isitsota / DeepSeek V3.2 Exp Thinking / Coding
Is DeepSeek V3.2 Exp Thinking SOTA in Coding?
Not enough data#82 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Standings
Coding
| # | Model | State |
|---|---|---|
| 1 | Claude Opus 5.5 | Co-SOTA |
| 1 | Claude Sonnet 5.5 | Co-SOTA |
| 2 | GPT-6.1 Sol | Near-SOTA |
| 2 | GPT-6 Astra | Near-SOTA |
| 3 | Claude Fable 5.1 | Near-SOTA |
| 4 | Claude Opus 5 | #4 in this category |
| 5 | GPT-6 Sol | #5 in this category |
| 6 | Claude Fable 5 | #6 in this category |
| 7 | GLM 5.3 | #7 in this category |
| 8 | Grok 4.7 | #8 in this category |
| 9 | GPT-5.6 Sol | #9 in this category |
| 10 | GLM 5.3 Flash | #10 in this category |