Anthropic’s Claude Opus 5 and related variants currently lead Code Arena leaderboards on arena.ai with Elo-style scores near 1688 on agentic web development and coding tasks, reflecting gains from improved tool use, multi-turn reasoning, and repository-scale edits. OpenAI’s GPT-5.6 family (Sol, Terra, Luna) has closed gaps quickly, tying for top spots in recent updates while undercutting costs, and Chinese labs like Moonshot’s Kimi K3 and Alibaba’s Qwen3 series post competitive scores above 1670. SWE-bench Verified results near 96% for top models and benchmark refinements addressing reward hacking underscore accelerating capabilities. With four months remaining, traders watch for additional frontier releases, long-context scaling, and developer conferences that could lift the highest scores before year-end resolution.
Résumé expérimental généré par IA à partir des données Polymarket. Ceci n'est pas un conseil de trading et ne joue aucun rôle dans la résolution de ce marché. · Mis à jour$193,932 Vol.
1560
38%
1580
20%
1600
13%
$193,932 Vol.
1560
38%
1580
20%
1600
13%
Results from the "Score" column under the "Text Arena | Coding" Leaderboard tab at https://arena.ai/leaderboard/text/coding-no-style-control with style control off will be used to resolve this market.
The resolution source for this market is the Chatbot Arena LLM Leaderboard found at arena.ai/leaderboard/text. If this resolution source is unavailable at check time, this market will remain open until the leaderboard comes back online and will resolve based on the first check after it becomes available. If permanently unavailable, this market will resolve to "No".
Marché ouvert : Apr 2, 2026, 6:09 PM ET
Résolveur
0x65070BE91...Results from the "Score" column under the "Text Arena | Coding" Leaderboard tab at https://arena.ai/leaderboard/text/coding-no-style-control with style control off will be used to resolve this market.
The resolution source for this market is the Chatbot Arena LLM Leaderboard found at arena.ai/leaderboard/text. If this resolution source is unavailable at check time, this market will remain open until the leaderboard comes back online and will resolve based on the first check after it becomes available. If permanently unavailable, this market will resolve to "No".
Résolveur
0x65070BE91...Anthropic’s Claude Opus 5 and related variants currently lead Code Arena leaderboards on arena.ai with Elo-style scores near 1688 on agentic web development and coding tasks, reflecting gains from improved tool use, multi-turn reasoning, and repository-scale edits. OpenAI’s GPT-5.6 family (Sol, Terra, Luna) has closed gaps quickly, tying for top spots in recent updates while undercutting costs, and Chinese labs like Moonshot’s Kimi K3 and Alibaba’s Qwen3 series post competitive scores above 1670. SWE-bench Verified results near 96% for top models and benchmark refinements addressing reward hacking underscore accelerating capabilities. With four months remaining, traders watch for additional frontier releases, long-context scaling, and developer conferences that could lift the highest scores before year-end resolution.
Résumé expérimental généré par IA à partir des données Polymarket. Ceci n'est pas un conseil de trading et ne joue aucun rôle dans la résolution de ce marché. · Mis à jour



Méfiez-vous des liens externes.
Méfiez-vous des liens externes.
Questions fréquentes