LLM Stats (SWE-Lancer (IC-Diamond subset)): leaderboard
Diamond subset of SWE-Lancer: high-value freelance software engineering tasks from real Upwork contracts testing end-to-end implementation.
Metric: Score (%). Source: llm-stats.com. Saturation forecast: Around January 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.3 Codex | 81.4 | #69 |
| 2 | GPT-5.2 | 74.6 | #110 |
| 3 | GPT-4.5 | 17.4 | #274 |
| 4 | GPT-4o | 12.4 | #343 |
| 5 | O3 Mini | 7.4 | #272 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-swe-lancer-ic-diamond-subset · How It Works · Data refreshed daily, snapshot 2026-10-20.