Benchmark Almanac

Labelbox

We track 6 benchmarks and 7 arenas that Labelbox made or helped make.

0 in use 0 with public code 7 with a leaderboard here

Arena leaderboards

Top five in each of its 2 arenas with three or more rated models, the most rated first. We don't have a leaderboard yet for 5 others, listed below.

Benchmarks

Name Kind Released Best score Status
Implicit Intelligence Agents 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 Reasoning Models 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-ConstraintBench Models 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 Search Agents 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 Agents Agents 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
EchoChain Voice 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 v2 Models generate videos from text prompts. Human raters compare the outputs for visual quality and adherence to the prompt. Video generation Dec 2024 1,268 Not in cards
Labelbox Image Generation (original) Models generate images from text prompts. Human raters compare how well the outputs meet the request. Image generation and editing Sep 2024 Not in cards
Labelbox Speech Generation (original) Models generate speech from text. Human raters compare the outputs for quality and naturalness. Speech recognition and translation Sep 2024 Not in cards
Labelbox Speech Generation v2 Models 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. Video generation Sep 2024 Not in cards