bilingual-gpt-neox-4B-instruction-ppo: benchmark results
Provider: Other. Access: Open.
Unified ELO 1192 ± 20, rank #2911 of 2928 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| pfgen-bench - Completion Mode - Truthfulness | 0.77 | Truthfulness Score | 58.5 |
| pfgen-bench - Completion Mode - Score | 0.44 | pfgen Score (mean of three) | 43.1 |
| pfgen-bench - Completion Mode - Fluency | 0.49 | Fluency Score | 33.9 |
| pfgen-bench - Completion Mode - Helpfulness | 0.06 | Helpfulness Score | 28.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 43.5 | MC2 (%) (0-shot) | 23.7 |
| Open LLM Leaderboard v1 - HellaSwag | 47.9 | Normalized accuracy (%) (10-shot) | 9.8 |
| Open LLM Leaderboard v1 - ARC Challenge | 28.24 | Normalized accuracy (%) (25-shot) | 7.5 |
| Open LLM Leaderboard v1 - WinoGrande | 52.25 | Accuracy (%) (5-shot) | 6.6 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.6 |
| Open LLM Leaderboard v1 - MMLU | 23.12 | Accuracy (%) (5-shot) | 1 |
Interactive version: theaggregate.ai/model?slug=bilingual-gpt-neox-4b-instruction-ppo · How It Works · Data refreshed daily, snapshot 2026-09-23.