nv-segment-ct-finetune: worth installing? Reported results

Reported results for nv-segment-ct-finetune (NVIDIA/skills) from NVIDIA, one row per receipt, in plain words.

Skill skills/nv-segment-ct-finetune 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: 2026-09-14
Tasks and runs: 4 tasks, as printed
Result: NVIDIA reported a score of 92.1% overall and no uplift figure (3 attempts per task). Overall: 92.1% — baseline ran, but no comparable score was available; uplift unavailable Security: 100.0% → 100.0% (±0.0 points) Correctness: 56.0% → 95.0% (+39.0 points) Discoverability: 99.0% — baseline ran, but no comparable score was available; uplift unavailable Effectiveness: 35.3% → 85.4% (+50.1 points) Efficiency: 81.1% — baseline ran, but no comparable score was available; uplift unavailable
Tokens: 602,120 tokens with the skill and 1,622,017 without, over all cases, as printed; the card gives no cost
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: nv-segment-ct-finetune-aws-anthropic-bedrock-claude-opus-4-8-imported-nvidia-cards-claude-code-2026-09-14-eace8176f041.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: 2026-09-14
Tasks and runs: 4 tasks, as printed
Result: NVIDIA reported a score of 92.9% overall and no uplift figure (3 attempts per task). Overall: 92.9% — baseline ran, but no comparable score was available; uplift unavailable Security: 75.0% → 100.0% (+25.0 points) Correctness: 95.0% → 95.0% (±0.0 points) Discoverability: 86.3% — baseline ran, but no comparable score was available; uplift unavailable Effectiveness: 80.4% → 86.7% (+6.3 points) Efficiency: 96.3% — baseline ran, but no comparable score was available; uplift unavailable
Tokens: 451,929 tokens with the skill and 781,810 without, over all cases, as printed; the card gives no cost
Freshness: Reported on GPT-5.5. Freshness unknown: the registry has no release date for it.
Skill commit: 14a98ae278cec7e867695189d0f4003c08e4f765
Receipt: nv-segment-ct-finetune-openai-openai-gpt-5-5-imported-nvidia-cards-codex-2026-09-14-eace8176f041.json

Built on 2026-10-15 from committed receipts.