Anahata AGI-1 Suite

All Tests All Providers All Status Passed Failed Sort: Newest Sort: Oldest Sort: Score (High-Low) Sort: Score (Low-High) Sort: Duration (Fastest) Sort: Duration (Slowest) Sort: Total Tokens (Fewest) Sort: Total Tokens (Most) Sort: Reasoning Tokens (Most) Sort: Turns (Fewest) Reset

Recorded Runs

Click column headers to sort • Click row to expand telemetry

Anahata-AGI-1 Benchmark Challenges

Complete challenge prompts, sandbox toolkits, and permission policies evaluated across all candidate models.