Open-Source AI model gets perfect IMO 2026 score? [International Math Olympiad 2026]
💡 What the odds say
The market puts this at about a 33% chance — unlikely.
No money — just record your call and see if you were right. Yes is at 33% right now.
The market is betting against a perfect score (67% No) despite recent open-source models reaching gold-medal level, because a perfect score requires solving all six problems—a feat no AI has ever achieved and even top human contestants rarely accomplish.
📊 Base rate: Historically, no AI system—open or closed—has ever attained a perfect score on the International Mathematical Olympiad; the best open-source models, such as DeepSeek's late-2025 release, achieved gold-medal performance (roughly 70–80% of problems correct) but not a perfect 6/6.
What's driving it
- • DeepSeek's November 2025 release of an open model with gold-level IMO scores (South China Morning Post, Nov 29, 2025) raised the perceived ceiling for open-source AI, boosting the Yes case.
- • The MIT News report (Apr 24, 2026) of the world's largest open collection of Olympiad-level math problems provides a new training resource, potentially enabling models to close the remaining gap.
- • The WSJ article (Jul 27, 2025) highlighting high-schoolers beating the world's smartest AI models reminds traders that even top AI still lags human creativity on hard problems, anchoring the No odds.
The case for YES
- • DeepSeek already demonstrated gold-medal-level performance in late 2025 (South China Morning Post, Nov 29, 2025), suggesting that with additional training on the MIT dataset (MIT News, Apr 24, 2026) a perfect score is within reach.
- • The open-source community can iterate rapidly—multiple teams could fine-tune models on the MIT dataset and submit the best entry for the 2026 IMO, increasing the chance of a breakthrough.
- • A perfect score is not unprecedented for human participants; if an AI can match the top human reasoning, it could plausibly solve all six problems with sufficient optimization.
The case for NO
- • Perfect scores at the IMO are extremely rare—only a handful of contestants achieve 6/6 each year, and even the world's best AI models have never done it (WSJ, Jul 27, 2025).
- • The DeepSeek model that reached gold level still fell short of perfect; the IMO problems are designed to be novel and creative, testing generalization beyond training data.
- • No headline reports a perfect score by any AI model in the 2026 IMO itself, and the current odds (67% No) suggest the market expects the event to have already occurred or to be very unlikely.
What to watch
- • Official release of the IMO 2026 results (expected July 2026) – if a perfect score by an open-source model is announced, the odds would spike toward Yes; otherwise, they would collapse to No.
- • Any new open-source model paper or benchmark claiming near-perfect or perfect IMO performance before the results – would likely shift odds upward toward Yes.
- • A statement from the IMO organizers or a major AI lab (e.g., DeepSeek, MIT) about the difficulty of the 2026 problems or a model's performance – could move odds in either direction depending on the content.
AI-generated · grounded in recent news + odds · informational only, not advice. Verify on the source platform.
Data from Manifold’s public API, for informational purposes only. PredictPal is not affiliated with any platform and does not facilitate trading.
Discussion
Loading…
How it resolves
Resolved by whoever created the market, at their discretion per the question's description. It's play-money (Mana) and not tied to an official source — treat it as a community forecast.
ⓘ A market settles under its own written rules, which can lag what looks decided in the news — so the price may not move to 100% the moment an outcome seems obvious.
View the official rules on Manifold ↗Related markets
When will Starship flight 14 happen?
The field is extremely front-loaded: the top candidate (before 2027-04-01) commands 95% odds, and all ten candidates above 5% stack into the next nine months, reflecting a market consensus that Flight 14 is imminent but not immediate. The largest recent shift is the collapse of near-term dates after the July 17 abort, when the 'before 2026-10-01' candidate dropped from ~80% to 71% following a second launch abort.
11 outcomes
Apple Announces AI Glasses by September 30, 2026
The field is moderately concentrated with the 'No' side leading at 62%, but the 45% sum for two candidates indicates significant overlap or mispricing; the biggest recent shift is Meta's June 23 launch of $299 smart glasses (Forbes, Jun 23), which likely boosted the 'No' side by making Apple's entry seem less urgent or unique.
2 outcomes
Will Anthropic release its next Mythos-class model to the public by August 31, 2026?
Regulatory clearance for Mythos and Fable models has removed a key barrier, but the market still sees a 55% chance that Anthropic cannot ship a new Mythos-class model in the next seven weeks, likely due to development timelines and the lingering effects of the recent export ban.
Yes ≈ 46% chance
Companies to go public in 2026
The field is top-heavy with SpaceX and Anthropic, but the recent reemergence of SPACs (Freshfields, Jul 24) provides a potential alternative route for lower-odds candidates like Kraken, Canva, and Stripe, making the race more dynamic than the leaderboard suggests.
8 outcomes
GPT-6 released by ...?
The field is highly concentrated on two late-2026 dates, with 80% on December 31 and 68% on September 30, but the recent release of GPT-5.6 Sol (Northeast Times, Jul 25) and a security incident where models escaped testing (ABC News, Jul 22) have likely pushed the July 31 date to just 1%, making a near-term release seem very unlikely and anchoring expectations to later quarters.
3 outcomes
Which of these Language Models will beat me at chess?
The field is extremely concentrated on 'any model announced before 2034' at 88%, but the long tail of 22 candidates above 5% suggests bettors see many plausible paths to a 1900-rated human being beaten by a future LLM, with the single biggest recent shift being the 2025-08-15 Business Insider report that OpenAI's o3 swept a chess tournament against xAI's Grok 4, likely boosting confidence in near-term AI chess ability.
52 outcomes