- 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
- 2026-09-11
- Tasks and runs
- 13 tasks, as printed
- Result
- NVIDIA reported a score of 93.6% overall and no uplift figure (3 attempts per task). Overall:
93.6% — baseline ran, but no comparable score was available; uplift unavailable
Security:100.0% → 100.0% (±0.0 points)
Correctness:92.3% → 98.5% (+6.2 points)
Discoverability:97.5% — baseline ran, but no comparable score was available; uplift unavailable
Effectiveness:69.2% → 79.9% (+10.7 points)
Efficiency:91.9% — baseline ran, but no comparable score was available; uplift unavailable
- Tokens
- 1,666,118 tokens with the skill and 1,251,598 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
- cudaq-guide-aws-anthropic-bedrock-claude-opus-4-8-imported-nvidia-cards-claude-code-2026-09-11-2889bbf53bef.json
cudaq-guide: worth installing? Reported results
Reported results for cudaq-guide (NVIDIA/skills) from NVIDIA, one row per receipt, in plain words.
Skill skills/cudaq-guide 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
- 2026-09-11
- Tasks and runs
- 13 tasks, as printed
- Result
- NVIDIA reported a score of 89.2% overall and no uplift figure (3 attempts per task). Overall:
89.2% — baseline ran, but no comparable score was available; uplift unavailable
Security:85.7% → 92.3% (+6.6 points)
Correctness:90.0% → 98.5% (+8.5 points)
Discoverability:92.0% — baseline ran, but no comparable score was available; uplift unavailable
Effectiveness:66.0% → 86.1% (+20.1 points)
Efficiency:77.1% — baseline ran, but no comparable score was available; uplift unavailable
- Tokens
- 1,861,622 tokens with the skill and 1,290,210 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
- cudaq-guide-openai-openai-gpt-5-5-imported-nvidia-cards-codex-2026-09-11-2889bbf53bef.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.