identity not independently verified
Distinct values used
354 of 355
Prompt environments
12 of 12

Capability and price

Sold by
Anthropic
Intelligence index
15 · v4.3.2, scored as non-reasoning
Index rank
12 of 12
Input, per 1M tokens
1.00
Output, per 1M tokens
5.00
Blended, per 1M tokens
2.00
Price rank
5 of 12
Context window
200,000 tokens

Read on 2026-10-02, not measured here: index page · price page

Distribution

Claude Haiku 4.50.8%

Selected number 267

ModelTimes chosenShare
Claude Haiku 4.5700.70%
Each bar shows a number’s share of all recorded choices. Both models use the same percentage scale. Tap the chart or enter a number for exact counts. These are recorded preferences, not a measure of intelligence or proof of identity.

Favourite numbers

NumberTimes chosenShare
267700.70%
289700.70%
189600.60%
74580.58%
69570.57%
135550.55%
298540.54%
72530.53%
87520.52%
61510.51%
312510.51%
251500.50%

How reliably it is recognised

In held-out testing across all twelve prompt environments, 12 of 12 three-answer runs named this model with a clear margin, 0 were close calls inside its family, 0 had only a weak match, and 0 named a different model with a clear margin.

With this model removed from the bank and its own answers scored against the rest, 0 of 12 runs still named another model with a clear margin, 0 were close calls inside the family, and 12 had only a weak match. Its answers landed most often on Kimi K2.6 (5 of 12). That is the number to keep in mind if you are testing a version that is not listed here.

Both measurements count the status the site attaches to the first-ranked model, not the bare ranking alone. The methodology page explains how they were made and what they leave out.