Implicit IntelligenceAgents respond to requests whose unstated requirements affect safety, privacy, or accessibility. Labelbox reports the share of scenarios each model passes.
General assistants
53.2%
Not in cards
Labelbox Complex ReasoningModels solve reasoning problems in mathematics, programming, and other domains. Labelbox reports overall and domain scores.
Language reasoning
Jul 2025
89.6%
Not in cards
R-ConstraintBenchModels produce feasible operational plans as constraints accumulate. The score gives more weight to harder levels.
Running a business
Aug 2025
79.2%
Not in cards
Labelbox Agentic SearchAgents search for answers to 200 questions across several knowledge domains. Labelbox reports overall and domain scores.
Questions that need search
Jun 2025
80%
Not in cards
Labelbox Deep Research AgentsAgents investigate research questions at the doctoral level. Labelbox compares their answers and reports scores by domain.
Deep research
Jul 2025
77.5%
Not in cards
EchoChainVoice agents reason through spoken exchanges while a speaker interrupts or changes instructions. The score measures whether the agent responds correctly.
Audio understanding and voice
Mar 2026
44%
Not in cards
Arenas without a leaderboard here
Name
Kind
Released
Best score
Status
Labelbox Video Generation v2Models generate videos from text prompts. Human raters compare the outputs for visual quality and adherence to the prompt.
Labelbox Speech Generation v2Models generate speech from text. Human raters compare the outputs for quality and naturalness.
Speech recognition and translation
Dec 2024
Not in cards
Labelbox Video Generation (original)Models generate videos from text prompts. Human raters compare the outputs for visual quality and adherence to the prompt.