03RUNS
runsv2-smoke-20260425T175201Z
mistralcompletedv2 smoke
Mistral Nemo
mistralai/mistral-nemoHeadline
71.2/100
CI [49.5, 91.2]Cost
$0.0000
0 judge callsCases
7/12≥ 70%
2 failingPer-band breakdown
- HARD78.0n=7 · ci [49.4, 99.3]
- EXPERT66.2n=5 · ci [40.0, 92.4]
Cluster radar
Latency & throughput
- Total elapsed—
- Avg judge latency—
- Judge calls0
- Total spend$0.0000
- CompletedSat, 25 Apr 2026 17:52:01 GMT
Q0.976LATp50 1.2s · p95 2.7s · p99 5.1sJUDGEgpt-4.1-miniQ-DEPTH0$/EVAL$0.00014