InferenceBench

meta-llama/Llama-3.1-70B-Instruct

vllm unknown on 8x NVIDIA H100 80GB HBM3 (fp16) · seed 0 · run 019e3b92-bf6e-7d98-9607-c9409191ccbc · signed

Headline metrics

TTFT P50 (ms) 33.45
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
drift_rate 0.0000
n_ok 5.00
n_samples 5.00
ok_rate 1.00
persona_consistency_mean 1.00
persona_consistency_p50 1.00
persona_consistency_p95 1.00
tokens_out_total 1,861
total_p50_ms 8,592
ttft_p50_ms 33.45

Provenance

Model revisionunknown00
Providervllm
Hardware fingerprint550474fc9132129654f5d20c316eaffec99a1f67c0cc0b4641e60efb46ea79e7
Datasetpersona-consistency-mini · ac864a018c1eb985c7f697a997162da20039e99fff11927ec3139fa4f2d4e9e3
Timestamp2026-05-18T14:52:13.550512+00:00
Envelope JSON15f036c3e160.json

Verify this result

bench verify /bench/leaderboard/envelopes/15f036c3e160.json

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