Model Comparator

Compare up to four models using the same criteria.

GPT-6 Sol (High)
OpenAI
Claude Haiku 5.5 (Max)
Anthropic

Differences only

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

Model Comparator
Metrics	GPT-6 Sol (High) OpenAI	Claude Haiku 5.5 (Max) Anthropic
Intelligence	42.4	Best: 43.4
Speed	87.1 t/s	Best: 236 t/s
TTFT	Best: 21.5 s	337 s
Input · $ / 1M tokens	$2×20 relative to the lowest price among the compared models	Best: $0.10
Output · $ / 1M tokens	$10×20 relative to the lowest price among the compared models	Best: $0.50
Context window	Best: 1.1M	1M
Reasoning	Yes	Yes
Open weights	No	No
Cost / task	$0.373×1.8 relative to the lowest price among the compared models	Best: $0.213

Intelligence

GPT-6 Sol (High): 42.4
Claude Haiku 5.5 (Max): Best: 43.4

Speed

GPT-6 Sol (High): 87.1 t/s
Claude Haiku 5.5 (Max): Best: 236 t/s

TTFT

GPT-6 Sol (High): Best: 21.5 s
Claude Haiku 5.5 (Max): 337 s

Input · $ / 1M tokens

GPT-6 Sol (High): $2×20 relative to the lowest price among the compared models
Claude Haiku 5.5 (Max): Best: $0.10

Output · $ / 1M tokens

GPT-6 Sol (High): $10×20 relative to the lowest price among the compared models
Claude Haiku 5.5 (Max): Best: $0.50

Context window

GPT-6 Sol (High): Best: 1.1M
Claude Haiku 5.5 (Max): 1M

Reasoning

GPT-6 Sol (High): Yes
Claude Haiku 5.5 (Max): Yes

Open weights

GPT-6 Sol (High): No
Claude Haiku 5.5 (Max): No

Cost / task

GPT-6 Sol (High): $0.373×1.8 relative to the lowest price among the compared models
Claude Haiku 5.5 (Max): Best: $0.213

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-6 Sol (High)42.4 · $0.373
Claude Haiku 5.5 (Max)43.4 · $0.213