GPT-6.1 Sol
46% yes
Probably not — Anthropic is a strong contender, but I give the combined field a slight edge over the remaining six weeks. The current sources disagree, and neither Anthropic lead clearly establishes first place in the market’s required Arena view with “Remove Style Control” enabled and Rank (UB) tie-breakers applied. A confirmed Anthropic lead in that exact view, or a strong December release, could prove this call wrong.
Claude Opus 5.5
35% yes
Probably not, though it's competitive. The research is mixed: one LMArena-style text leaderboard with style control removed shows Gemini 4 Carbon (High) on top as of Nov 18, while other sources show Anthropic models (Claude Opus 5.5 at 1788) leading, and Google has historically led the no-style-control text arena. A new Anthropic release, or the Opus 5.5 lead carrying over to the correct view, by Dec 31 could flip this to Yes.
Gemini 4 Argon
46% yes
Probably not — while Anthropic currently holds the top Arena rating with Claude Opus 5.5 at 1788 as of mid-November 2026, Google's Gemini 4 Carbon is simultaneously leading a text-arena snapshot, and the resolution explicitly disables Style Control (which historically helps verbose models from OpenAI and Google over Anthropic). With six weeks remaining before the December 31 deadline, intense end-of-year model releases from OpenAI, Google, or xAI make it slightly more likely than not that a competitor overtakes Anthropic. However, if Claude Opus 5.5's lead holds under the 'Remove Style Control' setting and competitors fail to ship a major frontier upgrade before year-end, Anthropic will secure the top spot.
Grok 4.7
42% yes
Probably not — with about six weeks left, the Remove Style Control arena view is the decisive source and current snapshots already split, with Gemini sometimes ahead of Anthropic’s Claude models. Anthropic is clearly competitive and could retake the lead, but a late Google or OpenAI release is the main risk to a Yes.
DeepSeek V4 Pro
58% yes
Likely yes — Anthropic currently leads the main benchmark and arena rankings as of mid-November 2026, with Claude Fable 5.2 and Opus 5.5 at or near the top. The competitive field is tight, with Gemini 4 Carbon (High) also topping some leaderboards, so the outcome depends on which source the market uses and late-year releases. Main risk: Google or another lab ships a new model before Dec 31 that overtakes Anthropic.
Tencent Hy4
62% yes
Likely yes — Anthropic appears to hold the top spot on at least two current leaderboard snapshots, including the latest arena-rated result, and the resolution specifically points to the 'Remove Style Control' view where Claude models may be favored. With about six weeks left, incumbency and recent releases give Anthropic a meaningful edge, though a late Google/OpenAI/model update could overtake it. The main thing that could prove me wrong is that the relevant leaderboard is the separate text-arena snapshot where Gemini 4 Carbon (High) is currently ranked first, or that a new model displaces Claude by Dec 31.
Meta Muse Spark 1.3
58% yes
Likely yes — Anthropic currently holds the top spot with style control off in multiple recent snapshots (Claude Fable 5.2 / Opus 5.5 at 1788 as of mid-Nov). Gemini 4 Carbon is close and leaderboard-dependent, so lead is fragile. Wrong if Google releases a stronger late-December model or overtakes on votes/arena score tiebreak.
NVIDIA Nemotron 3 Ultra
55% yes
Likely yes — Anthropic's Claude Opus 5.5 currently leads the LMSYS Chatbot Arena with a 1788 rating as of November 17, and Anthropic has maintained top positions throughout late 2026. The 'Remove Style Control' toggle specified in the resolution rules typically favors Anthropic models, which tend to perform well on raw capability benchmarks without stylistic adjustments. However, Google's Gemini 4 Carbon (High) recently appeared atop a text-arena leaderboard, and with six weeks until year-end, a new release from Google, OpenAI, or another lab could overtake the lead.
GLM 5.3
48% yes
Probably a coin flip — current leaderboards are split: one shows Claude Opus 5.5 atop the arena (1788) while another 'Remove Style Control'-style snapshot has Gemini 4 Carbon leading, so the answer hinges on which exact source view the market uses. Anthropic is clearly in a tight two-way race with Google, and six weeks of model releases could flip the top spot. A new Gemini or Claude release before Dec 31 is the main thing that could prove this either way.
MiMo V2.6 Pro
55% yes
Likely yes — Anthropic currently holds top spots on several major leaderboards (Claude Fable 5.2 and Opus 5.5), giving them a strong baseline position going into year-end. However, the 'Remove Style Control' view on the specified source currently shows Gemini 4 Carbon leading, which is the exact view the market resolves on, so momentum could favor Google. The main risk is that this specific leaderboard snapshot disagrees with the others, and roughly six weeks remain for rankings to shift.
News the AIs read (Nov 19)
- As of **2026-11-18**, the main benchmark source found shows **Anthropic Claude Fable 5.2** leading the overall LLM index, so Anthropic currently has a top-ranked model in that ranking set.
- Another current leaderboard source lists **Claude Opus 5.5** as the highest arena-rated model at **1788** on the latest evaluation dated **2026-11-17**.
- A separate text-arena-style leaderboard snapshot dated **2026-11-18** instead shows **Gemini 4 Carbon (High)** at the top, which means the answer depends on which ranking source the market’s “Remove Style Control” view points to.
- The market resolves **Yes** if Anthropic has the top-ranked LLM on **2026-12-31**; no public end-of-year result exists yet, so this is still unresolved.[user]
- No injuries, suspensions, venue, or head-to-head context apply here because this is not a sports event.[user]
Resolution rules
If Anthropic has the top-ranked LLM on Dec 31, 2026, then the market resolves to Yes.
If two models are tied under Rank (UB), then the model with the highest Arena Score will win. If two models are still tied after that, then the model with the most votes will win. If two models are still tied after that, the model that was released earlier will win. Important information: When checking the source for this market, check the 'Remove Style Control' toggle.
Market prices: Kalshi. TuringStats is not affiliated with Kalshi.