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...

Fibble2 Arena — leaderboard

Metric: Win Rate (%). Source: drchangliu.github.io. 46 models tracked.

Top models

#ModelScore
1Gemini 3.1 Pro (Preview)50
2Gemini 2.5 Pro25
3Kimi K2.58.57
4Llama33.03
5Gemma 3 27B2.7
6GPT-4o0
7GPT-4o Mini0
8GPT-50
9Claude Sonnet 4.50
10GPT-5 Mini0
11Llama 3.1 8B0
12Qwen 3 8B0
13Gemma 3 4B0
14Gemini 2.0 Flash0
15Claude Haiku 4.50

Interactive version: theaggregate.ai/benchmark?slug=fibble2-arena · 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.