Benchmark · coding

Code Arena (Elo)

1 results 1 models

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 %.

1400 1500 1600 1700 1800 2026-08-07 DeepSeek-V4-Flash-0731 · 1577 · 2026-08-07
DeepSeek-V4-Flash-0731
Timeline
Date Model Score Source
2026-08-07 DeepSeek-V4-Flash-0731 1577.0Elo DeepSeek releases V4-Flash-0731, outperforming V4-Pro at lower cost