InferenceBench

Qwen/Qwen2.5-7B-Instruct

vllm unknown on 8x NVIDIA H100 80GB HBM3 (fp16) · seed 0 · run 019e3b39-f3e2-7ab8-b53b-bf860dcbec21 · signed

Headline metrics

TTFT P50 (ms) 14.67
TTFT P99 (ms)
Throughput (tok/s)
$/M tokens
J/token
Power avg (W)
Power peak (W)
WER mean
J / audio s

All metrics

n_ok 5.00
n_samples 5.00
ok_rate 1.00
pass_at_1 1.00
pass_at_1_p05 1.00
pass_at_1_p50 1.00
pass_at_1_p95 1.00
timeout_rate 0.0000
tokens_out_total 1,281
total_p50_ms 1,699
ttft_p50_ms 14.67

Provenance

Model revisionunknown00
Providervllm
Hardware fingerprint550474fc9132129654f5d20c316eaffec99a1f67c0cc0b4641e60efb46ea79e7
Datasetbuiltin-humaneval-mini · c9122e6eca7b960ed8a8dc8fcb40702b25024622a3ab90c546914b949193da06
Timestamp2026-05-18T13:15:14.274581+00:00
Envelope JSON658af3aec8ea.json

Verify this result

bench verify /bench/leaderboard/envelopes/658af3aec8ea.json

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