ECE-TW3-JRGL-V1: benchmark results
paloalma's SLERP merge of Senku-70B and miqu-1-70b by ECE engineering students with TW3 Partners, aimed at EQ-Bench performance. Provider: ECE & TW3 Partners. Released 2024-04-03. Access: Open.
Aggregate Rating 1499 ± 22, rank #785 of 1656 rated models, from 20 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 85.24 | Accuracy (%) (5-shot) | 97.8 |
| Open LLM Leaderboard v1 - MMLU | 75.58 | Accuracy (%) (5-shot) | 97 |
| Open LLM Leaderboard v1 - ARC Challenge | 72.53 | Normalized accuracy (%) (25-shot) | 92.4 |
| Open LLM Leaderboard v1 - HellaSwag | 88.29 | Normalized accuracy (%) (10-shot) | 90.7 |
| Open LLM Leaderboard - MuSR | 46.21 | Score | 88.6 |
| Open LLM Leaderboard v1 - GSM8K | 69.14 | Accuracy (%) (5-shot) | 88.1 |
| Open LLM Leaderboard - GPQA | 34.73 | Score | 87.1 |
| Open LLM Leaderboard - BBH | 62.84 | Score | 86.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 65.89 | MC2 (%) (0-shot) | 84.3 |
| Open Chinese LLM - WinoGrande | 66.54 | Accuracy (%) | 79 |
| Open Chinese LLM - TruthfulQA MC | 58.62 | Accuracy (%) | 77.8 |
| Open LLM Leaderboard - MMLU-Pro | 42.21 | Score | 76.6 |
Interactive version: theaggregate.ai/model?slug=ece-tw3-jrgl-v1 · How It Works · Data refreshed daily, snapshot 2026-10-20.