nemo-relay-get-started: worth installing? Reported results

Reported results for nemo-relay-get-started (NVIDIA/skills) from NVIDIA, one row per receipt, in plain words.

Skill skills/nemo-relay-get-started 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: 2026-08-21
Tasks and runs: 15 tasks, as printed
Result: NVIDIA reported +39 points overall (1 attempt per task). Overall: 49% → 88% (+39 points) Security: 100% → 100% (±0 points) Correctness: 23% → 92% (+69 points) Discoverability: 51% → 95% (+44 points) Effectiveness: 27% → 68% (+40 points) Efficiency: 44% → 84% (+40 points)
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: nemo-relay-get-started-aws-anthropic-bedrock-claude-opus-4-8-imported-nvidia-cards-claude-code-2026-08-21-59faad1aefb4.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: 2026-08-21
Tasks and runs: 15 tasks, as printed
Result: NVIDIA reported +32 points overall (1 attempt per task). Overall: 51% → 83% (+32 points) Security: 73% → 90% (+17 points) Correctness: 68% → 89% (+21 points) Discoverability: 44% → 90% (+45 points) Effectiveness: 42% → 70% (+27 points) Efficiency: 27% → 76% (+49 points)
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: nemo-relay-get-started-openai-openai-gpt-5-5-imported-nvidia-cards-codex-2026-08-21-59faad1aefb4.json

Built on 2026-10-15 from committed receipts.