Dusk_Rainbow — benchmark results
SicariusSicariiStuff's low-censorship Llama-3-8B storytelling fine-tune of Invisietch's EtherealRainbow-v0.3, trained on human-written creative data. Provider: Other. Released 2024-08-16. Access: Open.
Unified ELO 1418 ± 39, rank #1140 of 1776 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI - Willingness (W/10) | 7.2 | W/10 Score | 73.6 |
| Open LLM Leaderboard - GPQA | 7.83 | Score | 66.2 |
| UGI Leaderboard | 35.05 | UGI Score | 52.1 |
| Open LLM Leaderboard - MMLU-Pro | 27.15 | Score | 49.8 |
| Open LLM Leaderboard - BBH | 25.96 | Score | 40.2 |
| Open LLM Leaderboard - MATH Level 5 | 7.48 | Score | 39.1 |
| Open LLM Leaderboard - MuSR | 7.45 | Score | 34.7 |
| Open LLM Leaderboard - IFEval | 35.88 | Score | 34.3 |
| UGI - Natural Intelligence | 13.01 | NatInt Score | 11.7 |
| UGI - Writing | 11.67 | Writing Score | 2.9 |
Interactive version: theaggregate.ai/model?slug=dusk-rainbow · How the rankings work · Data refreshed daily, snapshot 2026-07-22.