InferenceBench

Qwen/Qwen2-VL-7B-Instruct

vllm unknown on 8x NVIDIA H100 80GB HBM3 (fp16) · seed 0 · run 019e3b85-fc73-7f06-b94d-d553f9b579a4 · signed

Headline metrics

TTFT P50 (ms) 29.44
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 150
total_p50_ms 177
ttft_p50_ms 29.44

Provenance

Model revisionunknown00
Providervllm
Hardware fingerprint550474fc9132129654f5d20c316eaffec99a1f67c0cc0b4641e60efb46ea79e7
Datasetbuiltin-factual-mini · e5232bb18b090369b2ecf5029d03a22847760b5f2839779afa65cbfef67ba948
Timestamp2026-05-18T14:38:17.203276+00:00
Envelope JSON77ee6cc698ab.json

Verify this result

bench verify /bench/leaderboard/envelopes/77ee6cc698ab.json

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