Back

SpaceXSI

Grok 4 Fast

Closed weightsModels.dev
Intelligence
11.1
Rank 403 of 747 measured models
Price/1M
$0.275
Rank 201 of 664 measured models
Context window
2M
Rank 8 of 1207 measured models

Grok 4 Fast (Non-reasoning) scores 11.1 on the Artificial Analysis Intelligence Index, ranking 403rd of 747 measured models. The closest models on this index are GLM-4.5-Air (11.1), Granite 4.2 8B (11.1), and Ling 3.0 Tiny (11.1). At $0.275 per million tokens (3:1 input/output blended price), it is cheaper than GLM-4.5-Air ($0.372), more expensive than Granite 4.2 8B ($0.107).

Artificial Analysis Indices
Non-reasoning
Intelligence11.1
Rank 403 of 747 measured models
Math41.3
Rank 153 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 Pro73.0%
Rank 200 of 349 measured models
GPQA Diamond60.6%
Rank 401 of 620 measured models
HLE4.5%
Rank 524 of 667 measured models
LiveCodeBench40.1%
Rank 181 of 343 measured models
AIME 202541.3%
Rank 153 of 270 measured models
IFBench37.7%
Rank 306 of 450 measured models
AA-LCR24.0%
Rank 433 of 578 measured models
TerminalBench Hard12.1%
Rank 223 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