Benchmark
JobBench
A benchmark for evaluating the performance of AI on occupational tasks.
Timeline (last 90 days)
Oct 17
Meta claims MuseSpark Open achieves open-source SOTA on agentic benchmarks such as JobBench and MCPAtlas.
Unverified50%
Oct 16
On the JobBench agent evaluation suite, Muse Spark Open scores 61.8, far exceeding the 31.1 of comparable competitor Inkling.
Unverified50%