Open_Gpt4.8x7B_v0.2: benchmark results
A Mixtral-family TIES merge by rombodawg of Mixtral-8x7B-Instruct-v0.1 and bagel-dpo-8x7b-v0.2 against MixtralOrochi8x7B. Provider: rombodawg. Access: Open.
Aggregate Rating 1476 ± 34, rank #2724 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 72.07 | Accuracy (%) (5-shot) | 95.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 71.92 | MC2 (%) (0-shot) | 92.6 |
| Open LLM Leaderboard v1 - WinoGrande | 83.58 | Accuracy (%) (5-shot) | 89.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 68.69 | Normalized accuracy (%) (25-shot) | 81 |
| Open LLM Leaderboard v1 - HellaSwag | 86.16 | Normalized accuracy (%) (10-shot) | 79.1 |
| Open LLM Leaderboard v1 - GSM8K | 59.14 | Accuracy (%) (5-shot) | 70.8 |
Interactive version: theaggregate.ai/model?slug=open-gpt4-8x7b-v0-2 · How It Works · Data refreshed daily, snapshot 2026-11-08.