Skip to content

The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Guesswork Metrics
The Aggregate
Loading data...

UGI - Willingness (W/10) — leaderboard

Metric: W/10 Score. Source: huggingface.co. 1291 models tracked.

Top models

#ModelScore
1Tiger-Gemma-9B-v38.5
2zetasepic-abliteratedV2-Qwen2.5-32B-Inst-BaseMerge-TIES8.2
3Qwen2.5-14B-Instruct-abliterated-v28.2
4Qwen2.5-32B-Instruct-abliterated-v27.8
5Qwen 3 VL 4B Instruct7.8
6Mistral Large 2 (Nov) Instruct (2411)7.5
7Grok 4.20 0309 (Reasoning)7.5
8Dans-PersonalityEngine-V1.2.0-24B7.5
9Dobby-Mini-Unhinged-Llama-3.1-8B7.5
10L3-70B-Euryale-v2.17.5
11Tiger-Gemma-9B-v17.5
12Llama-3.1-Nemotron-lorablated-70B7.5
13SOLAR-10.7B-Instruct-v1.0-uncensored7.5
14jamba-large-1.77.2
15Ministral-3-14B-Reasoning-25127.2

Interactive version: theaggregate.ai/benchmark?slug=ugi-willingness-w-10 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.