Apex — Full/unfiltered Apex set (DeepSeek); distinct subset from Shortlist variants (diff score range)
| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | Gemini 3.1 Pro | 60.9 | 4 | 2026-07-04 | |
| 2 | GPT-5.4 | OpenAI | 54.1 | 4 | 2026-07-04 |
| 3 | DeepSeek-V4-Pro | DeepSeek | 38.3 | 9 | 2026-06-27 |
| 4 | Claude Opus 4.6 | Anthropic | 34.5 | 4 | 2026-07-04 |
| 5 | DeepSeek-V4-Flash | DeepSeek | 33 | 4 | 2026-06-27 |
| 6 | Kimi K2.6 | Moonshot | 24 | 4 | 2026-07-04 |
| 7 | Qwen3.7 Plus Preview | Alibaba | 22.7 | 1 | 2026-08-23 |
| 8 | GLM-5.1 | Z.ai | 11.5 | 2 | 2026-06-06 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.