Next Qwen Max Model (3.9+): Text Arena Debut?
This event asks whether the next Alibaba Qwen Max model numbered 3.9 or higher will debut on the Arena.AI Text leaderboard (style control off) with a score at or above a set threshold. Four thresholds are open: 1460, 1480, 1500 and 1520. The key rule is that the score counts only as shown at 12:00 PM ET on the day after the model first appears, and only if it is not labeled "AutoEval".
Leading right now: 1460+ 78%, 1480+ 55%, 1500+ 18%, 1520+ 8%.
| Market | Chance of yes | Deadline |
|---|---|---|
| Will the next Qwen Max model (3.9+) debut at a score of at least 1460 by June 30, 2027? | 78.5% | Jul 1, 2027, 3:59 UTC |
| Will the next Qwen Max model (3.9+) debut at a score of at least 1480 by June 30, 2027? | 54.5% | Jul 1, 2027, 3:59 UTC |
| Will the next Qwen Max model (3.9+) debut at a score of at least 1500 by June 30, 2027? | 18.0% | Jul 1, 2027, 3:59 UTC |
| Will the next Qwen Max model (3.9+) debut at a score of at least 1520 by June 30, 2027? | 7.8% | Jul 1, 2027, 3:59 UTC |
Odds read from Polymarket at 22:18 UTC on Nov 21, 2026. $106K traded so far, $6K in the last 24 hours.
How this market resolves
Yes: A qualifying model (name includes "Qwen" and "Max", flagship Max tier, version 3.9 or higher) is newly added to the leaderboard by June 30, 2027, 11:59 PM ET. Its Score, shown without an "AutoEval" label at 12:00 PM ET on the next calendar date, is at or above that market's threshold. If several qualifying models are added on the same ET date, the highest-scoring one is used.
No: No qualifying model is added by June 30, 2027, 11:59 PM ET. It is also NO if the score at the check time is below the threshold, if the model is only shown as AutoEval, if the model has been removed by the check time, or if no score is available through the end of the seventh day after first appearance.
When it really ends
A qualifying model must first appear by June 30, 2027, 11:59 PM ET (EDT, UTC-4), which is 2027-07-01 03:59 UTC. This matches the data's end date. The score is read at 12:00 PM ET the next day (16:00 UTC if the model appears on June 30), so the final reading can fall after the listed end date. If the source is down, the first later available score is used, up to seven days after first appearance.
What counts
- A model named like Qwen3.9-Max, Qwen3.9-Max-Preview or a later version such as Qwen4-Max, in any capitalization or with prefixes, suffixes or dates.
- A model that was already public or in beta before it reached the leaderboard, as long as it is newly added to the leaderboard.
- The rounded Score in the Score column of the Text Arena | Overall tab with style control off.
- The highest-scoring qualifying model when several are added on the same ET calendar date.
What does not count
- Any model below version 3.9, such as Qwen3.8-Max or Qwen3.8-Max-Preview, including its stable, open-weight or snapshot re-releases.
- Models without "Max" in the name.
- Derivative lines such as VL, Coder, Omni or other specialized variants (for example qwen-vl-max).
- A score shown with the "AutoEval" label, which means the model is not yet considered added.
- Qualifying models added on the calendar date after the first qualifying model appeared.
Fine print people miss
- Only the displayed Score counts, not any more granular or unrounded data shown elsewhere.
- The leaderboard to use is the no-style-control version of the Text overall page, not the default style-controlled view.
- If the model is added and then removed, and is not on the board at 12:00 PM ET the next day, it does not count as added.
- Only the first qualifying appearance sets the clock; later models added after the next calendar date are ignored.
- The rules do not say what happens if a model first appears as AutoEval and later gets a full score. The text only says AutoEval scores are not counted.
- If the leaderboard is unavailable, the first later available score is used, but only through the seventh day after first appearance.
What moves the price
- An Alibaba announcement or preview of a 3.9 or 4.0 Max model would raise the chance that a qualifying model appears before the deadline.
- Signs that the next Max release is a 3.8 version or has no "Max" name would lower the chance of any qualifying model.
- Benchmark results or early user tests showing strong chat performance would raise the odds of higher thresholds.
- Strong scores from rival flagship models on the same leaderboard suggest the scale is moving up, which helps higher thresholds.
- A release timeline pointing past June 30, 2027 would push all four markets toward NO.
Put a bot on this market
A PROWL bot reads the news around the clock, judges each post against these exact rules, and trades inside the limits you set. It starts in paper mode.
Questions people ask
What is the Qwen Max Text Arena debut market?
It asks whether the next Alibaba Qwen Max model numbered 3.9 or higher will debut on the Arena.AI Text leaderboard at or above a stated score. There are four markets with different score thresholds.
When is the score measured?
At 12:00 PM ET on the calendar date after the model first appears on the leaderboard. A score on the first day itself does not decide the market.
Does Qwen3.8-Max count?
No. Only versions 3.9 or higher qualify. Qwen3.8-Max, its Preview, and any stable, open-weight or snapshot re-release are excluded.
What if the model shows as AutoEval?
A model marked AutoEval is not treated as added to the leaderboard. Only scores shown without that label count.
What happens if no qualifying model is released?
If no qualifying model is added by June 30, 2027, 11:59 PM ET, every market in this event resolves to No.
Which leaderboard view is used?
The Text Arena | Overall tab at arena.ai/leaderboard/text/overall-no-style-control, with style control off. The Score column value is the one that counts.
More Tech markets explained
Written from the market's own rules text on Nov 17, 2026. If the rules on Polymarket differ from this page, the rules on Polymarket govern.