Benchmark · coding
Code Arena (Elo)
arena.ai's crowdsourced pairwise Elo for web-dev code generation (WebDev / Frontend / Fullstack boards, formerly WebDev Arena). Not the overall Text board (lmsys-arena) and not WebArena's task-success %.
| Date | Modèle | Score | Source |
|---|---|---|---|
| 2026-08-07 | DeepSeek-V4-Flash-0731 | 1577.0Elo | DeepSeek publie V4-Flash-0731, surpassant V4-Pro à moindre coût |