priorsBuilder

Cognition

SWE 2

Measured on 2 benchmarks.

General frontier

Not ranked in this mix — too little measured data for its benchmarks.

Your mix’s benchmarks

0 of 8 measured

This model has no results on your mix’s benchmarks.

All 2 benchmarks

show 2 more

coding

FrontierCode 1.1 Extended

130 results
  1. #15max of 13062.5%
  2. #29high of 13060.1%
  3. #53medium of 13056.4%

Leader: Opus 5.5 · 65.3%

coding

FrontierCode 1.1 Main

130 results
  1. #17max of 13050.0%
  2. #36high of 13047.2%
  3. #52medium of 13043.1%

Leader: Opus 5.5 · 54.6%