TENSORTEST / BENCHMARKS
Benchmarks for real work.
Each benchmark is built from complete professional jobs and graded on the finished work. TimelineBench is live, CharacterBench has its first study out, and three more are in progress.
TimelineBench ↗
Can AI agents complete real video editing jobs, from raw footage to final cut?
- 56jobs
- 16agent setups
- 93%claimed success
- 14.0%resolved
CharacterBench ↗
Can models build an editable 3D character in Blender from an artist’s reference images?
Read the first study ↗IN PROGRESS
Suggest a domain ↗- 03 / 3D ANIMATION
3D animation
Evaluating agents on the craft of bringing characters to life.
Coming soon - 04 / LANGUAGE
Copywriting
How AI handles creative writing for real briefs.
Coming soon - 05 / AI RESEARCH
Recursive self-improvement
Studying how AI systems can improve other AI systems.
Coming soon
WHAT EVERY BENCHMARK HAS
Three tests before a run counts.
- 01 / WHOLE JOBS
The task is the full job
Each task is a complete piece of work from start to finish, with the same inputs a professional would get.
- 02 / HARD CHECKS
Broken work fails
A run fails if the delivery is broken, content is missing or the brief is ignored, however confident the agent sounds when it stops.
- 03 / CALIBRATED QUALITY
Professionals set the bar
Work that passes is scored by a quality test calibrated on blind judgments from people who do the job.