CONCUR: leaderboard
Metric: Pass@1 (%): share of the 115 CONCUR problems whose single generated Java 8 program compiles and passes Java PathFinder model checking (no deadlock, race condition, starvation, uncaught exception, missing entry point or single-thread execution) within bounded threads and depth; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 23 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 77.39 | #91 |
| 2 | Claude Opus 4.1 | 67.83 | #132 |
| 3 | Gemini 3 Pro | 66.09 | #77 |
| 4 | GPT-4o | 60 | #333 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=concur · How It Works · Data refreshed daily, snapshot 2026-10-11.