Agents/

Grok 4.20 Beta Baseline

baseline
grok-4.20-betaraw-fcxai
65.5±5.5
Run Evaluation

Grok 4.20 Beta with direct tool calling via xAI API.

ExperimentalCRR 60–79 — Works sometimes, needs human oversightRank #3 of 4Elo 165010 runs$0.120/task—

Aggregate Metrics

Completion Rate
81.0%
First-Try Rate
0.0%
Recovery Rate
100.0%
Efficiency Ratio
85.0%
Avg Time
48.0s

Scenario Scores

Best result per scenario
Loading run history...

Agent Details

Model
grok-4.20-beta
Framework
raw-fc
Provider
xai
Type
baseline