MarketsAI
Will Meta be the third-best Math AI lab at the end of October 2026?
Polymarket prediction market· Same prices, rules and result
OPENResearch 1h ago
35% chance
+1.3 pts 24hAI analysts 33% (3)Top traders 0 Yes · 1 NoNews 1 todayOpening price · no trades yet
News
- match: Meta
- match: Meta · Math · AI
- match: Meta
- match: Meta · Math
Headlines link to the publisher. Kellian shows titles only.
AI research
What decides it
Company third by Lab Rank on arena.ai Text Arena Math with style control OFF (Adjustments: None), Labs view, checked Oct 31, 2026 12:00 PM ET. AutoEval-marked models are ignored; an ambiguous Lab Rank falls back to each lab's best model in the Models view, then unrounded score, then alphabetical order.
Latest
Arena's dataset (text, math, no style control) orders labs by best model: Google 1536.06, Anthropic 1532.21, Z.ai glm-5.3-flash 1503.27, Alibaba qwen3.8-max 1502.13, Xiaomi mimo-v2.6-pro 1496.36, Meta muse-spark-1.3-max 1496.03.
huggingface.coMeta released Muse Wonder and Muse Wonder Full, its first frontier models; Muse Wonder is offered through the Meta Model API.
techcrunch.comBy the 2026-10-08 snapshot Meta had dropped to sixth (1493.59) behind Z.ai (1499.79), Alibaba (1498.90) and Xiaomi (1494.21).
huggingface.co
Case for Yes
Meta was the third Math lab on Sep 30 and Oct 2. Its new Muse Wonder (released Oct 12) scores 1503.87 on the Overall board, though it has no Math entry yet. The labs in third to sixth place sit within about 7 points with overlapping intervals.
Case for No
On Oct 13 Meta ranked sixth in Math, 7.24 points behind third-placed Z.ai (1503.27), with Alibaba and Xiaomi also ahead. muse-wonder-max had no Math listing in that snapshot, and Meta's best Math model rests on 804 votes.
What to watch next Whether Meta's muse-wonder-max appears on the Math board without an AutoEval label before Oct 31 noon ET, and weekly moves among Z.ai, Alibaba, Xiaomi and Meta, which sat within about 7 points on Oct 13.
Full research
What decides it
Company third by Lab Rank on arena.ai Text Arena Math with style control OFF (Adjustments: None), Labs view, checked Oct 31, 2026 12:00 PM ET. AutoEval-marked models are ignored; an ambiguous Lab Rank falls back to each lab's best model in the Models view, then unrounded score, then alphabetical order. Trap: Math has few votes per model (hundreds to a few thousand), so intervals are wide and the order has changed between weekly snapshots.
Earlier
Arena launched AutoEval, which gives new models a preliminary Arena Score before enough people have voted; this market ignores AutoEval-marked models.
runtimewire.com
Sources
- lmarena-ai/leaderboard-dataset (Arena, Hugging Face) · huggingface.co
- Meta releases its first frontier model, Muse Wonder (TechCrunch) · techcrunch.com
- Arena launches AutoEval to rank new AI models (RuntimeWire) · runtimewire.com
Research, not advice.
AI analysts' average
33%
2 pts below the market · 3 AI analysts
All 3, with track records
AI analysts
- 30%
- 35%
- 33%
Top traders
1 of the top 21 holds this market0 Yes · 1 No
See who they are, their side and latest moves.
Play money · for training
Think 35% is wrong? Test your call first.
Practice on this exact market with play money: the same price, rules and result as Polymarket. Play money has no cash value. Every call goes on your record, so you can see how good your read really is.
Free. No card. Turn it off any time.
Rules
- Resolution criteria
- This market will resolve according to the third-highest ranked Company based on the arena.ai Text Arena (Math) when the table under the "Leaderboard" tab filtered for "Labs" is checked on October 31, 2026, 12:00 PM ET. Results from the "Lab Rank" column under the "Text Arena | Math" Leaderboard tab at https://arena.ai/leaderboard/text/math-no-style-control?rankBy=labs with style control off (Adjustments: None) and filtered for "Labs" 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. AI companies will be ordered primarily by their Lab Rank at the market’s check time. If the results based on the lab ranking are ambiguous or unavailable, the relevant AI companies will be ordered according to their highest-ranking AI model in the leaderboard’s “Models” view. 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 AI lab/company names as listed in this market group will be used as a final tiebreaker (e.g., if the two models are tied by exact arena score, “Google” would be ranked ahead of “SpaceXAI”). This market will resolve based on the company that occupies third place under this ranking. The resolution source for this market is the arena.ai Text Arena (Math). 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".Kellian is not affiliated with Polymarket.
Kellian is not affiliated with Polymarket. Research, not financial advice.
