scriptoriumadmin/OpenSpace
1
0
Fork 0
mirror of https://github.com/HKUDS/OpenSpace.git synced 2026-08-28 05:15:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

docs: add Terminal-Bench v2 results

Browse source
This commit is contained in:
spidercatfly 2026-07-17 13:26:14 +08:00
parent fadc4bccab
commit 2c5cc409b0
No known key found for this signature in database
2 changed files with 11 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
README.md
View file

@ -55,15 +55,15 @@ Your agent can already run tasks. But can it remember which skills worked? Can i
- **2026-07-17** 🚀 **OpenSpace v2 is released**: v2 turns OpenSpace into a quality-first Skill Hub with package-based skill browsing, skill quality summaries, task-trace uploads, and a refreshed dashboard / TUI experience. - **2026-07-17** 🚀 **OpenSpace v2 is released**: v2 turns OpenSpace into a quality-first Skill Hub with package-based skill browsing, skill quality summaries, task-trace uploads, and a refreshed dashboard / TUI experience.
<details>
<summary>Earlier news</summary>
- **2026-07-04** 📊 **Skill quality summaries now visible while browsing v2 skills**: package and skill detail views show usage-quality summaries; public lineage pages display redacted placeholders for unavailable content. - **2026-07-04** 📊 **Skill quality summaries now visible while browsing v2 skills**: package and skill detail views show usage-quality summaries; public lineage pages display redacted placeholders for unavailable content.
- **2026-07-03** 🔎 **Package skill search and task-trace uploads are now first-class v2 flows**: package pages search skills directly, and task traces can be validated, stored, and uploaded idempotently as quality evidence. - **2026-07-03** 🔎 **Package skill search and task-trace uploads are now first-class v2 flows**: package pages search skills directly, and task traces can be validated, stored, and uploaded idempotently as quality evidence.
- **2026-06-25** 🌐 **The v2 cloud path became more stable for public browsing and private skill access**: public pages, private skill endpoints, frontend / backend routes, and TLS access are now checked together. - **2026-06-25** 🌐 **The v2 cloud path became more stable for public browsing and private skill access**: public pages, private skill endpoints, frontend / backend routes, and TLS access are now checked together.
<details>
<summary>Earlier news</summary>
- **2026-06-19** 🌐 **Public v2 pages can be read without login**: anonymous visitors can browse public skills, existing users gained an agent bootstrap path, and search / recall services were restored. - **2026-06-19** 🌐 **Public v2 pages can be read without login**: anonymous visitors can browse public skills, existing users gained an agent bootstrap path, and search / recall services were restored.
- **2026-06-18** 🧭 **The v2 cloud experience became more complete**: package, group, profile, and agent pages were assembled into a cleaner package-browser flow with a more structured import path. - **2026-06-18** 🧭 **The v2 cloud experience became more complete**: package, group, profile, and agent pages were assembled into a cleaner package-browser flow with a more structured import path.
@ -219,6 +219,14 @@ Run the agent in a way that leaves useful evidence.
- Organizes cloud skills by package for meaningful browsing, then imports them locally before any reuse. - Organizes cloud skills by package for meaningful browsing, then imports them locally before any reuse.
- Runs agents in a harness that captures the evidence quality judgment and skill evolution both depend on. - Runs agents in a harness that captures the evidence quality judgment and skill evolution both depend on.
### 📊 Terminal-Bench 2.1: Self-Evolution That Shows Up in the Score
With the same frozen Hy3 backbone, OpenSpace improves from a 65.2% Cold run to a 78.7% Warm run as its trusted skill library evolves.
<div align="center">
<img src="assets/benchmark_v2.png" width="100%" alt="OpenSpace and Hy3 performance on Terminal-Bench 2.1, including leaderboard standing, task-family scores, and capability profile">
</div>
## 📋 Table of Contents ## 📋 Table of Contents
- [⚡ Quick Start](#-quick-start) - [⚡ Quick Start](#-quick-start)

BIN
assets/benchmark_v2.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 392 KiB