Compare LLMs

1Grok 4.7
2Gemini 3.1 Pro

Drag a grip to reorder the columns, or press ← / → on a focused grip.2 / 5 models

Score items

7 / 7 selected

Click a score to show or hide its row; hover a table row to remove it.

Grok 4.7 is ~43% cheaper per blended million tokens.

DimensionGrok 4.7Gemini 3.1 Pro
GPQA Diamond—94.3%
HLE—44.4%
MathArena Apex—60.9%
Terminal-Bench 4.038%—
DeepSWE v1.171%—
HLE (w/tools)—51.4%
Automation-Bench—35.4%
Blended price$4.00 /1M$7.00 /1M
Full priceInput · Output · Cached input$2.00 · $6.00 · $0.500$2.00 · $12.00 · $0.200
Context window500K1,000K

What your usage would cost

Adjust the monthly volume — every model recomputes instantly.

Grok 4.7
$140/mo
Gemini 3.1 Pro
$200/mo

Estimates use list prices and ignore cached input, batch discounts, and off-peak rates.

Popular comparisons