BANT lead qualifier

▦

Sales

Score any inbound lead (call note, email thread, or form) on Budget, Authority, Need, Timeline and return a qualified / not-yet verdict with the gaps to chase.

The routing recipe

Job typeStructured extractionPolicyBalanced

routes to

Qwen3 Coder 480B-A35B Instruct nvidia

nvidia:qwen/qwen3-coder-480b-a35b-instruct

86.3

match score

87.1

task fit

100

cost

62.9

speed

Why this model from benchmarks & capabilities

"Structured extraction" leans hardest on instruction; Qwen3 Coder 480B-A35B Instruct scores 91/100 there — #10 of 32.
Strength on this class of work shows up on IFEval, IFBench (instruction following), where Qwen (Alibaba) models are competitive.
Cost: runs on NVIDIA free credits / self-hostable NIM — effectively $0 marginal. Speed: ~90 tok/s (estimated).
Chosen over GPT-OSS 120B for cheaper & more context.

Capability the job needs	Weight	Qwen3 Coder 480B-A35B Instruct	Catalog rank
instruction	1.00	91	#10 of 32
tool_use	0.60	100	#2 of 32
speed	0.60	63	#17 of 32

Relevant benchmarksIFEval IFBench (instruction following) EconomicsCost: runs on NVIDIA free credits / self-hostable NIM — effectively $0 marginal.
Speed: ~90 tok/s (estimated). vs runner-upChosen over GPT-OSS 120B for cheaper & more context. (GPT-OSS 120B, score 84.7)

Example result

Sample input ▾

Inbound form + reply: 'We're a 60-person fintech, currently failing our SOC 2 Type II readiness. Our compliance lead asked me (VP Eng) to find tooling before our December audit. We have budget approved up to ~$30k/yr.'

{ "budget": {"score":3, "evidence":"~$30k/yr approved"}, "authority":{"score":2, "evidence":"VP Eng sourcing; compliance lead is sponsor; approver unnamed"}, "need": {"score":3, "evidence":"Failing SOC 2 Type II readiness"}, "timeline": {"score":3, "evidence":"December audit"}, "qualified": true, "missing": ["final approver", "current tooling/incumbent"], "recommended_action": "Fast-track demo this week; confirm the economic buyer before proposal." }

Test it on your own data