TEBench - Identification: leaderboard
Metric: Identification F1 (%) for all three evolution types: the tests the agent modified, deleted (method level) or added (file level) against the developer's own test changes, on TEBench (314 commits from 10 Java projects): given the project at the commit with its production changes but not its test changes, the agent edits the test suite in an isolated worktree with default agent settings; higher is better. Source: arxiv.org. Saturation forecast: Around August 2027. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.3 Codex | 49.4 |
| 2 | GLM-5 | 49.3 |
| 3 | Kimi K2.5 | 48.5 |
| 4 | Claude Sonnet 4.6 | 48.3 |
| 5 | DeepSeek V3.2 | 45.7 |
Interactive version: theaggregate.ai/benchmark?slug=tebench-identification · How It Works · Data refreshed daily, snapshot 2026-10-07.