Model Comparator

Compare up to four models using the same criteria.

Qwen3.5 122B A10B (Reasoning)
Alibaba
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	Qwen3.5 122B A10B (Reasoning) Alibaba	K2 Horizon 375B A23B Institute of Foundation Models
Intelligence	17.7	Best: 17.8
Coding	45.7	Best: 61.5
Agentic	7.6	Best: 40
Speed	Best: 128 t/s	108 t/s
TTFT	Best: 2.3 s	2.74 s
Input · $ / 1M tokens	$0.40	—
Output · $ / 1M tokens	$3.20	—
Context window	Best: 1M	524K
Reasoning	Yes	Yes
Open weights	Yes	Yes
Cost / task	$0.325	Best: $0

Intelligence

Qwen3.5 122B A10B (Reasoning): 17.7
K2 Horizon 375B A23B: Best: 17.8

Coding

Qwen3.5 122B A10B (Reasoning): 45.7
K2 Horizon 375B A23B: Best: 61.5

Agentic

Qwen3.5 122B A10B (Reasoning): 7.6
K2 Horizon 375B A23B: Best: 40

Speed

Qwen3.5 122B A10B (Reasoning): Best: 128 t/s
K2 Horizon 375B A23B: 108 t/s

TTFT

Qwen3.5 122B A10B (Reasoning): Best: 2.3 s
K2 Horizon 375B A23B: 2.74 s

Input · $ / 1M tokens

Qwen3.5 122B A10B (Reasoning): $0.40
K2 Horizon 375B A23B: —

Output · $ / 1M tokens

Qwen3.5 122B A10B (Reasoning): $3.20
K2 Horizon 375B A23B: —

Context window

Qwen3.5 122B A10B (Reasoning): Best: 1M
K2 Horizon 375B A23B: 524K

Reasoning

Qwen3.5 122B A10B (Reasoning): Yes
K2 Horizon 375B A23B: Yes

Open weights

Qwen3.5 122B A10B (Reasoning): Yes
K2 Horizon 375B A23B: Yes

Cost / task

Qwen3.5 122B A10B (Reasoning): $0.325
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.

Qwen3.5 122B A10B (Reasoning)17.7 · $0.325
K2 Horizon 375B A23B17.8 · $0