Hy-SWE Max Verified (Internal): leaderboard
Tencent’s internal Hy-SWE Max Verified software-engineering evaluation uses 300 tasks, hidden pass/fail verifier tests, and averages results over three runs. The evaluated model works on text-based coding tasks. The pinned metric is pass rate. Source: BenchmarkList’s attributed result table.
Metric: Pass Rate (%). Source: benchmarklist.com. Saturation forecast: Around February 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol | 69.8 | #22 |
| 2 | GLM-5.3 | 67.2 | #44 |
| 3 | DeepSeek V4 Pro (0813) | 65.7 | #58 |
| 4 | Kimi K3 | 65.6 | #35 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=hy-swe-max-verified-internal · How It Works · Data refreshed daily, snapshot 2026-11-05.