Buttocks-7B-v1.0: benchmark results

An experimental release by TeeZee recreating the Toppy-M-7B recipe with MergeMonster and an extended RPG preset, using SLERP for the final merge. The two versions retain different merge methods. Provider: TeeZee. Access: Open.

Aggregate Rating 1310 ± 35, rank #8537 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - ARC Challenge54.61Normalized accuracy (%) (25-shot)31.7
Open LLM Leaderboard v1 - MMLU50.22Accuracy (%) (5-shot)29.5
Open LLM Leaderboard v1 - TruthfulQA MC244.72MC2 (%) (0-shot)28.2
Open LLM Leaderboard v1 - HellaSwag75.61Normalized accuracy (%) (10-shot)26.9
Open LLM Leaderboard v1 - GSM8K5.76Accuracy (%) (5-shot)24.7
Open LLM Leaderboard v1 - WinoGrande68.9Accuracy (%) (5-shot)23

Interactive version: theaggregate.ai/model?slug=buttocks-7b-v1-0 · How It Works · Data refreshed daily, snapshot 2026-11-08.