doca-pcc: worth installing? Reported results

Reported results for doca-pcc (NVIDIA/skills) from NVIDIA, one row per receipt, in plain words.

Skill skills/doca-pcc in NVIDIA/skills.

One row per receipt. No figure on this page combines two rows.

Reported by: Reported by NVIDIA in its benchmark card
Model: Claude Opus 4.8 (aws/anthropic/bedrock-claude-opus-4-8, as the source names it)
Harness: claude-code, version not stated
Date: 2026-07-26
Tasks and runs: 4 tasks, as printed
Result: NVIDIA reported figures per dimension only (1 attempt per task). The card prints each uplift as a bare percent and does not say whether it is points or a share of the baseline. Security: 100% (+0%) Correctness: 100% (+35%) Discoverability: 100% (+38%) Effectiveness: 88% (+54%) Efficiency: 94% (+45%)
Tokens: token use not recorded
Freshness: Reported on Opus 4.8. Registered opus models released after this run, as of the build date: Opus 5.5.
Skill commit: 14a98ae278cec7e867695189d0f4003c08e4f765
Receipt: doca-pcc-aws-anthropic-bedrock-claude-opus-4-8-imported-nvidia-cards-claude-code-2026-07-26-466f045457f9.json

Reported by: Reported by NVIDIA in its benchmark card
Model: GPT-5.5 (openai/openai/gpt-5.5, as the source names it)
Harness: codex, version not stated
Date: 2026-07-26
Tasks and runs: 4 tasks, as printed
Result: NVIDIA reported figures per dimension only (1 attempt per task). The card prints each uplift as a bare percent and does not say whether it is points or a share of the baseline. Security: 100% (+0%) Correctness: 100% (+35%) Discoverability: 95% (+39%) Effectiveness: 94% (+46%) Efficiency: 98% (+58%)
Tokens: token use not recorded
Freshness: Reported on GPT-5.5. Freshness unknown: the registry has no release date for it.
Skill commit: 14a98ae278cec7e867695189d0f4003c08e4f765
Receipt: doca-pcc-openai-openai-gpt-5-5-imported-nvidia-cards-codex-2026-07-26-466f045457f9.json

Built on 2026-10-15 from committed receipts.