MODEL DIRECTORY
Follow the model.
See the evidence.
Benchmark results, evaluation settings and disclosed training methods—collected in one place for each model.
3,335 reported models and checkpoint variants. Scores keep their original units and sources.
71 models · page 2 of 2
xAI
Grok 4.5-high
1 benchmarks · 1 observations
Explore results →xAI
Grok 4.5-high-web-x-search†
1 benchmarks · 1 observations
Explore results →xAI
Grok 4.6 (Terminus 2)
1 benchmarks · 1 observations
Explore results →xAI
Grok 4.6 / Grok Build
1 benchmarks · 1 observations
Explore results →xAI
Grok 4.6-xhigh
1 benchmarks · 1 observations
Explore results →xAI
Grok 4.6-xhigh-web-x-search†
1 benchmarks · 1 observations
Explore results →xAI
Grok 4.7 (Terminus 2)
1 benchmarks · 1 observations
Explore results →xAI
Grok Build 0.1 (Grok Build)
1 benchmarks · 1 observations
Explore results →xAI
Grok Code Fast
1 benchmarks · 1 observations
Explore results →xAI
Grok Voice Transcribe 1.0
1 benchmarks · 1 observations
Explore results →xAI
Grok Voice Transcribe 2.0
1 benchmarks · 1 observations
Explore results →xAI
x-ai/grok-4.1-fast@reasoning=high
1 benchmarks · 4 observations
Explore results →xAI
x-ai/grok-4.1-fast@reasoning=none
1 benchmarks · 4 observations
Explore results →xAI
x-ai/grok-4.20-beta@reasoning=low
1 benchmarks · 4 observations
Explore results →xAI
x-ai/grok-4.20-beta@reasoning=xhigh
1 benchmarks · 4 observations
Explore results →xAI
x-ai/grok-4.20-multi-agent-beta@reasoning=low
1 benchmarks · 4 observations
Explore results →xAI
x-ai/grok-4.20-multi-agent-beta@reasoning=xhigh
1 benchmarks · 4 observations
Explore results →xAI
x-ai/grok-4.3@reasoning=minimal
1 benchmarks · 4 observations
Explore results →xAI
x-ai/grok-4.3@reasoning=xhigh
1 benchmarks · 4 observations
Explore results →xAI
x-ai/grok-4.5@reasoning=high
1 benchmarks · 4 observations
Explore results →xAI
x-ai/grok-4.5@reasoning=low
1 benchmarks · 4 observations
Explore results →xAI
x-ai/grok-4.6@reasoning=max
1 benchmarks · 4 observations
Explore results →xAI
x-ai/grok-4.6@reasoning=minimal
1 benchmarks · 4 observations
Explore results →