Model Comparator

Compare up to four models using the same criteria.

GPT-5.6 Sol (High)
OpenAI
Claude Opus 4.8 (batch)
Anthropic

Differences only

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

Model Comparator
Metrics	GPT-5.6 Sol (High) OpenAI	Claude Opus 4.8 (batch) Anthropic
Intelligence	Best: 42.3	41.8
Coding	Best: 77.2	74.3
Agentic	Best: 44.2	41.9
Speed	81 t/s	—
TTFT	29.1 s	—
Input · $ / 1M tokens	$4	—
Output · $ / 1M tokens	$20	—
Context window	1M	1M
Reasoning	Yes	Yes
Open weights	No	—
Cost / task	$0.808	—

Intelligence

GPT-5.6 Sol (High): Best: 42.3
Claude Opus 4.8 (batch): 41.8

Coding

GPT-5.6 Sol (High): Best: 77.2
Claude Opus 4.8 (batch): 74.3

Agentic

GPT-5.6 Sol (High): Best: 44.2
Claude Opus 4.8 (batch): 41.9

Speed

GPT-5.6 Sol (High): 81 t/s
Claude Opus 4.8 (batch): —

TTFT

GPT-5.6 Sol (High): 29.1 s
Claude Opus 4.8 (batch): —

Input · $ / 1M tokens

GPT-5.6 Sol (High): $4
Claude Opus 4.8 (batch): —

Output · $ / 1M tokens

GPT-5.6 Sol (High): $20
Claude Opus 4.8 (batch): —

Context window

GPT-5.6 Sol (High): 1M
Claude Opus 4.8 (batch): 1M

Reasoning

GPT-5.6 Sol (High): Yes
Claude Opus 4.8 (batch): Yes

Open weights

GPT-5.6 Sol (High): No
Claude Opus 4.8 (batch): —

Cost / task

GPT-5.6 Sol (High): $0.808
Claude Opus 4.8 (batch): —

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-5.6 Sol (High)42.3 · $0.808

Not plotted for lack of data on these axes: Claude Opus 4.8 (batch).