Back

Google

Gemini 3 Pro Preview

ReasoningClosed weights
Intelligence
28.0
Rank 144 of 744 measured models
Price/1M
$4.50
Rank 563 of 659 measured models
Context window
1M
Rank 84 of 1199 measured models

Gemini 3 Pro Preview (High) scores 28.0 on the Artificial Analysis Intelligence Index, ranking 144th of 744 measured models. The closest models on this index are Nex-N2-Pro (Based on Qwen3.5-397B-A17B) (28.2), Solar Pro 4 (28.2), and GLM-5 (27.9). At $4.50 per million tokens (3:1 input/output blended price), it is more expensive than Solar Pro 4 ($0.525) and GLM-5 ($1.55).

Artificial Analysis Indices
High
Intelligence28.0
Rank 144 of 744 measured models
Math95.7
Rank 7 of 270 measured models
Reasoning levels
Each point is a reasoning level of this model: more reasoning often raises the score but costs more. Select a point to open that level.
Intelligence Indexmost efficient ↗Price / 1M tokens
Standard Benchmarks
MMLU Pro89.8%
Rank 1 of 349 measured models
GPQA Diamond90.8%
Rank 57 of 619 measured models
HLE39.7%
Rank 86 of 664 measured models
LiveCodeBench91.7%
Rank 1 of 343 measured models
AIME 202595.7%
Rank 7 of 270 measured models
IFBench70.4%
Rank 68 of 450 measured models
AA-LCR76.0%
Rank 147 of 575 measured models
TerminalBench Hard41.7%
Rank 50 of 432 measured models
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy