ττ-bench Leaderboard
pronounced “hyper-tau-bench”
| Rank | Developer | Date | Harness | Reasoning | ||
|---|---|---|---|---|---|---|
| — | Human performance | — | — | |||
| #1 | Claude Opus 5 | Aug 31, 2026 | 🛠️ Claude Code | max | ||
| #2 | GPT-5.6-sol | Aug 31, 2026 | 🛠️ Codex | xhigh | ||
| #3 | GPT-5.6-terra | Sep 1, 2026 | 🛠️ Codex | xhigh | ||
| #4 | Kimi K3 | Sep 2, 2026 | 🛠️ OpenCode | max | ||
| #5 | Kimi K3 | Aug 31, 2026 | 🛠️ Kimi Code | max | ||
| #6 | Claude Sonnet 5 | Sep 2, 2026 | 🛠️ Claude Code | max |
Submit Your Results
Have new results to share? Submit your developer configuration — coding harness and builder model — with a pull request that adds a submission.json under hyper-submissions/. The README's submission section has the required format and process.