THE RECORD
Benchmark updates
A dated record of source imports, corrections, and editorial changes.
42 use-case ranking entries added: searchArena · official dataset
165 use-case ranking entries added: visionArena · official dataset
140 use-case ranking entries added: codingArena · official dataset
48 use-case ranking entries added: videoArena · official dataset
82 use-case ranking entries added: imageArena · official dataset
416 use-case ranking entries added: textArena · official dataset
54 use-case ranking entries added: agentsArena · official dataset
54 use-case ranking entries added: overallArena · official dataset
34 use-case ranking entries added: searchArena · official dataset
165 use-case ranking entries added: visionArena · official dataset
139 use-case ranking entries added: codingArena · official dataset
48 use-case ranking entries added: videoArena · official dataset
82 use-case ranking entries added: imageArena · official dataset
414 use-case ranking entries added: textArena · official dataset
52 use-case ranking entries added: agentsArena · official dataset
52 use-case ranking entries added: overallArena · official dataset
34 use-case ranking entries added: searchArena · official dataset
165 use-case ranking entries added: visionArena · official dataset
139 use-case ranking entries added: codingArena · official dataset
48 use-case ranking entries added: videoArena · official dataset
82 use-case ranking entries added: imageArena · official dataset
414 use-case ranking entries added: textArena · official dataset
52 use-case ranking entries added: agentsArena · official dataset
52 use-case ranking entries added: overallArena · official dataset
48 use-case ranking entries added: videoArena · official dataset
82 use-case ranking entries added: imageArena · official dataset
414 use-case ranking entries added: textArena · official dataset
52 use-case ranking entries added: agentsArena · official dataset
52 use-case ranking entries added: overallArena · official dataset
108 result observations added from openevalsOpenEvals / Hugging Face
