Back

SpaceXSI

Grok 3 mini Reasoning (High)

ReasoningClosed weights
Intelligence
14.6
Rank 315 of 744 measured models
Output speed
65.3 t/s
Rank 263 of 403 measured models
Price/1M
$0.35
Rank 221 of 659 measured models
Context window
1M
Rank 84 of 1199 measured models

Grok 3 mini Reasoning (High) scores 14.6 on the Artificial Analysis Intelligence Index, ranking 315th of 744 measured models. The closest models on this index are Gemma 4 31B (14.7), DeepSeek V3.2 Speciale (14.5), and Gemini 2.5 Pro Preview (May' 25) (14.5). At $0.35 per million tokens (3:1 input/output blended price), it is cheaper than Gemini 2.5 Pro Preview (May' 25) ($3.44). With an output speed of 65.3 t/s, it is faster than Gemma 4 31B (35.5 t/s).

Artificial Analysis Indices
Intelligence14.6
Rank 315 of 744 measured models
Math84.7
Rank 48 of 270 measured models
Standard Benchmarks
MMLU Pro82.8%
Rank 64 of 349 measured models
GPQA Diamond79.1%
Rank 215 of 619 measured models
HLE11.0%
Rank 313 of 664 measured models
LiveCodeBench69.6%
Rank 71 of 343 measured models
MATH-50099.2%
Rank 2 of 202 measured models
AIME 202493.3%
Rank 5 of 194 measured models
AIME 202584.7%
Rank 48 of 270 measured models
IFBench45.9%
Rank 209 of 450 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