Across 5 models scored on Banking, Kimi K2.6 1T A32B leads at 23.1, ahead of nvidia-nemotron-3-ultra-550b-a55b at 22.6. The median tracked score is 20.9, and the field spans 12.8 to 23.1.
Data as of August 24, 2026| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | Kimi K2.6 1T A32B | Moonshot | 23.1 | 1 | 2026-08-24 |
| 2 | nvidia-nemotron-3-ultra-550b-a55b | NVIDIA | 22.6 | 1 | 2026-08-24 |
| 3 | Qwen 3.5 397B 17B | Alibaba | 20.9 | 1 | 2026-08-24 |
| 4 | MiniMax 2.7 230B A10B | MiniMax | 14.6 | 1 | 2026-08-24 |
| 5 | GLM-5.1-744B-A40B | Z.ai | 12.8 | 1 | 2026-08-24 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.