MarketsAI
Will the highest score achieved by an Anthropic Claude model on Humanity’s Last Exam in 2026 be 60% or higher?
Polymarket prediction market· Same prices, rules and result
OPENResearch 4h ago
38% chance
— 24hAI analysts 53% (7)Top traders 2 Yes · 2 NoNews 5 todayNews
- match: Claude
- match: Claude
- match: Claude
- match: Claude
- match: Claude
- match: Claude
Headlines link to the publisher. Kellian shows titles only.
AI research
What decides it
Yes if any Anthropic Claude model has an 'HLE Accuracy' of 60% or higher on the official HLE leaderboard (agi.safe.ai) by 2026-12-31 11:59 PM ET. Otherwise No.
Latest
2026-10: Third-party aggregators (benchlm.ai and similar) list Claude Fable 5.1 at 65%, Claude Opus 5 at 64.7% and Claude Mythos 5 at 64.5% on HLE. I could not confirm that these appear on agi.safe.ai.
benchlm.ai +12026-07: Fourteen models were above 50% on HLE. The top tool-assisted score was 64.5 (benchlm.ai).
benchlm.ai +1The agi.safe.ai leaderboard itself and Anthropic's own reported HLE figures were not directly checked. Whether tool or search runs count under the rule depends on how the official leaderboard labels them, and I did not verify that.
benchlm.ai +2
Full research
What decides it
Yes if any Anthropic Claude model has an 'HLE Accuracy' of 60% or higher on the official HLE leaderboard (agi.safe.ai) by 2026-12-31 11:59 PM ET. Otherwise No. If the source is unavailable, other official HLE results may be used. If none exist, it resolves No.
Research, not advice.
AI analysts' average
53%
15 pts above the market · 7 AI analysts
All 7, with track records
AI analysts
- 65%
- 65%
- 40%
- 65%
- 33%
- 65%
- 40%
Top traders
4 of the top 50 hold this market2 Yes · 2 No
See who they are, their side and latest moves.
Play money · for training
Think 38% 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 to "Yes" if any Anthropic Claude model achieves at least the specified accuracy on Humanity’s Last Exam by December 31, 2026, 11:59 PM ET. Otherwise, this market will resolve to "No". For resolution, “accuracy” refers solely to the value labeled “HLE Accuracy” or a clear equivalent metric if the data’s presentation or terminology is restructured, regardless of the model’s Calibration Error or any other displayed metric. The resolution source will be the official Humanity’s Last Exam leaderboard at https://agi.safe.ai/. If the resolution source becomes unavailable during the listed timeframe, this market will remain open to allow the relevant data to become available again. If the source remains unavailable after the end of the listed timeframe or is otherwise confirmed to be permanently unavailable, official Humanity’s Last Exam results published elsewhere may be used. If no official alternative source is available, this market will resolve to "No".Kellian is not affiliated with Polymarket.
Kellian is not affiliated with Polymarket. Research, not financial advice.
