Recent release of Claude Opus 5.5 on September 22 has introduced fresh uncertainty into the tight race for top model by September 28. Early benchmarks show the new Opus variant outperforming or matching Claude Fable 5.1—Anthropic’s prior leaderboard leader since its September 1 launch—on key agentic coding and reasoning tests like Terminal-Bench 4.0 while cutting costs roughly 40%. Traders appear split between Fable 5.1’s established frontier scores and the possibility that Opus 5.5, GPT-6 Astra, or another unreleased contender claims the edge in the final days. Market-implied odds reflect this contest between proven capability and rapid iteration, with resolution hinging on the latest verifiable benchmark updates.
Экспериментальная сводка, созданная ИИ на основе данных Polymarket. Это не является торговой рекомендацией и не влияет на то, как разрешается этот рынок. · ОбновленоЛучшая модель ИИ 28 сентября?
Другая 54%
claude-fable-5.1-max 44%
claude-opus-4-6-high 8%
claude-opus-5-high 5%
Другая
54%
claude-fable-5.1-max
44%
claude-opus-4-6-high
8%
claude-opus-5-high
5%
claude-opus-5-max
3%
Другая 54%
claude-fable-5.1-max 44%
claude-opus-4-6-high 8%
claude-opus-5-high 5%
Другая
54%
claude-fable-5.1-max
44%
claude-opus-4-6-high
8%
claude-opus-5-high
5%
claude-opus-5-max
3%
Results from the "Rank" column under the "Text Arena | Overall" Leaderboard tab at https://arena.ai/leaderboard/text/overall-no-style-control with style control off (Adjustments: None) and filtered for "Models" will be used to resolve this market.
Note: Models marked “AutoEval” at the applicable check time will not be considered, regardless of whether they display a rank or score.
No new model will be added to this market after market creation. Any model not explicitly listed in this market will be encompassed under the "Other" option.
Models will be ordered primarily by their leaderboard rank at the market’s check time. If two or more models are tied on rank, they will be ordered by their Arena score, including any underlying, unrounded, granular values reflected in the data below the leaderboard. If a tie still remains, alphabetical order of model names as listed in this market group (full string, including suffixes such as “-high” and “-max”) will be used as a final tiebreaker (e.g., if two models remain tied, “claude-opus-5-high” would be ranked ahead of “claude-opus-5-max”). This market will resolve to the model that comes first according to this order.
The resolution source for this market is the arena.ai Text Arena (Overall). 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 it becomes permanently unavailable, this market will resolve to "Other".
Открытие рынка: Sep 22, 2026, 10:42 AM ET
Кто определяет исход
0x69c47De9D...Results from the "Rank" column under the "Text Arena | Overall" Leaderboard tab at https://arena.ai/leaderboard/text/overall-no-style-control with style control off (Adjustments: None) and filtered for "Models" will be used to resolve this market.
Note: Models marked “AutoEval” at the applicable check time will not be considered, regardless of whether they display a rank or score.
No new model will be added to this market after market creation. Any model not explicitly listed in this market will be encompassed under the "Other" option.
Models will be ordered primarily by their leaderboard rank at the market’s check time. If two or more models are tied on rank, they will be ordered by their Arena score, including any underlying, unrounded, granular values reflected in the data below the leaderboard. If a tie still remains, alphabetical order of model names as listed in this market group (full string, including suffixes such as “-high” and “-max”) will be used as a final tiebreaker (e.g., if two models remain tied, “claude-opus-5-high” would be ranked ahead of “claude-opus-5-max”). This market will resolve to the model that comes first according to this order.
The resolution source for this market is the arena.ai Text Arena (Overall). 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 it becomes permanently unavailable, this market will resolve to "Other".
Кто определяет исход
0x69c47De9D...Recent release of Claude Opus 5.5 on September 22 has introduced fresh uncertainty into the tight race for top model by September 28. Early benchmarks show the new Opus variant outperforming or matching Claude Fable 5.1—Anthropic’s prior leaderboard leader since its September 1 launch—on key agentic coding and reasoning tests like Terminal-Bench 4.0 while cutting costs roughly 40%. Traders appear split between Fable 5.1’s established frontier scores and the possibility that Opus 5.5, GPT-6 Astra, or another unreleased contender claims the edge in the final days. Market-implied odds reflect this contest between proven capability and rapid iteration, with resolution hinging on the latest verifiable benchmark updates.
Экспериментальная сводка, созданная ИИ на основе данных Polymarket. Это не является торговой рекомендацией и не влияет на то, как разрешается этот рынок. · Обновлено


Не доверяй внешним ссылкам.
Не доверяй внешним ссылкам.
Часто задаваемые вопросы