vicuna-7B-chemical: benchmark results
An experimental chemistry fine-tune by FelixChao of CleverShovel/vicuna-7b-v1.3-sharded-bf16. The release card identifies the chemistry dataset and marks the model as under testing. Provider: FelixChao. Access: Open.
Aggregate Rating 1277 ± 35, rank #9007 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 51.7 | MC2 (%) (0-shot) | 52.9 |
| Open LLM Leaderboard v1 - HellaSwag | 74.42 | Normalized accuracy (%) (10-shot) | 24.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 49.83 | Normalized accuracy (%) (25-shot) | 24.3 |
| Open LLM Leaderboard v1 - MMLU | 44.1 | Accuracy (%) (5-shot) | 23.1 |
| Open LLM Leaderboard v1 - GSM8K | 3.34 | Accuracy (%) (5-shot) | 21.4 |
| Open LLM Leaderboard v1 - WinoGrande | 67.17 | Accuracy (%) (5-shot) | 21.2 |
Interactive version: theaggregate.ai/model?slug=vicuna-7b-chemical · How It Works · Data refreshed daily, snapshot 2026-11-08.