Model Comparator

Compare up to four models using the same criteria.

Claude Sonnet 4.6 (Max)
Anthropic
K2 Horizon 375B A23B
Institute of Foundation Models

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 (Max) Anthropic	K2 Horizon 375B A23B Institute of Foundation Models
Intelligence	30.1	Best: 30.5
Coding	Best: 63	61.5
Agentic	31.8	Best: 40
Speed	51.8 t/s	Best: 837 t/s
TTFT	79.6 s	Best: 2.56 s
Input · $ / 1M tokens	$3	—
Output · $ / 1M tokens	$15	—
Context window	Best: 1M	524K
Reasoning	Yes	Yes
Open weights	No	Yes
Cost / task	$2.49	Best: $0

Intelligence

Claude Sonnet 4.6 (Max): 30.1
K2 Horizon 375B A23B: Best: 30.5

Coding

Claude Sonnet 4.6 (Max): Best: 63
K2 Horizon 375B A23B: 61.5

Agentic

Claude Sonnet 4.6 (Max): 31.8
K2 Horizon 375B A23B: Best: 40

Speed

Claude Sonnet 4.6 (Max): 51.8 t/s
K2 Horizon 375B A23B: Best: 837 t/s

TTFT

Claude Sonnet 4.6 (Max): 79.6 s
K2 Horizon 375B A23B: Best: 2.56 s

Input · $ / 1M tokens

Claude Sonnet 4.6 (Max): $3
K2 Horizon 375B A23B: —

Output · $ / 1M tokens

Claude Sonnet 4.6 (Max): $15
K2 Horizon 375B A23B: —

Context window

Claude Sonnet 4.6 (Max): Best: 1M
K2 Horizon 375B A23B: 524K

Reasoning

Claude Sonnet 4.6 (Max): Yes
K2 Horizon 375B A23B: Yes

Open weights

Claude Sonnet 4.6 (Max): No
K2 Horizon 375B A23B: Yes

Cost / task

Claude Sonnet 4.6 (Max): $2.49
K2 Horizon 375B A23B: Best: $0

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 (Max)30.1 · $2.49
K2 Horizon 375B A23B30.5 · $0