Model Comparator

Compare up to four models using the same criteria.

GPT-5.2 (Non-reasoning)
OpenAI
Claude 4.5 Haiku (Non-reasoning)
Anthropic

Differences only

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

Model Comparator
Metrics	GPT-5.2 (Non-reasoning) OpenAI	Claude 4.5 Haiku (Non-reasoning) Anthropic
Intelligence	Best: 17	16.9
Coding	—	43.9
Math	Best: 51	39
Agentic	—	8
Speed	62.2 t/s	Best: 81.9 t/s
TTFT	0.81 s	Best: 0.58 s
Input · $ / 1M tokens	$1.75×1.8 relative to the lowest price among the compared models	Best: $1
Output · $ / 1M tokens	$14×2.8 relative to the lowest price among the compared models	Best: $5
Context window	1M	1M
Reasoning	No	No
Open weights	No	No

Intelligence

GPT-5.2 (Non-reasoning): Best: 17
Claude 4.5 Haiku (Non-reasoning): 16.9

Coding

GPT-5.2 (Non-reasoning): —
Claude 4.5 Haiku (Non-reasoning): 43.9

Math

GPT-5.2 (Non-reasoning): Best: 51
Claude 4.5 Haiku (Non-reasoning): 39

Agentic

GPT-5.2 (Non-reasoning): —
Claude 4.5 Haiku (Non-reasoning): 8

Speed

GPT-5.2 (Non-reasoning): 62.2 t/s
Claude 4.5 Haiku (Non-reasoning): Best: 81.9 t/s

TTFT

GPT-5.2 (Non-reasoning): 0.81 s
Claude 4.5 Haiku (Non-reasoning): Best: 0.58 s

Input · $ / 1M tokens

GPT-5.2 (Non-reasoning): $1.75×1.8 relative to the lowest price among the compared models
Claude 4.5 Haiku (Non-reasoning): Best: $1

Output · $ / 1M tokens

GPT-5.2 (Non-reasoning): $14×2.8 relative to the lowest price among the compared models
Claude 4.5 Haiku (Non-reasoning): Best: $5

Context window

GPT-5.2 (Non-reasoning): 1M
Claude 4.5 Haiku (Non-reasoning): 1M

Reasoning

GPT-5.2 (Non-reasoning): No
Claude 4.5 Haiku (Non-reasoning): No

Open weights

GPT-5.2 (Non-reasoning): No
Claude 4.5 Haiku (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.

GPT-5.2 (Non-reasoning)17 · $4.81
Claude 4.5 Haiku (Non-reasoning)16.9 · $2