Model Comparator

Compare up to four models using the same criteria.

Claude Opus 4.5 (Non-reasoning)
Anthropic
GPT-5.1 Codex (High)
OpenAI

Differences only

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

Model Comparator
Metrics	Claude Opus 4.5 (Non-reasoning) Anthropic	GPT-5.1 Codex (High) OpenAI
Intelligence	23.7	23.7
Math	62.7	Best: 95.7
Speed	46.1 t/s	Best: 126 t/s
TTFT	Best: 1.18 s	7.22 s
Input · $ / 1M tokens	$5×4 relative to the lowest price among the compared models	Best: $1.25
Output · $ / 1M tokens	$25×2.5 relative to the lowest price among the compared models	Best: $10
Context window	200K	Best: 400K
Reasoning	No	Yes
Open weights	No	No

Intelligence

Claude Opus 4.5 (Non-reasoning): 23.7
GPT-5.1 Codex (High): 23.7

Math

Claude Opus 4.5 (Non-reasoning): 62.7
GPT-5.1 Codex (High): Best: 95.7

Speed

Claude Opus 4.5 (Non-reasoning): 46.1 t/s
GPT-5.1 Codex (High): Best: 126 t/s

TTFT

Claude Opus 4.5 (Non-reasoning): Best: 1.18 s
GPT-5.1 Codex (High): 7.22 s

Input · $ / 1M tokens

Claude Opus 4.5 (Non-reasoning): $5×4 relative to the lowest price among the compared models
GPT-5.1 Codex (High): Best: $1.25

Output · $ / 1M tokens

Claude Opus 4.5 (Non-reasoning): $25×2.5 relative to the lowest price among the compared models
GPT-5.1 Codex (High): Best: $10

Context window

Claude Opus 4.5 (Non-reasoning): 200K
GPT-5.1 Codex (High): Best: 400K

Reasoning

Claude Opus 4.5 (Non-reasoning): No
GPT-5.1 Codex (High): Yes

Open weights

Claude Opus 4.5 (Non-reasoning): No
GPT-5.1 Codex (High): 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.

Claude Opus 4.5 (Non-reasoning)23.7 · $10
GPT-5.1 Codex (High)23.7 · $3.44