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...

Ducky Bench (Africa) — leaderboard

Metric: ELO. Source: ducky-bench.joinity.site. 14 models tracked.

Top models

#ModelScore
1DeepSeek R11267
2GPT-5 (High)1253
3Gemini 3 Pro1185
4Claude Opus 4.1 (Thinking)1150
5Gemini 2.5 Pro991
6O3 (High)962
7Grok 4874
8Claude Sonnet 4.5846
9GPT-4o839
10GPT-5 Mini (High)781
11Llama 4 Maverick641
12Kimi K2593

Interactive version: theaggregate.ai/benchmark?slug=ducky-bench-africa · 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.