Model Comparator

Compare up to four models using the same criteria.

Claude Opus 4.7 (Max)
Anthropic
Qwen3.8 Max
Alibaba

Differences only

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

Model Comparator
Metrics	Claude Opus 4.7 (Max) Anthropic	Qwen3.8 Max Alibaba
Intelligence	Best: 40.7	40.2
Coding	Best: 73.6	71.8
Agentic	38.6	Best: 49.1
Speed	Best: 61.4 t/s	39.5 t/s
TTFT	20.1 s	Best: 2.75 s
Input · $ / 1M tokens	$5×2.5 relative to the lowest price among the compared models	Best: $2
Output · $ / 1M tokens	$25×4.2 relative to the lowest price among the compared models	Best: $6
Context window	1M	1M
Reasoning	Yes	Yes
Open weights	No	No
Cost / task	—	$2.67

Intelligence

Claude Opus 4.7 (Max): Best: 40.7
Qwen3.8 Max: 40.2

Coding

Claude Opus 4.7 (Max): Best: 73.6
Qwen3.8 Max: 71.8

Agentic

Claude Opus 4.7 (Max): 38.6
Qwen3.8 Max: Best: 49.1

Speed

Claude Opus 4.7 (Max): Best: 61.4 t/s
Qwen3.8 Max: 39.5 t/s

TTFT

Claude Opus 4.7 (Max): 20.1 s
Qwen3.8 Max: Best: 2.75 s

Input · $ / 1M tokens

Claude Opus 4.7 (Max): $5×2.5 relative to the lowest price among the compared models
Qwen3.8 Max: Best: $2

Output · $ / 1M tokens

Claude Opus 4.7 (Max): $25×4.2 relative to the lowest price among the compared models
Qwen3.8 Max: Best: $6

Context window

Claude Opus 4.7 (Max): 1M
Qwen3.8 Max: 1M

Reasoning

Claude Opus 4.7 (Max): Yes
Qwen3.8 Max: Yes

Open weights

Claude Opus 4.7 (Max): No
Qwen3.8 Max: No

Cost / task

Claude Opus 4.7 (Max): —
Qwen3.8 Max: $2.67

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 Opus 4.7 (Max)40.7 · $10
Qwen3.8 Max40.2 · $3