youri-7B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1340 ± 20, rank #2537 of 2928 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| pfgen-bench - Completion Mode - Fluency | 0.65 | Fluency Score | 63.6 |
| pfgen-bench - Completion Mode - Truthfulness | 0.8 | Truthfulness Score | 63.3 |
| pfgen-bench - Completion Mode - Score | 0.53 | pfgen Score (mean of three) | 61.3 |
| pfgen-bench - Completion Mode - Helpfulness | 0.15 | Helpfulness Score | 56.4 |
| Open LLM Leaderboard v1 - GSM8K | 8.64 | Accuracy (%) (5-shot) | 28.9 |
| Open LLM Leaderboard v1 - WinoGrande | 71.82 | Accuracy (%) (5-shot) | 27.5 |
| Open LLM Leaderboard v1 - HellaSwag | 74.89 | Normalized accuracy (%) (10-shot) | 25.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 49.06 | Normalized accuracy (%) (25-shot) | 23.7 |
| Open LLM Leaderboard v1 - MMLU | 42.22 | Accuracy (%) (5-shot) | 22 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 36.03 | MC2 (%) (0-shot) | 3.1 |
Interactive version: theaggregate.ai/model?slug=youri-7b · How It Works · Data refreshed daily, snapshot 2026-09-23.