Compare runs
cohort sha256:7725b3f8e7e7abbb… · source-native profile
ranking-v1
no ranks: not comparable
Comparison identity
operation
045-audio-encoder-to-language-model-multimodal-fusion
workload
suite of 16 cases · mean latency · 83418c82
protocol
SOL-ExecBench evaluation stack · 2964c5c4
environment
NVIDIA B200 · 5296c820
correctness policy
d2595bd5
metric
latency mean (ns)
Context · 10 fields›
architecture
sm_100
CUDA
unknown
driver
unknown
framework
unknown
samples
unknown
evidence
reported
license
unknown
source
unavailable
status
passed
observed
2026-06-26
No winner: these runs didn't measure the same thing. The rows above show what differs. Why comparable?
Add run ›
Export ›
Markdown CSV JSON
doubleAI · sha256:15041c74f5c79… · observed 2026-06-26