◇
Trust center FAQ writer
ComplianceAnswer a prospect’s security question for your public trust center — accurate, confident, and honestly non-committal where it should be.
The routing recipe
Job typeGeneral chat / assistantPolicyBalanced
routes to
GPT-OSS 20B groq
groq:openai/gpt-oss-20b
87.1
match score
77.7
task fit
100
cost
96.4
speed
Why this model from benchmarks & capabilities
- "General chat / assistant" leans hardest on instruction; GPT-OSS 20B scores 78/100 there — #23 of 40.
- Strength on this class of work shows up on LMArena Elo, MT-Bench, IFEval, where OpenAI (open-weight) models are competitive.
- Cost: free tier. Speed: ~1000 tok/s on Groq LPU.
- Chosen over NVIDIA Nemotron 3 Super 120B-A12B for faster.
| Capability the job needs | Weight | GPT-OSS 20B | Catalog rank |
|---|---|---|---|
| instruction | 0.80 | #23 of 40 | |
| knowledge | 0.60 | #26 of 40 | |
| speed | 0.60 | #1 of 40 |
Relevant benchmarksLMArena Elo MT-Bench IFEval
EconomicsCost: free tier.
Speed: ~1000 tok/s on Groq LPU. vs runner-upChosen over NVIDIA Nemotron 3 Super 120B-A12B for faster. (NVIDIA Nemotron 3 Super 120B-A12B, score 85.3)
Speed: ~1000 tok/s on Groq LPU. vs runner-upChosen over NVIDIA Nemotron 3 Super 120B-A12B for faster. (NVIDIA Nemotron 3 Super 120B-A12B, score 85.3)
Example result
Sample input ▾
Prospect asks: "Do you encrypt data at rest, and who can access production data?"
Yes. All customer data is encrypted at rest using AES-256 and in transit using TLS 1.2+. Access to production is restricted to a small set of authorized engineers via SSO with MFA, granted on a least-privilege basis and reviewed quarterly. Production access is logged and monitored, and is revoked promptly when no longer needed. We can share more detail under NDA, including our latest SOC 2 report.
Test it on your own data