SMaxxxer-v1-70B: benchmark results
ChuckMcSneed's TIES merge using lizpreciatior/lzlv_70b_fp16_hf as its base, with jondurbin/spicyboros-70b-2.2, Xwin-LM/Xwin-LM-70B-V0.1 and cognitivecomputations/dolphin-2.2-70b as additional inputs. It is distinct from the complementary Maxxxer release and their larger BenchmaxxxerPS layer merge. Provider: ChuckMcSneed. Access: Open.
Aggregate Rating 1472 ± 33, rank #2803 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 70.55 | Accuracy (%) (5-shot) | 94.1 |
| Open LLM Leaderboard v1 - HellaSwag | 88.02 | Normalized accuracy (%) (10-shot) | 89.2 |
| Open LLM Leaderboard v1 - ARC Challenge | 70.65 | Normalized accuracy (%) (25-shot) | 86.6 |
| Open LLM Leaderboard v1 - WinoGrande | 82.87 | Accuracy (%) (5-shot) | 86 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 60.7 | MC2 (%) (0-shot) | 76.4 |
| Open LLM Leaderboard v1 - GSM8K | 60.58 | Accuracy (%) (5-shot) | 72.7 |
Interactive version: theaggregate.ai/model?slug=smaxxxer-v1-70b · How It Works · Data refreshed daily, snapshot 2026-11-08.