AI beats human baseline on PostTrainBench by 1 Oct 2026?
56
1ká¹€9205Oct 6
59%
chance
9
1H
6H
1D
1W
1M
ALL
Jack Clark predicts YES: https://importai.substack.com/p/import-ai-439-ai-kernels-decentralized.
Resolves to YES if any LLM released prior to 1 Oct 2026 exceeds the human baseline of 61.77% on https://posttrainbench.com/. Reasonable time (to at most 1 Nov) will be given after the deadline in case a model is released close to the deadline that might do it. Result does not have to appear on posttrainbench.com per se but needs to be credible, and not contradicted by the website.
Resolves to NO if this does not occur.
Esta pergunta é gerenciada e resolvida pela Predita.
Get 
1,000 to start trading!
1,000Ordenar por:
Paper is out: https://arxiv.org/abs/2603.08640
And more models have been added: https://posttrainbench.com/
Looks like the human baseline (now labeled Official Instruct Models) has changed as well
Pessoas também estão operando
Perguntas relacionadas
Chatbot Arena: How high will AI score in 2026?
Will AIs beat human experts in question-answering on the GPQA benchmark before January 1st, 2027?
95% chance
In what year will AI achieve a score of 95% or higher on the PhysBench leaderboard?
2036
AI beats Minecraft (RSG) in under 10 minutes before 2027?
13% chance
Will an AI achieve >80% performance on the FrontierMath benchmark before 2027?
45% chance
AI model achieves superhuman ELO on Codeforces by June 1st 2027?
69% chance
AI beats Portal 2 Cooperative mode with a human (or itself) by what date?
2028
AI outperforms humans in all mathematical research areas by 2028?
16% chance
In what year will AI achieve a score of 85% or higher on the SimpleBench leaderboard?
7/20/32
Benchmark Gap #3: Once a model achieves superhuman performance on a competitive programming benchmark, will it be less than 2 years before there are "entry level" AI programmers in industry use?
78% chance