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...

CodeGolf Bench — leaderboard

Metric: C++ Best %ile (self-reported). Source: benchmarklist.com. 9 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro (Preview 05-06)73.9
2Gemini 2.5 Flash (Preview 04-17)55.19
3Qwen 3 235B A22B48.24
4Llama 4 Maverick44.85
5DeepSeek R1 Distill Llama 70B44.18
6DeepSeek V3 (0324)38
7Gemma 3 27B20.92
8Llama 4 Scout16.65

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