Will Claude Sonnet 5 achieve a SOTA score on SciPredict?
3
Ṁ100Ṁ120Dec 31
64%
chance
1H
6H
1D
1W
1M
ALL
Benchmark is here: https://scale.com/leaderboard/scipredict. It tests models' ability to predict the results of scientific experiments. As of writing, current SOTA is Gemini 3 Pro's 25.27%.
This question is managed and resolved by Manifold.
Market context
Get 
1,000 to start trading!
1,000People are also trading
Related questions
What will be true of the SOTA AI on the FrontierMath benchmark, before 2027?
Will Claude Sonnet 5 exceed 85% on SWE-bench verified?
16% chance
[Carlini questions] SOTA AI scores better than X% of other participants in competitive programming contest by 2030
95.2
[Carlini questions] SOTA AI scores better than X% of other participants in competitive programming contest by 2027
91.5
Will Anthropic’s next Sonnet model exceed 83% on SWE-bench verified?
60% chance
BIG-bench accuracy 75% #5: Will SOTA for a single model on BIG-bench pass 75% by the start of 2028?
87% chance
What will be true of the SOTA AI on the FrontierMath benchmark, before 2028?
When will SOTA for Atari 100k pass human median and mean score on all 57 games?
BIG-bench accuracy 75% #4: Will SOTA for a single model on BIG-bench pass 75% by the start of 2027?
86% chance
MMLU 99% #4: Will SOTA for MMLU (average) pass 99% by the start of 2027?
8% chance