Unverified50% confidenceBenchmarkExact time
Deal Pilot achieved a 6.0% reply rate across 644 A/B-tested emails.
1
Sources
50%
Confidence
Long-term
Relevance
11/7/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedZero-shot Qwen2.5-VL-3B-Instruct achieved a full-invoice exact rate of 5.3% and an auto-approval rate of 8.1% on the test set; the OCR + rules baseline achieved a full-invoice exact rate of 37.8% and an auto-approval rate of 55.0%.59% similarUnverifiedThe prompt token counts for the four successful reviews were Sentinel 5,095, Vuln-Scanner 5,365, Bloom 5,149, and Wiper 24,372, with response tokens of 1,820, 1,764, 1,974, and 1,605 respectively; the probe cost 443 prompt and 1,009 response tokens.58% similarUnverifiedCaveman's fixed benchmark test results from 54 runs show a 33.2% reduction in input tokens, with all 18/18 correctness checks passing.57% similarUnverifiedTesting with the Qwen model yielded consistent conclusions, with the token approach achieving 67.0% accuracy versus 64.8% for real data.57% similarUnverifiedIn agentgateway's testing, claude-sonnet-5 had a valid answer rate of 98.3% (59/60), an accuracy rate among answered questions of 93.2% (55/59), and an overall accuracy rate of 91.7% (55/60), with a latency p50 of 1080ms, p95 of 1412ms, and a cost of $0.000704 per call.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1146220API
curl https://kongchang.com/api/v1/knowledge/claims/1146220MCP
get_claim(id=1146220)