Model Comparator

Compare up to four models using the same criteria.

K2 Horizon 375B A23B
Institute of Foundation Models
Qwen3.6 35B A3B (Reasoning)
Alibaba

Differences only

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

Model Comparator
Metrics	K2 Horizon 375B A23B Institute of Foundation Models	Qwen3.6 35B A3B (Reasoning) Alibaba
Intelligence	17.8	Best: 18.2
Coding	Best: 61.5	41.9
Agentic	Best: 40	13.1
Speed	96.1 t/s	Best: 122 t/s
TTFT	13.4 s	Best: 2.08 s
Input · $ / 1M tokens	—	$0.375
Output · $ / 1M tokens	—	$2.25
Context window	Best: 524K	262K
Reasoning	Yes	Yes
Open weights	Yes	Yes
Cost / task	Best: $0	$0.475

Intelligence

K2 Horizon 375B A23B: 17.8
Qwen3.6 35B A3B (Reasoning): Best: 18.2

Coding

K2 Horizon 375B A23B: Best: 61.5
Qwen3.6 35B A3B (Reasoning): 41.9

Agentic

K2 Horizon 375B A23B: Best: 40
Qwen3.6 35B A3B (Reasoning): 13.1

Speed

K2 Horizon 375B A23B: 96.1 t/s
Qwen3.6 35B A3B (Reasoning): Best: 122 t/s

TTFT

K2 Horizon 375B A23B: 13.4 s
Qwen3.6 35B A3B (Reasoning): Best: 2.08 s

Input · $ / 1M tokens

K2 Horizon 375B A23B: —
Qwen3.6 35B A3B (Reasoning): $0.375

Output · $ / 1M tokens

K2 Horizon 375B A23B: —
Qwen3.6 35B A3B (Reasoning): $2.25

Context window

K2 Horizon 375B A23B: Best: 524K
Qwen3.6 35B A3B (Reasoning): 262K

Reasoning

K2 Horizon 375B A23B: Yes
Qwen3.6 35B A3B (Reasoning): Yes

Open weights

K2 Horizon 375B A23B: Yes
Qwen3.6 35B A3B (Reasoning): Yes

Cost / task

K2 Horizon 375B A23B: Best: $0
Qwen3.6 35B A3B (Reasoning): $0.475

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.

K2 Horizon 375B A23B17.8 · $0
Qwen3.6 35B A3B (Reasoning)18.2 · $0.475