Model Comparator

Compare up to four models using the same criteria.

Gemini 3.1 Flash-Lite
Google
K2 Horizon 3.7B
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	Gemini 3.1 Flash-Lite Google	K2 Horizon 3.7B Institute of Foundation Models
Intelligence	15.6	15.6
Coding	Best: 34.7	26.1
Agentic	1.6	Best: 16.5
Speed	342 t/s	—
TTFT	4.25 s	—
Input · $ / 1M tokens	$0.25	—
Output · $ / 1M tokens	$1.50	—
Context window	Best: 1M	524K
Reasoning	Yes	Yes
Open weights	No	Yes
Cost / task	$0.0602	—

Intelligence

Gemini 3.1 Flash-Lite: 15.6
K2 Horizon 3.7B: 15.6

Coding

Gemini 3.1 Flash-Lite: Best: 34.7
K2 Horizon 3.7B: 26.1

Agentic

Gemini 3.1 Flash-Lite: 1.6
K2 Horizon 3.7B: Best: 16.5

Speed

Gemini 3.1 Flash-Lite: 342 t/s
K2 Horizon 3.7B: —

TTFT

Gemini 3.1 Flash-Lite: 4.25 s
K2 Horizon 3.7B: —

Input · $ / 1M tokens

Gemini 3.1 Flash-Lite: $0.25
K2 Horizon 3.7B: —

Output · $ / 1M tokens

Gemini 3.1 Flash-Lite: $1.50
K2 Horizon 3.7B: —

Context window

Gemini 3.1 Flash-Lite: Best: 1M
K2 Horizon 3.7B: 524K

Reasoning

Gemini 3.1 Flash-Lite: Yes
K2 Horizon 3.7B: Yes

Open weights

Gemini 3.1 Flash-Lite: No
K2 Horizon 3.7B: Yes

Cost / task

Gemini 3.1 Flash-Lite: $0.0602
K2 Horizon 3.7B: —

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.

Gemini 3.1 Flash-Lite15.6 · $0.0602

Not plotted for lack of data on these axes: K2 Horizon 3.7B.