Model Comparator

Compare up to four models using the same criteria.

Claude 3.7 Sonnet (Reasoning)
Anthropic
Gemini 3 Flash Preview (Non-reasoning)
Google

Differences only

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

Model Comparator
Metrics	Claude 3.7 Sonnet (Reasoning) Anthropic	Gemini 3 Flash Preview (Non-reasoning) Google
Intelligence	17.7	Best: 17.9
Coding	36.4	—
Math	Best: 56.3	55.7
Speed	—	195 t/s
TTFT	—	0.86 s
Input · $ / 1M tokens	—	$0.50
Output · $ / 1M tokens	—	$3
Context window	200K	Best: 1M
Reasoning	Yes	No
Open weights	No	No

Intelligence

Claude 3.7 Sonnet (Reasoning): 17.7
Gemini 3 Flash Preview (Non-reasoning): Best: 17.9

Coding

Claude 3.7 Sonnet (Reasoning): 36.4
Gemini 3 Flash Preview (Non-reasoning): —

Math

Claude 3.7 Sonnet (Reasoning): Best: 56.3
Gemini 3 Flash Preview (Non-reasoning): 55.7

Speed

Claude 3.7 Sonnet (Reasoning): —
Gemini 3 Flash Preview (Non-reasoning): 195 t/s

TTFT

Claude 3.7 Sonnet (Reasoning): —
Gemini 3 Flash Preview (Non-reasoning): 0.86 s

Input · $ / 1M tokens

Claude 3.7 Sonnet (Reasoning): —
Gemini 3 Flash Preview (Non-reasoning): $0.50

Output · $ / 1M tokens

Claude 3.7 Sonnet (Reasoning): —
Gemini 3 Flash Preview (Non-reasoning): $3

Context window

Claude 3.7 Sonnet (Reasoning): 200K
Gemini 3 Flash Preview (Non-reasoning): Best: 1M

Reasoning

Claude 3.7 Sonnet (Reasoning): Yes
Gemini 3 Flash Preview (Non-reasoning): No

Open weights

Claude 3.7 Sonnet (Reasoning): No
Gemini 3 Flash Preview (Non-reasoning): No

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.

Gemini 3 Flash Preview (Non-reasoning)17.9 · $1.13

Not plotted for lack of data on these axes: Claude 3.7 Sonnet (Reasoning).