Unverified50% confidenceBenchmarkExact time
Ablation experiments on GPT-6-Luna show that QERA's gains are established before answer generation: the fixed answering protocol contributes 3.8 scoring points and request-specific questions contribute 1.6 scoring points.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/27/2026
First Seen
Valid until: 1/25/2027
Sources
Related Entities
Related Claims
UnverifiedIn the evaluation with seven held-out queries, the trained IRM achieved 4/7 correct on top-1 results, versus 3/7 for the identity-transform baseline.68% similarUnverifiedOn all 405 tasks, QERA achieves the highest solve rate across four frontier large models, averaging 21.0%; the strongest of the three inference-time baselines is 18.2%, and direct answering is 14.6%.68% similarUnverifiedIn agentgateway's testing, qwen3.8 (27.3B, Q4_K_M quantization, 262K context) had a valid answer rate of 90.0% (54/60), an accuracy rate among answered questions of 98.1% (53/54), and an overall accuracy rate of 88.3% (53/60).67% 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.66% similarUnverifiedOrder effect: swapping the order of two answers, GPT-5.4 changed its verdict 11.4% of the time on one benchmark and 10.5% on another; Gemini 3.1 Pro and Claude Opus 4.6 were between 2.0% and 3.8%.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1102093API
curl https://kongchang.com/api/v1/knowledge/claims/1102093MCP
get_claim(id=1102093)