- 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
- 2026-09-17
- Tasks and runs
- 1 task, as printed
- Result
- NVIDIA reported a score of 94.5% overall and no uplift figure (3 attempts per task). Overall:
94.5% — baseline ran, but no comparable score was available; uplift unavailable
Security:100.0% → 100.0% (±0.0 points)
Correctness:0.0% → 100.0% (+100.0 points)
Discoverability:100.0% — baseline ran, but no comparable score was available; uplift unavailable
Effectiveness:16.7% → 100.0% (+83.3 points)
Efficiency:72.6% — baseline ran, but no comparable score was available; uplift unavailable
- Tokens
- 98,394 tokens with the skill and 120,129 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
- tao-setup-aws-anthropic-bedrock-claude-opus-4-8-imported-nvidia-cards-claude-code-2026-09-17-9d8ec833fa74.json
tao-setup: worth installing? Reported results
Reported results for tao-setup (NVIDIA/skills) from NVIDIA, one row per receipt, in plain words.
Skill skills/tao-setup 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
- GPT-5.5 (openai/openai/gpt-5.5, as the source names it)
- Harness
- codex, version not stated
- Date
- 2026-09-17
- Tasks and runs
- 1 task, as printed
- Result
- NVIDIA reported a score of 73.7% overall and no uplift figure (3 attempts per task). Overall:
73.7% — baseline ran, but no comparable score was available; uplift unavailable
Security:100.0% → 100.0% (±0.0 points)
Correctness:0.0% → 100.0% (+100.0 points)
Discoverability:0.0% — baseline ran, but no comparable score was available; uplift unavailable
Effectiveness:16.7% → 70.0% (+53.3 points)
Efficiency:99.5% → 98.6% (-0.9 points)
- Tokens
- 13,682 tokens with the skill and 41,805 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
- tao-setup-openai-openai-gpt-5-5-imported-nvidia-cards-codex-2026-09-17-9d8ec833fa74.json
Figures from NVIDIA/skills at commit 14a98ae278cec7e867695189d0f4003c08e4f765, licensed CC BY 4.0. Reformatted by Driftproof; NVIDIA does not endorse this page.
Built on from committed receipts.