Is DeepSeek V4.1 Flash 1017 SOTA in Reasoning?Not enough data#17 on GPQA Diamond; missing Humanity's Last Exam and LMArena Text (style-controlled, hard prompts)
Standings
Reasoning
| # | Model | State |
|---|---|---|
| 1 | Gemini 4 Carbon | Leading · crown pending |
| 1 | Gemini 4 Argon | Co-SOTA |
| 1 | Claude Opus 5.5 | Co-SOTA |
| 1 | Muse Wonder | Co-SOTA |
| 2 | Claude Opus 4.6 | Near-SOTA |
| 3 | Claude Fable 5 | Near-SOTA |
| 4 | Claude Opus 4.7 | Near-SOTA |
| 6 | Claude Fable 5.1 | Was SOTA |
| 7 | Gemini 3.8 Flash | #7 in this category |
| 8 | Kimi K3 | #8 in this category |
| 9 | Claude Opus 5 | Was SOTA |
| 10 | Muse Spark 1.3 | #10 in this category |