Backend Bench
Frontier
BackendBench environment for LLM kernel benchmarking
- Domain
- rl-env
- License
- unknown
- Published
- Mar 2026
Cite
Notes
Only stored in your browser.
Top score 38.9% by gpt-oss-120b - 3 models reporting (3 frontier)
Score history
3Top models
3
Related tools
1Implementations, trainers, datasets and scaffolds linked to this eval.
FAQ
- What is Backend Bench?
- BackendBench environment for LLM kernel benchmarking
- What is the current top score on Backend Bench?
- The top reported score is 38.9% by gpt-oss-120b, across 3 models reporting (3 from frontier labs).
- How can a model improve its Backend Bench score?
- Tools linked to Backend Bench on Sophon include Backend Bench RL Env (Prime Community) - RL environments, datasets, and scaffolds that target this eval.
- What license is Backend Bench under?
- Backend Bench is available under unknown.