| Paper | Code | Pass Rate | ModelName | ReleaseDate |
|---|---|---|---|---|
| SkillsBench Leaderboard | 67.3 | GPT-5.5 (OpenHands) | 2026-04-23 | |
| SkillsBench Leaderboard | 61.2 | Opus 4.7 (Claude Code) | 2026-04-16 | |
| SkillsBench Leaderboard | 60.8 | Gemini 3.1 Pro (Gemini CLI) | 2026-02-19 | |
| SkillsBench Leaderboard | ✓ Link | 58.4 | GLM 5.1 (OpenHands) | 2026-04-03 |
| SkillsBench Leaderboard | 54.6068 | Gemini 3 Flash (Gemini CLI) | 2025-11-18 | |
| SkillsBench Leaderboard | 54.1 | Opus 4.8 (OpenHands) | 2026-05-28 | |
| SkillsBench Leaderboard | ✓ Link | 54 | Kimi K2.6 (OpenHands) | 2026-04-20 |
| SkillsBench Leaderboard | ✓ Link | 53 | MiniMax M3 (OpenHands) | 2026-05-31 |
| SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries | 52.4 | SkillZip (Claude Sonnet 4.5) (OpenHands (BenchFlow 0.6.2)) | 2026-08-06 | |
| SkillsBench Leaderboard | 51.7046 | GPT-5.2 (Codex) | 2025-12-11 | |
| SkillsBench Leaderboard | 50.2241 | Opus 4.6 (Claude Code) | 2026-02-05 | |
| SkillsBench Leaderboard | ✓ Link | 50.1 | DeepSeek V4 Pro (OpenHands) | 2026-04-26 |
| Intern-S2-Preview: Scientific Agentic Foundation Model | ✓ Link | 50.03 | Intern-S2-Preview-397B (OpenClaw 2026.5.7) | 2026-08-13 |
| SkillsBench Leaderboard | 49.0395 | Opus 4.5 (Claude Code) | 2025-11-24 | |
| SkillsBench Leaderboard | 48.2 | Gemini 3.5 Flash (OpenHands) | 2026-05-19 | |
| SkillsBench Leaderboard | 47.2 | Sonnet 4.6 (OpenHands) | 2026-02-17 | |
| SkillsBench Leaderboard | ✓ Link | 44.7 | DeepSeek V4 Flash (OpenHands) | 2026-04-26 |
| SkillsBench Leaderboard | 41.7 | Grok 4.3 (OpenHands) | 2026-04-30 | |
| SkillsBench Leaderboard | 41.4 | GPT-5.4 Mini (OpenHands) | 2026-03-05 | |
| SkillsBench Leaderboard | 36.1723 | Sonnet 4.5 (Claude Code) | 2025-09-29 | |
| SkillsBench Leaderboard | ✓ Link | 34.9 | MiniMax M2.7 (OpenHands) | 2026-05-26 |
| SkillsBench Leaderboard | 30.0831 | Haiku 4.5 (Claude Code) | 2025-10-15 | |
| SkillsBench Leaderboard | 20.1 | Gemini 3.1 Flash Lite (OpenHands) | 2026-03-03 |