Cydonia-24B-v4.1: benchmark results

Provider: Other. Released 2025-08-17. Access: Open.

Unified ELO 1620 ± 46, rank #552 of 2656 rated models, from 10 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
UGI Leaderboard47.31UGI Score84.2
FMNB Leaderboard93Score81.2
UGI - Willingness (W/10)7.5W/10 Score77.9
UGI - Writing40.76Writing Score75.5
SnakeBench23TrueSkill Rating53.3
UGI - Natural Intelligence21.56NatInt Score48.7
Tinybird AI SQL Benchmark - Exactness45.68Result exactness vs human reference queries (0-100)38.7
Tinybird AI SQL Benchmark - Success Rate98Questions answered with a valid query within 3 retries (%)35.5
Tinybird AI SQL Benchmark - First-Attempt Success Rate88Questions answered with a valid query on the first attempt (29.5
Fucc Boi Bench7.47Average Fuccboi Score (0-10, lower is better)2.5

Interactive version: theaggregate.ai/model?slug=cydonia-24b-v4-1 · How It Works · Data refreshed daily, snapshot 2026-09-19.