2B-ad — benchmark results

SicariusSicariiStuff's Gemma 2 2B fine-tune geared toward roleplay and creative writing with reduced censorship. Provider: Other. Released 2024-08-26. Access: Open.

Unified ELO 1400 ± 25, rank #1227 of 1776 rated models, from 10 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
UGI - Willingness (W/10)5.8W/10 Score49.3
Open LLM Leaderboard - IFEval43.79Score46.9
Open LLM Leaderboard - MuSR8.12Score38.1
Open LLM Leaderboard - GPQA4.14Score36
Open LLM Leaderboard - MATH Level 55.06Score28.2
Open LLM Leaderboard - MMLU-Pro18.47Score28.1
Open LLM Leaderboard - BBH16.01Score24.4
UGI Leaderboard25.07UGI Score19.3
UGI - Writing19.59Writing Score12.6
UGI - Natural Intelligence9.71NatInt Score6.5

Interactive version: theaggregate.ai/model?slug=2b-ad · How the rankings work · Data refreshed daily, snapshot 2026-07-22.