Modelsby GlyphBest for coding
Claude Fable 5.1 and GPT-6 Astra tie for the lead · 2 fresh boards · counts toward the leader of leaders · Fixing real repositories, building web apps, editing code.
| # | Model | Score#1s | ||
|---|---|---|---|---|
| 1 | 75.0 | 75.00 | 2 | |
| 1 | 75.0 | 75.00 | 2 | |
| 3 | 65.0 | 65.01 | 2 | |
| 4 | 50.0 | 50.01 | 1 | |
| 5 | 45.0 | 45.00 | 2 | |
| 6 | 45.0 | 45.00 | 1 | |
| 7 | 35.0 | 35.00 | 1 | |
| 7 | 35.0 | 35.00 | 1 | |
| 9 | 25.0 | 25.00 | 1 | |
| 10 | 25.0 | 25.00 | 1 | |
| 11 | 25.0 | 25.00 | 1 | |
| 12 | 20.0 | 20.00 | 1 |
Boards
- 1
Claude Opus 5.51,814
- 2
- 3
GPT-6 Astra1,770
- 1
- 2
- 3
Gemini 4 Argon92.2%
- 1
- 2
- 2
MiniMax-M2.575.8%
- 1
- 2
- 3
The wall
#1 with the vendor’s logo23 podium7 top 10 stale board, not countedArrow keys move, Enter opens