Model Comparator

Compare up to four models using the same criteria.

Claude Opus 5.5 (Low, Default Fallback)
Anthropic
DeepSeek V4 Flash 0731 (Max)
DeepSeek

Differences only

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

Model Comparator
Metrics	Claude Opus 5.5 (Low, Default Fallback) Anthropic	DeepSeek V4 Flash 0731 (Max) DeepSeek
Intelligence	Best: 34.8	34.3
Coding	—	69.1
Agentic	—	41
Speed	71.9 t/s	Best: 129 t/s
TTFT	10.5 s	Best: 1.6 s
Input · $ / 1M tokens	$4×28.6 relative to the lowest price among the compared models	Best: $0.14
Output · $ / 1M tokens	$20×71.4 relative to the lowest price among the compared models	Best: $0.28
Context window	1M	1M
Reasoning	Yes	Yes
Open weights	No	Yes
Cost / task	$0.976×5.5 relative to the lowest price among the compared models	Best: $0.178

Intelligence

Claude Opus 5.5 (Low, Default Fallback): Best: 34.8
DeepSeek V4 Flash 0731 (Max): 34.3

Coding

Claude Opus 5.5 (Low, Default Fallback): —
DeepSeek V4 Flash 0731 (Max): 69.1

Agentic

Claude Opus 5.5 (Low, Default Fallback): —
DeepSeek V4 Flash 0731 (Max): 41

Speed

Claude Opus 5.5 (Low, Default Fallback): 71.9 t/s
DeepSeek V4 Flash 0731 (Max): Best: 129 t/s

TTFT

Claude Opus 5.5 (Low, Default Fallback): 10.5 s
DeepSeek V4 Flash 0731 (Max): Best: 1.6 s

Input · $ / 1M tokens

Claude Opus 5.5 (Low, Default Fallback): $4×28.6 relative to the lowest price among the compared models
DeepSeek V4 Flash 0731 (Max): Best: $0.14

Output · $ / 1M tokens

Claude Opus 5.5 (Low, Default Fallback): $20×71.4 relative to the lowest price among the compared models
DeepSeek V4 Flash 0731 (Max): Best: $0.28

Context window

Claude Opus 5.5 (Low, Default Fallback): 1M
DeepSeek V4 Flash 0731 (Max): 1M

Reasoning

Claude Opus 5.5 (Low, Default Fallback): Yes
DeepSeek V4 Flash 0731 (Max): Yes

Open weights

Claude Opus 5.5 (Low, Default Fallback): No
DeepSeek V4 Flash 0731 (Max): Yes

Cost / task

Claude Opus 5.5 (Low, Default Fallback): $0.976×5.5 relative to the lowest price among the compared models
DeepSeek V4 Flash 0731 (Max): Best: $0.178

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 5.5 (Low, Default Fallback)34.8 · $0.976
DeepSeek V4 Flash 0731 (Max)34.3 · $0.178