Model Comparator

Compare up to four models using the same criteria.

Kimi K2.5 (Non-reasoning)
Moonshot AI
Claude 4.5 Sonnet (Non-reasoning)
Anthropic

Differences only

✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.

Model Comparator
Metrics	Kimi K2.5 (Non-reasoning) Moonshot AI	Claude 4.5 Sonnet (Non-reasoning) Anthropic
Intelligence	Best: 19.4	19.3
Coding	—	52.1
Math	—	37
Agentic	—	15.8
Speed	Best: 57.4 t/s	41.3 t/s
TTFT	2.49 s	Best: 1.09 s
Input · $ / 1M tokens	Best: $0.60	$3×5 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $3	$15×5 relative to the lowest price among the compared models
Context window	256K	Best: 1M
Reasoning	No	No
Open weights	Yes	No

Intelligence

Kimi K2.5 (Non-reasoning): Best: 19.4
Claude 4.5 Sonnet (Non-reasoning): 19.3

Coding

Kimi K2.5 (Non-reasoning): —
Claude 4.5 Sonnet (Non-reasoning): 52.1

Math

Kimi K2.5 (Non-reasoning): —
Claude 4.5 Sonnet (Non-reasoning): 37

Agentic

Kimi K2.5 (Non-reasoning): —
Claude 4.5 Sonnet (Non-reasoning): 15.8

Speed

Kimi K2.5 (Non-reasoning): Best: 57.4 t/s
Claude 4.5 Sonnet (Non-reasoning): 41.3 t/s

TTFT

Kimi K2.5 (Non-reasoning): 2.49 s
Claude 4.5 Sonnet (Non-reasoning): Best: 1.09 s

Input · $ / 1M tokens

Kimi K2.5 (Non-reasoning): Best: $0.60
Claude 4.5 Sonnet (Non-reasoning): $3×5 relative to the lowest price among the compared models

Output · $ / 1M tokens

Kimi K2.5 (Non-reasoning): Best: $3
Claude 4.5 Sonnet (Non-reasoning): $15×5 relative to the lowest price among the compared models

Context window

Kimi K2.5 (Non-reasoning): 256K
Claude 4.5 Sonnet (Non-reasoning): Best: 1M

Reasoning

Kimi K2.5 (Non-reasoning): No
Claude 4.5 Sonnet (Non-reasoning): No

Open weights

Kimi K2.5 (Non-reasoning): Yes
Claude 4.5 Sonnet (Non-reasoning): No

Each reasoning level remains a separate configuration.

Score and cost

Each line joins the reasoning levels of a compared model; the large point marks the configuration in the table. The top-right corner holds the best score for the lowest cost. Select another point to compare that level.

Kimi K2.5 (Non-reasoning)19.4 · $1.20
Claude 4.5 Sonnet (Non-reasoning)19.3 · $6