SQBench - L3 Business Scenarios: leaderboard
Metric: Strict Pass@1 (%; the 60 L3 domain business-scenario tasks on SQBench v1.0, 220 production-oriented delivery tasks in which an agent processes input assets, uses tools and produces a specified deliverable; a task passes only with functional Completion 1 and no triggered 10-dimension risk penalty; one run per configuration and task; higher is better). Source: arxiv.org. Saturation forecast: Around 2030. 27 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GLM-5.2 (Max) | 28.3 |
| 2 | Kimi K3 | 26.7 |
| 3 | Claude Opus 4.8 (Max) | 25 |
| 4 | DeepSeek V4 Flash (High) | 23.3 |
| 5 | Kimi K2.6 | 21.7 |
| 6 | GLM-5.1 | 21.7 |
| 7 | Qwen 3.7 Plus | 21.7 |
| 8 | MiMo-V2.5 | 21.7 |
| 9 | DeepSeek V4 Pro (Max) | 21.7 |
| 10 | DeepSeek V4 Pro (High) | 21.7 |
| 11 | MiMo-V2.5-Pro | 20 |
| 12 | Kimi K2.7 Code | 20 |
| 13 | DeepSeek V4 Flash (Max) | 20 |
| 14 | MiniMax-M2.7 | 18.3 |
| 15 | MiniMax-M3 | 18.3 |
Interactive version: theaggregate.ai/benchmark?slug=sqbench-l3-business-scenarios · How It Works · Data refreshed daily, snapshot 2026-09-29.