OR-Space: leaderboard
Metric: Build Pass@1 (self-reported). Source: benchmarklist.com. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 72 |
| 2 | Gemini 3 Flash | 68 |
| 3 | DeepSeek V4 Pro | 67 |
| 4 | Claude Opus 4.6 | 62 |
| 5 | GPT-5.4 | 59 |
| 6 | GPT-5 Mini | 58 |
| 7 | DeepSeek R1 0528 | 55 |
| 8 | DeepSeek V4 Flash | 54 |
| 9 | Claude Sonnet 4.5 | 53 |
| 10 | Gemini 2.5 Flash | 53 |
| 11 | GPT-5.1 | 53 |
| 12 | Claude Sonnet 4.5 (Thinking) | 53 |
| 13 | Qwen 3 Max | 49 |
| 14 | Gemini 2.5 Pro | 47 |
| 15 | Qwen 3 32B | 32 |
Interactive version: theaggregate.ai/benchmark?slug=or-space · How It Works · Data refreshed daily, snapshot 2026-09-05.