Magnum-Picaro-0.7-v2-12B — benchmark results

Trappu's merge of the Nemo-Picaro storytelling tune with Magnum v2 12B, balancing narration with roleplay and general chat. Provider: Other. Released 2024-09-11. Access: Open.

Unified ELO 1484 ± 42, rank #863 of 1776 rated models, from 10 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard - MuSR19.56Score94
Open LLM Leaderboard - GPQA9.73Score77
Open LLM Leaderboard - BBH35.75Score72.5
Open LLM Leaderboard - MMLU-Pro28.67Score54.1
UGI - Writing34.37Writing Score53.4
Open LLM Leaderboard - MATH Level 56.65Score36
UGI - Natural Intelligence18.59NatInt Score35.4
UGI - Willingness (W/10)3.8W/10 Score27.8
Open LLM Leaderboard - IFEval30.03Score27.4
UGI Leaderboard28.57UGI Score27.4

Interactive version: theaggregate.ai/model?slug=magnum-picaro-0-7-v2-12b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.