InferenceBench

microsoft/Phi-3.5-mini-instruct

vllm unknown on 8x NVIDIA H100 80GB HBM3 (fp16) · seed 0 · run 019e3b5d-2482-754c-b3f9-bc5d986b6775 · signed

Headline metrics

TTFT P50 (ms) 11.24
TTFT P99 (ms)
Throughput (tok/s)
$/M tokens
J/token
Power avg (W)
Power peak (W)
WER mean
J / audio s

All metrics

accuracy 0.7500
accuracy_p05 0.0000
accuracy_p50 1.00
accuracy_p95 1.00
n_ok 8.00
n_samples 8.00
ok_rate 1.00
tokens_out_total 208
total_p50_ms 31.72
ttft_p50_ms 11.24

Provenance

Model revisionunknown00
Providervllm
Hardware fingerprint550474fc9132129654f5d20c316eaffec99a1f67c0cc0b4641e60efb46ea79e7
Datasetbuiltin-arithmetic-mini · 57f39a33ef4f155221fa496e4a096d8f2bed722273872dbd4013f98771621f26
Timestamp2026-05-18T13:53:40.482136+00:00
Envelope JSON4fa1e1b0190b.json

Verify this result

bench verify /bench/leaderboard/envelopes/4fa1e1b0190b.json

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