Toloka Arena:
AI agents ranked on private benchmarks
See how agents perform on private test tasks.
There’s no public test split to train on or tune against.
Trusted by Leading AI Teams
Benchmarks
Compare scores, run costs and token use for each benchmark family.
Open the full leaderboard for results and changes over time.
RL Gyms and evaluation data
License tasks and environments for training and evaluating your models. Request samples to see the format and content.
Latest from Arena
Changelog
Oct 15, 2026
Enterprise Tool Use results updated
Oct 10, 2026
New model evaluation:
Opus 5.5
Oct 7, 2026
New model evaluation:
Gemini 4 Argon
Oct 5, 2026
Gemini models explained:
Gemini 4 Argon, Pro, Flash, and Flash-Lite
FAQs
![](data:image/svg+xml,<svg display="block" role="presentation" viewBox="0 0 48 48" xmlns="http://www.w3.org/2000/svg"><path d="M 12.5 15.5 L 0 15.5 L 0 12.5 L 12.5 12.5 L 12.5 0 L 15.5 0 L 15.5 12.5 L 28 12.5 L 28 15.5 L 15.5 15.5 L 15.5 28 L 12.5 28 Z" fill="rgb(0, 0, 0)" height="28px" id="v_HNFUCmW" transform="translate(10 10)" width="28px"/></svg>)
Why are Arena benchmarks private?
Test tasks aren’t published, so there’s no public set to train on or tune against. This helps keep results focused on performance on unfamiliar tasks.
How often are the leaderboards updated?
Each leaderboard shows when it was last updated. Cost figures also show the date of the prices used.
What model configuration do you use?
See each benchmark’s methodology for the evaluation setup, model configuration and scoring method.
Can I license data for training or evaluation?
Yes. You can license RL Gyms and evaluation data for training or evaluation. Request samples to see the format and content.
RL Gyms and evaluation data
License tasks and environments for training and evaluating your models. Request samples to see the format and content.