InferenceBench

Qwen/Qwen2.5-Coder-7B-Instruct

vllm unknown on 8x NVIDIA H100 80GB HBM3 (fp16) · seed 0 · run 019e3b3f-a902-7a6c-b6cc-b8ec0c603d14 · signed

Headline metrics

TTFT P50 (ms) 18.07
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 971
total_p50_ms 1,261
ttft_p50_ms 18.07

Provenance

Model revisionunknown00
Providervllm
Hardware fingerprint550474fc9132129654f5d20c316eaffec99a1f67c0cc0b4641e60efb46ea79e7
Datasetbuiltin-mbpp-mini · 9dd0eb0ef0d05cee08d36b6485ebf2855f24e2ecb863cd704393a0edbd38d1a9
Timestamp2026-05-18T13:21:28.322681+00:00
Envelope JSON91867f6c7bb5.json

Verify this result

bench verify /bench/leaderboard/envelopes/91867f6c7bb5.json

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