Jev Benchmark / Evaluation Report
Jev Support Ticket Routing Benchmark
A transparent fixture measuring categorical routing accuracy, tail latency, cost per 1k decisions, and human fallback trade-offs on labeled customer queries.
Reproducible Evaluation Protocol
We freeze the 4-queue schema (billing, technical, sales, abuse) with strict criteria definitions. Each test query is evaluated against human ground truth and frontier LLM consensus (GPT-6 Astra & Claude Fable 5.1). Full probabilities, confidence scores, and round-trip execution durations are captured.
Harness: Zero prompt bloat, native typed contract (TypeSafe System One Adapter)
Metric Scope: Macro F1 (Macro Precision & Recall harmonic mean), P95 Latency, Cost / 1k decisions
Consensus Agreement vs Ground Truth
Official vendor evals measure consensus agreement with high-reasoning frontier models. Our test reports both human ground-truth Macro F1 and agreement rates. Benchmark scores do not replace domain-specific calibration before setting production SLAs.
Jev vs Frontier LLMs Performance Matrix
Cross-evaluating categorical precision, latency, and cost across identical decision contracts.
| Model / Architecture | Accuracy / Agreement | Macro F1 | P95 Latency | Cost / 1k | Architectural Notes |
|---|---|---|---|---|---|
Jev (jev-1.13 / jev-latest) | 76.0% (Agreement) / 78.4% (F1) | 78.4% | 410 ms | $0.021 | Fastest and cheapest; parallel softmax probabilities without autoregressive generation tokens. |
GPT-5.6 Terra | 78.3% (Agreement) / 78.6% (F1) | 78.6% | 10,120 ms | $1.600 | Near parity in accuracy; 25x slower latency due to reasoning chain token generation. |
GPT Sol (Reasoning) | 78.3% (Agreement) / 81.2% (F1) | 81.2% | 23,300 ms | $4.180 | Highest precision on compound ambiguity; prohibitive cost and latency for online webhooks. |
Claude Opus 5 | 79.2% (Agreement) / 82.1% (F1) | 82.1% | 37,800 ms | $8.805 | Deepest edge case discernment; best suited for offline audits rather than front-door ingress. |
Claude Haiku 4.5 | 53.6% (Agreement) / 54.2% (F1) | 54.2% | 12,500 ms | $0.975 | Frequent category overlap between technical malfunction and account billing inquiries. |
Gold Dataset Slices & Coverage
Curated from anonymized multi-turn SaaS helpdesk tickets, cross-validated by tier-3 support engineers and aligned with the official TypeSafe Customer Service eval slice.
Double charges, invoice adjustments, payment gateway declines, refund demands
API rate limits, SDK runtime crashes, 5xx outages, webhooks signature verification
Enterprise plan inquiries, seat add-ons, annual discounts, feature trials
Phishing reports, token exfiltration complaints, unauthorized team invites
Cross-Category Misclassification
Rows = Predicted class, Columns = Ground truth class:
| Pred \ Truth | Billing | Technical | Sales | Abuse |
|---|---|---|---|---|
| Billing | 63 | 2 | 2 | 0 |
| Technical | 3 | 56 | 3 | 1 |
| Sales | 2 | 3 | 42 | 0 |
| Abuse | 0 | 1 | 1 | 25 |
Optimal Routing Automation Curve
By calibrating the confidence threshold, teams can decide what proportion of support volume is automated immediately versus routed to human specialists.
Representative Case Analyses
Examining model behavior and calibrated confidence on clear-cut vs compound queries.
Case 1: Ambiguous Refund Request Caused by Outage
Trigger FallbackContains both Technical root cause (502s) and Billing demand (invoice credit). Jev correctly chose Billing but lowered confidence to 0.68. Under our threshold rule, this moves to human review, preventing inappropriate automated bot replies.
Case 2: Direct Enterprise Seat Expansion
AccurateUnambiguous sales intent with explicit enterprise volume keywords. High confidence (0.96) triggers immediate webhook dispatch to the account executive team.
Run This Benchmark in Local Node.js
Install dependencies with `pnpm add @ai-sdk/typesafe @ai-sdk/provider`. Run against your test CSV or JSON suite using Node 22+ or Bun.
import { experimental_evaluate } from '@ai-sdk/typesafe';
const TICKET_ROUTING_SCHEMA = {
department: {
type: 'choice',
instructions: 'Determine the primary department responsible for resolving this customer ticket.',
criteria: {
billing: 'Questions regarding invoices, payment failures, duplicate charges, or refunds.',
technical: 'Software bugs, API failures, service outages, or integration errors.',
sales: 'Inquiries about plan upgrades, enterprise pricing, seat additions, or contract renewals.',
abuse: 'Reports of phishing, spam, Terms of Service violations, or malicious activity.',
},
},
};
export async function runRoutingEval(ticket: string) {
const t0 = performance.now();
const result = await experimental_evaluate({
model: 'jev-latest',
state: { ticketText: ticket },
questions: TICKET_ROUTING_SCHEMA,
});
const durationMs = Math.round(performance.now() - t0);
return {
choice: result.answers.department.value,
confidence: result.providerMetadata?.typesafe?.confidence?.department ?? result.answers.department.confidence,
probabilities: result.answers.department.probabilities,
durationMs,
};
}Benchmark & System One FAQs
Why does Jev achieve similar accuracy to GPT-5.6 Terra at 1/76th the cost?
LLMs generate routing decisions by autoregressively sampling hundreds of hidden reasoning tokens before outputting a JSON label. Jev evaluates classification boundaries natively in parallel, mapping input representations directly to output probability distributions without conversational overhead.
What is the recommended confidence cutoff for customer ticket automation?
For tier-1 SaaS ticketing, we recommend setting the auto-routing gate at 0.85 confidence. This automates approximately 78% of incoming volume with over 94% categorical precision, diverting tricky cross-cutting disputes to human staff.
Explore More Jev Benchmarks & Tools
Jev Spam Detection & Moderation Benchmark
A task-level evaluation isolating false positives, stealth marketing evasion, inference latency, and quarantine queue trade-offs.
Jev Prompt Injection & Safety Defense Benchmark
An adversarial benchmark evaluating defense against instruction overrides, tool hijack attempts, context poisoning, and benign instruction preservation.
Prompt Injection Defense Recipe
Deploy zero-generation security middleware, gateway adapters, and test attack vectors in the interactive sandbox.
Run Live in Playground
Test Jev decision models live with zero setup. Inspect real-time probabilities and confidence scores.