Will any AI model reach 1580 Coding Arena Score by December 31, 2026?
As of September 3, 2026, the market gives “Will any AI model reach 1580 Coding Arena Score by December 31, 2026?” a 82% chance of NO.
| YES odds | 18% |
|---|---|
| NO odds | 82% |
| Volume | $66,901 |
| Closes | January 1, 2027 |
Updated September 3, 2026 · Live data from Polymarket
About this market
Recent releases from Alibaba's Qwen3.8-Max-0902 series and Anthropic's Claude Opus 5 / Fable 5 variants have driven Coding Arena Elo scores above 1,690 in WebDev and general coding leaderboards as of early September 2026, reflecting targeted post-training on agentic workflows and complex code tasks. Anthropic models maintain strong leads on SWE-bench Verified (up to 96%) and related agent benchmarks, while open-weight challengers like Qwen and GLM variants close gaps through scale and specialized fine-tuning. With four months remaining, trader sentiment hinges on whether frontier labs can sustain incremental gains or if a major capability jump from any provider pushes the threshold before year-end.