Question

What will be the best performance on SWE-bench Verified by December 31st 2025?

Total Forecasters12

Community Prediction89.3 (83.3 - 94.1)

Make a Prediction

PDF

CDF

weight:

	lower 25%	median	upper 75%
community	83.3	89.34	94.08
My Prediction	—	—	—

Quartiles	community	My Prediction
lower 25%	83.3	—
median	89.34	—
upper 75%	94.08	—

Authors:

RyanBeck

Opened:

Dec 4, 2024

Closes:

Dec 31, 2025

Scheduled resolution:

Jan 1, 2026

AI 2025 Forecasting Survey

Artificial Intelligence

Is DeepSeek Just a Well-Timed PR Storm?

Observer (NY)•Feb 16, 2025

These researchers used NPR Sunday Puzzle questions to benchmark AI ‘reasoning’ models

TechCrunch•Feb 17, 2025

The hottest AI models, what they do, and how to use them

TechCrunch•Feb 18, 2025

Learn more about Metaculus NewsMatch

What will be the best performance on OSWorld by December 31st 2025?

70.8

What will be the best normalized score achieved on the original 7 RE-Bench tasks by December 31st 2025?

1.25

What will be the best performance on FrontierMath by December 31st 2025?

65.7

Comments

? comments