Model Comparator

Compare up to four models using the same criteria.

Claude Sonnet 4.6 (Non-reasoning, High)
Anthropic
GPT-5 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 Sonnet 4.6 (Non-reasoning, High) Anthropic	GPT-5 Codex (High) OpenAI
Intelligence	24.7	Best: 24.9
Coding	63	—
Math	—	98.7
Agentic	31.8	—
Speed	45.2 t/s	Best: 166 t/s
TTFT	Best: 1.08 s	6.42 s
Input · $ / 1M tokens	$3×2.4 relative to the lowest price among the compared models	Best: $1.25
Output · $ / 1M tokens	$15×1.5 relative to the lowest price among the compared models	Best: $10
Context window	Best: 1M	400K
Reasoning	No	Yes
Open weights	No	No

Intelligence

Claude Sonnet 4.6 (Non-reasoning, High): 24.7
GPT-5 Codex (High): Best: 24.9

Coding

Claude Sonnet 4.6 (Non-reasoning, High): 63
GPT-5 Codex (High): —

Math

Claude Sonnet 4.6 (Non-reasoning, High): —
GPT-5 Codex (High): 98.7

Agentic

Claude Sonnet 4.6 (Non-reasoning, High): 31.8
GPT-5 Codex (High): —

Speed

Claude Sonnet 4.6 (Non-reasoning, High): 45.2 t/s
GPT-5 Codex (High): Best: 166 t/s

TTFT

Claude Sonnet 4.6 (Non-reasoning, High): Best: 1.08 s
GPT-5 Codex (High): 6.42 s

Input · $ / 1M tokens

Claude Sonnet 4.6 (Non-reasoning, High): $3×2.4 relative to the lowest price among the compared models
GPT-5 Codex (High): Best: $1.25

Output · $ / 1M tokens

Claude Sonnet 4.6 (Non-reasoning, High): $15×1.5 relative to the lowest price among the compared models
GPT-5 Codex (High): Best: $10

Context window

Claude Sonnet 4.6 (Non-reasoning, High): Best: 1M
GPT-5 Codex (High): 400K

Reasoning

Claude Sonnet 4.6 (Non-reasoning, High): No
GPT-5 Codex (High): Yes

Open weights

Claude Sonnet 4.6 (Non-reasoning, High): No
GPT-5 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 Sonnet 4.6 (Non-reasoning, High)24.7 · $6
GPT-5 Codex (High)24.9 · $3.44