Model Comparator

Compare up to four models using the same criteria.

Claude Sonnet 5.5 (Low, Default Fallback)
Anthropic
K2 Horizon MoVA 36B A4B
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 5.5 (Low, Default Fallback) Anthropic	K2 Horizon MoVA 36B A4B Institute of Foundation Models
Intelligence	Best: 25.6	25.3
Agentic	—	33.5
Speed	92.7 t/s	—
TTFT	1.27 s	—
Input · $ / 1M tokens	$2	—
Output · $ / 1M tokens	$10	—
Context window	Best: 1M	524K
Reasoning	Yes	Yes
Open weights	No	Yes
Cost / task	$0.511	—

Intelligence

Claude Sonnet 5.5 (Low, Default Fallback): Best: 25.6
K2 Horizon MoVA 36B A4B: 25.3

Agentic

Claude Sonnet 5.5 (Low, Default Fallback): —
K2 Horizon MoVA 36B A4B: 33.5

Speed

Claude Sonnet 5.5 (Low, Default Fallback): 92.7 t/s
K2 Horizon MoVA 36B A4B: —

TTFT

Claude Sonnet 5.5 (Low, Default Fallback): 1.27 s
K2 Horizon MoVA 36B A4B: —

Input · $ / 1M tokens

Claude Sonnet 5.5 (Low, Default Fallback): $2
K2 Horizon MoVA 36B A4B: —

Output · $ / 1M tokens

Claude Sonnet 5.5 (Low, Default Fallback): $10
K2 Horizon MoVA 36B A4B: —

Context window

Claude Sonnet 5.5 (Low, Default Fallback): Best: 1M
K2 Horizon MoVA 36B A4B: 524K

Reasoning

Claude Sonnet 5.5 (Low, Default Fallback): Yes
K2 Horizon MoVA 36B A4B: Yes

Open weights

Claude Sonnet 5.5 (Low, Default Fallback): No
K2 Horizon MoVA 36B A4B: Yes

Cost / task

Claude Sonnet 5.5 (Low, Default Fallback): $0.511
K2 Horizon MoVA 36B A4B: —

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 5.5 (Low, Default Fallback)25.6 · $0.511

Not plotted for lack of data on these axes: K2 Horizon MoVA 36B A4B.