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

DiffusionGemma 26B-A4B nvidia

nvidia:google/diffusiongemma-26b-a4b-it

87.8

match score

78.5

task fit

100

cost

97.7

speed

Why this model from benchmarks & capabilities

"Structured extraction" leans hardest on instruction; DiffusionGemma 26B-A4B scores 76/100 there — #40 of 54.
Strength on this class of work shows up on IFEval, IFBench (instruction following), where Google models are competitive.
Cost: runs on NVIDIA free credits / self-hostable NIM — effectively $0 marginal. Speed: ~1100 tok/s (estimated).
Chosen over Nemotron 3.5 Lightning 30B-A3B for faster.

Capability the job needs	Weight	DiffusionGemma 26B-A4B	Catalog rank
instruction	1.00	76	#40 of 54
tool_use	0.60	68	#47 of 54
speed	0.60	97	#1 of 54

Relevant benchmarksIFEval IFBench (instruction following) EconomicsCost: runs on NVIDIA free credits / self-hostable NIM — effectively $0 marginal.
Speed: ~1100 tok/s (estimated). vs runner-upChosen over Nemotron 3.5 Lightning 30B-A3B for faster. (Nemotron 3.5 Lightning 30B-A3B, score 87.2)

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