JobBench
Progress Over Time
Interactive timeline showing model performance evolution on JobBench
State-of-the-art frontier
Open
Proprietary
JobBench Leaderboard
2 models
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Xiaomi | 1.0T | 1.0M | $0.43 / $0.87 | ||
| 2 | Xiaomi | 309B | 1.0M | $0.14 / $0.28 |
Notice missing or incorrect data?
What is JobBench?
JobBench evaluates agents on work-related tasks, as reported in the MiMo-V2.6 release.
JobBench is a text benchmark evaluating models on knowledge, productivity, and agents tasks. LLM Stats tracks 2 models on this benchmark, scored on a 0–1 scale. The current average is 0.6, with the leader at 0.6.
Compare leaders on the best AI for knowledge, best AI for productivity and best AI for agents leaderboards.
Current leaders
MiMo-V2.6-Pro from Xiaomi currently leads the JobBench leaderboard with a score of 0.620 across 2 evaluated AI models.
FAQ
Common questions about the JobBench benchmark and leaderboard.