Finding the Right Fit - Terminal-Bench 4 (63 Tasks, OpenHands): leaderboard
Metric: Task score (%), OpenHands harness, high reasoning effort, one run per task over 63 tasks. Source: huggingface.co. Saturation forecast: Around April 2027. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5 (High) | 57.14 |
| 2 | GPT-6 Astra (High) | 49.21 |
| 3 | GLM-5.3 (High) | 41.27 |
| 4 | Kimi K3 (High) | 11.11 |
| 5 | DeepSeek V4 Pro (High) | 3.17 |
Interactive version: theaggregate.ai/benchmark?slug=finding-the-right-fit-terminal-bench-4-63-tasks-openhands · How It Works · Data refreshed daily, snapshot 2026-10-05.