Herodotos-14B — benchmark results
Triangle104's community TIES merge of Qwen2.5 14B fine-tunes (Lumen, Coder 14B, DRT-o1). Provider: Other. Released 2025-01-13. Access: Open.
Unified ELO 1547 ± 43, rank #632 of 1776 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MATH Level 5 | 50.45 | Score | 97.2 |
| Open LLM Leaderboard - MuSR | 19.88 | Score | 94.7 |
| Open LLM Leaderboard - GPQA | 16.44 | Score | 93.2 |
| Open LLM Leaderboard - MMLU-Pro | 47.67 | Score | 92.4 |
| Open LLM Leaderboard - BBH | 48.91 | Score | 89.4 |
| UGI - Willingness (W/10) | 6 | W/10 Score | 53.7 |
| Open LLM Leaderboard - IFEval | 46.67 | Score | 53.2 |
| UGI Leaderboard | 33.6 | UGI Score | 46.5 |
| UGI - Writing | 26.22 | Writing Score | 25.9 |
| UGI - Natural Intelligence | 15.46 | NatInt Score | 20.9 |
Interactive version: theaggregate.ai/model?slug=herodotos-14b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.