BB
BIG-bench
Evaluation·infrastructure·open·#615 of 884·+49·Rising
66.0
Low
High confidence
Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models
Pillar Breakdown
Adoption
35%
73.3
Maintenance
30%
57.9
Friction
20%
94.0
Ecosystem
15%
44.4
Momentum
0.53Rising
7d change -0.24
High confidenceIn Evaluation
Ranked #31 of 57