Model Comparator

Compare up to four models using the same criteria.

Qwen3.8 27B (Xhigh)
Alibaba
GPT-5.1 Codex mini (High)
OpenAI

Differences only

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

Model Comparator
Metrics	Qwen3.8 27B (Xhigh) Alibaba	GPT-5.1 Codex mini (High) OpenAI
Intelligence	20.1	Best: 20.4
Coding	68.1	—
Math	—	91.7
Agentic	45.8	—
Cyber Index	12.7%	—
Speed	41.1 t/s	Best: 175 t/s
TTFT	Best: 3.99 s	19.2 s
Input · $ / 1M tokens	$0.50×2 relative to the lowest price among the compared models	Best: $0.25
Output · $ / 1M tokens	$3×1.5 relative to the lowest price among the compared models	Best: $2
Context window	256K	Best: 1M
Reasoning	Yes	Yes
Open weights	Yes	No
Cost / task	$3.53	—

Intelligence

Qwen3.8 27B (Xhigh): 20.1
GPT-5.1 Codex mini (High): Best: 20.4

Coding

Qwen3.8 27B (Xhigh): 68.1
GPT-5.1 Codex mini (High): —

Math

Qwen3.8 27B (Xhigh): —
GPT-5.1 Codex mini (High): 91.7

Agentic

Qwen3.8 27B (Xhigh): 45.8
GPT-5.1 Codex mini (High): —

Cyber Index

Qwen3.8 27B (Xhigh): 12.7%
GPT-5.1 Codex mini (High): —

Speed

Qwen3.8 27B (Xhigh): 41.1 t/s
GPT-5.1 Codex mini (High): Best: 175 t/s

TTFT

Qwen3.8 27B (Xhigh): Best: 3.99 s
GPT-5.1 Codex mini (High): 19.2 s

Input · $ / 1M tokens

Qwen3.8 27B (Xhigh): $0.50×2 relative to the lowest price among the compared models
GPT-5.1 Codex mini (High): Best: $0.25

Output · $ / 1M tokens

Qwen3.8 27B (Xhigh): $3×1.5 relative to the lowest price among the compared models
GPT-5.1 Codex mini (High): Best: $2

Context window

Qwen3.8 27B (Xhigh): 256K
GPT-5.1 Codex mini (High): Best: 1M

Reasoning

Qwen3.8 27B (Xhigh): Yes
GPT-5.1 Codex mini (High): Yes

Open weights

Qwen3.8 27B (Xhigh): Yes
GPT-5.1 Codex mini (High): No

Cost / task

Qwen3.8 27B (Xhigh): $3.53
GPT-5.1 Codex mini (High): —

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.

Qwen3.8 27B (Xhigh)20.1 · $1.13
GPT-5.1 Codex mini (High)20.4 · $0.688