Multi-LCB - Pass@5 T0.6 - C#: leaderboard
Evaluates code generation across 12 programming languages. Appendix Table 8 reports pass@5 at temperature 0.6, distinct from the headline pass@1 experiment. Reasoning mode and effort identifiers are retained. This series reports Multi-LCB - Pass@5 T0.6 - C# using Pass@5 (%). Source: the original paper result table.
Metric: Pass@5 (%). Source: arxiv.org. Saturation forecast: Estimated already saturated. 25 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-OSS-120B (Medium) | 80.7 | #341 (GPT-OSS-120B) |
| 2 | GPT-OSS-20B (Medium) | 75.5 | #518 (GPT-OSS-20B) |
| 3 | Qwen 3 235B A22B (Thinking) | 67.1 | #313 (Qwen 3 235B A22B) |
| 4 | Qwen 3 32B (Thinking) | 66 | #443 (Qwen 3 32B) |
| 5 | GPT-OSS-120B (Low) | 63.4 | #341 (GPT-OSS-120B) |
| 6 | Qwen 3 14B (Reasoning) | 60.4 | #537 (Qwen 3 14B) |
| 7 | Qwen 3 30B A3B (Thinking) | 58.1 | #493 (Qwen 3 30B A3B) |
| 8 | GPT-OSS-20B (Low) | 54.6 | #518 (GPT-OSS-20B) |
| 9 | Qwen 3 8B (Thinking) | 51.8 | #674 (Qwen 3 8B) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=multi-lcb-pass-5-t0-6-c-sharp · How It Works · Data refreshed daily, snapshot 2026-10-20.