guanaco-33B-GPTQ: benchmark results
TheBloke's GPTQ publication of Guanaco 33B, whose original release is timdettmers/guanaco-33b-merged. Conversion publication is credited separately from the original model creator. Quantization method does not establish a single effective bit width or exact evaluated branch for this catalog row. Provider: TheBloke. Access: Open.
Aggregate Rating 1130 ± 16, rank #10319 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - TruthfulQA MC2 | 48.98 | Accuracy (%) | 71.5 |
| MMLU-by-task - College Physics | 28.43 | Accuracy (%) | 67.4 |
| Open LLM Leaderboard v1 - WinoGrande | 78.85 | Accuracy (%) (5-shot) | 65.9 |
| MMLU-by-task - Moral Scenarios | 28.04 | Accuracy (%) | 63 |
| MMLU-by-task - Abstract Algebra | 31 | Accuracy (%) | 60.2 |
| MMLU-by-task - High School Mathematics | 27.78 | Accuracy (%) | 58.6 |
| MMLU-by-task - Econometrics | 28.07 | Accuracy (%) | 47.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 48.98 | MC2 (%) (0-shot) | 43.4 |
| Open LLM Leaderboard v1 - GSM8K | 23.81 | Accuracy (%) (5-shot) | 43.2 |
| MMLU-by-task - Electrical Engineering | 31.03 | Accuracy (%) | 34.2 |
| MMLU-by-task - High School Statistics | 30.09 | Accuracy (%) | 31.8 |
| MMLU-by-task - Professional Psychology | 28.27 | Accuracy (%) | 31.6 |
Interactive version: theaggregate.ai/model?slug=guanaco-33b-gptq · How It Works · Data refreshed daily, snapshot 2026-11-08.