Unverified50% confidenceFactExact time
Two models with an Elo difference of 80 points have a win rate difference of approximately 11 to 13 percentage points in head-to-head matchups.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the Elo system, a rating difference of 400 points means the stronger player's expected win rate is approximately 91%, with player A's winning probability being 1/(1+10^((Rb-Ra)/400)).67% similarUnverifiedIn the Elo rating system, when the score difference between two models is within 30–50 points, they are generally considered to be at a statistically indistinguishable level.65% similarUnverifiedThe power-law exponent between test loss and compute is approximately 0.05, meaning that every 10x increase in compute yields approximately a 12% improvement in model performance.63% similarUnverified当两个模型的配对比较次数低于约200-300次时，其Elo分数的置信区间会显著扩大63% similarUnverifiedThe solve rate of current top AI models on SWE-bench remains far below the level implied by their competition performance.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/977799API
curl https://kongchang.com/api/v1/knowledge/claims/977799MCP
get_claim(id=977799)