uitars-1.5-7B: benchmark results
Provider: ByteDance. Released 2025-04-16. Access: Open.
Unified ELO 1460 ± 1, rank #898 of 1392 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AI Chess Leaderboard (Continuation) | 442 | Elo | 23.1 |
| ScratchWorld - Compute | 0 | Success Rate (%) | 23.1 |
| ScratchWorld - Extend | 0 | Success Rate (%) | 23.1 |
| MobileGym-Bench | 13.8 | Success Rate (%) | 22.2 |
| Beyond Binary | 56.78 | NDCG@All (self-reported) | 15.4 |
| OSWorld | 29.6 | Success Rate (%) | 13.6 |
| GameWorld Computer-Use | 31.1 | Progress (%) | 12.5 |
| ScratchWorld - Create | 0 | Success Rate (%) | 7.7 |
| Kagi LLM Benchmark | 20.7 | Accuracy (%) | 4.6 |
| AI Chess Leaderboard (Reasoning) | 405 | Elo | 1.5 |
| ScratchWorld - Debug | 0 | Success Rate (%) | 0 |
| ScratchWorld - Overall | 0 | Success Rate (%) | 0 |
Interactive version: theaggregate.ai/model?slug=uitars-1-5-7b · How It Works · Data refreshed daily, snapshot 2026-09-05.