InferenceBench

microsoft/Phi-3.5-mini-instruct

vllm unknown on 8x NVIDIA H100 80GB HBM3 (fp16) · seed 0 · run 019e3b5d-1176-7e5d-9ef9-98861cbb1681 · signed

Headline metrics

TTFT P50 (ms) 11.21
TTFT P99 (ms)
Throughput (tok/s)
$/M tokens
J/token
Power avg (W)
Power peak (W)
WER mean
J / audio s

All metrics

accuracy 1.00
accuracy_p05 1.00
accuracy_p50 1.00
accuracy_p95 1.00
n_ok 10.00
n_samples 10.00
ok_rate 1.00
tokens_out_total 943
total_p50_ms 500
ttft_p50_ms 11.21

Provenance

Model revisionunknown00
Providervllm
Hardware fingerprint550474fc9132129654f5d20c316eaffec99a1f67c0cc0b4641e60efb46ea79e7
Datasetbuiltin-factual-mini · e5232bb18b090369b2ecf5029d03a22847760b5f2839779afa65cbfef67ba948
Timestamp2026-05-18T13:53:35.606289+00:00
Envelope JSON9d3ae7a8bf8e.json

Verify this result

bench verify /bench/leaderboard/envelopes/9d3ae7a8bf8e.json

bench verify re-downloads this envelope, recomputes the canonical content hash, and validates the Sigstore signature against the embedded certificate + Rekor entry.