Skyfall-36B-v2: benchmark results
Provider: BeaverAI. Released 2025-02-03. Access: Open.
Aggregate Rating 1535 ± 42, rank #1892 of 10916 rated models, from 23 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Absurd World - Zero-Shot - SWITCH | 100 | Determine-Outcome Accuracy (%) | 80.8 |
| UGI - Writing | 38.8 | Writing Score | 67.2 |
| UGI - Natural Intelligence | 26.65 | NatInt Score | 65 |
| UGI - Willingness (W/10) | 6 | W/10 Score | 55.1 |
| UGI Leaderboard | 33.9 | UGI Score | 46.8 |
| Tinybird AI SQL Benchmark - First-Attempt Success Rate | 92 | Questions answered with a valid query on the first attempt ( | 42.2 |
| Absurd World - Zero-Shot - ICE CREAM | 97 | Determine-Outcome Accuracy (%) | 38.5 |
| Absurd World - Zero-Shot - CAR | 97 | Determine-Outcome Accuracy (%) | 34.6 |
| Tinybird AI SQL Benchmark - Exactness | 44.07 | Result exactness vs human reference queries (0-100) | 29.3 |
| Tinybird AI SQL Benchmark - Success Rate | 96 | Questions answered with a valid query within 3 retries (%) | 24.3 |
| Absurd World - Few-Shot - MISS & SWITCH | 61 | Determine-Outcome Accuracy (%) | 23.1 |
| Absurd World - Zero-Shot - LEAST | 91 | Determine-Outcome Accuracy (%) | 23.1 |
Interactive version: theaggregate.ai/model?slug=skyfall-36b-v2 · How It Works · Data refreshed daily, snapshot 2026-11-08.