A benchmark that evaluates whether models can complete realistic software-engineering tasks performed by individual contributors.
Browse the latest scores, model modes, release dates, and parameter sizes for IC SWE-Lancer(Diamond).
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Rank | Model | License | |||
|---|---|---|---|---|---|
 GPT-5.3 Codex Standard Mode | 81.40 | 2026-02-05 | Unknown | Closed | |
GPT-5.2 Thinking Level · Extra HighTools | 74.60 | 2025-12-11 | Unknown | Closed | |
GPT-5.1 Thinking Level · High | 69.70 | 2025-11-12 | Unknown | Closed | |
4 | GPT-4.1 mini Standard Mode | 33.00 | 2025-04-14 | Unknown | Closed |
5 | GPT-4.5 Standard Mode | 32.60 | 2025-02-28 | Unknown | Closed |
6 | GPT-4o Standard Mode | 23.30 | 2024-05-13 | Unknown | Closed |
7 | GPT-4.1 nano Standard Mode | 15.30 | 2025-04-14 | Unknown | Closed |
8 | GPT-4.1 Standard Mode | 14.40 | 2025-04-14 | Unknown | Closed |
