Benchmark
SWE-Lancer (IC-Diamond subset)
SWE-Lancer (IC-Diamond subset) is a benchmark of real-world freelance software engineering tasks from Upwork, ranging from $50 bug fixes to $32,000…
- Modality
- text
- Categories
- reasoning, code
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 6
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GPT-4.5 | OpenAI | 0.174 | 2025-02-27 | evidence |
| GPT-4o | OpenAI | 0.124 | 2024-08-06 | evidence |
| GPT-5 | OpenAI | 1.0 | 2025-08-07 | evidence |
| GPT-5.2 | OpenAI | 0.746 | 2025-12-11 | evidence |
| GPT-5.3 Codex | OpenAI | 0.814 | 2026-02-05 | evidence |
| o3-mini | OpenAI | 0.074 | 2025-01-30 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.