✓
Meeting action extractor
OperationsPull decisions and action items — with owner and due date — out of messy meeting notes or a transcript, ready to paste into your tracker.
The routing recipe
Job typeStructured extractionPolicyCheapest that passes
routes to
GPT-OSS 20B groq
groq:openai/gpt-oss-20b
93.1
match score
80.9
task fit
100
cost
96.4
speed
Why this model from benchmarks & capabilities
- "Structured extraction" leans hardest on instruction; GPT-OSS 20B scores 78/100 there — #23 of 40.
- Strength on this class of work shows up on IFEval, IFBench (instruction following), where OpenAI (open-weight) models are competitive.
- Cost: free tier. Speed: ~1000 tok/s on Groq LPU.
- Chosen over Qwen3 Coder 480B-A35B Instruct for faster.
| Capability the job needs | Weight | GPT-OSS 20B | Catalog rank |
|---|---|---|---|
| instruction | 1.00 | #23 of 40 | |
| tool_use | 0.60 | #25 of 40 | |
| speed | 0.60 | #1 of 40 |
Relevant benchmarksIFEval IFBench (instruction following)
EconomicsCost: free tier.
Speed: ~1000 tok/s on Groq LPU. vs runner-upChosen over Qwen3 Coder 480B-A35B Instruct for faster. (Qwen3 Coder 480B-A35B Instruct, score 91.9)
Speed: ~1000 tok/s on Groq LPU. vs runner-upChosen over Qwen3 Coder 480B-A35B Instruct for faster. (Qwen3 Coder 480B-A35B Instruct, score 91.9)
Example result
Sample input ▾
…so we agreed to ship the Cloudflare provider this week. Priya will own the pricing-page update, hopefully by Friday. Someone needs to email the design partner about the demo — Dana said she'd take that next Tuesday. We punted the SSO work to next sprint.
DECISIONS:
• Ship the Cloudflare provider this week.
• Defer SSO work to next sprint.
ACTIONS:
• [Priya] Update the pricing page — due Fri.
• [Dana] Email the design partner about the demo — due Tue.
Test it on your own data