Unverified50% confidenceFactExact time
Inference energy consumption across different model and decoding configuration combinations spans from 0.79 MJ to 8.68 MJ, roughly equivalent to the energy of 250 to 2800 GPT-4.1 queries.
1
Sources
50%
Confidence
Long-term
Relevance
10/26/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe same parameter name reasoning_effort behaves differently across models from different vendors: in gpt-5.4-mini the median output tokens rose from 18 at none to 254 at high (×14.1); gpt-oss-120b rose from refusal to 1,340 (×4.6); claude-haiku-5.5 rose from 150 to 298 (×2.0); gemini-3.7-flash rose from 453 to 1,013 (×2.2).75% similarUnverifiedLarge language models that can run on-device typically have parameter scales of 1B to 13B, far smaller than cloud-based models such as GPT-4 or Claude with hundreds of billions of parameters.71% similarUnverifiedAccording to Logic42's Q3 2026 customer audit benchmark, brute-force GraphRAG (chained LLM) has an average query latency of 16400 milliseconds, 14800 tokens per query, a cost of $222 per 10,000 queries, and 89% relational accuracy.71% similarUnverifiedGPT-4o-mini scores about 18% accuracy on the same HS code benchmark; the best AI Agent with web search reaches 46.8%, but costs $1-10 per call and takes 10-30 seconds; human experts are about 95%.69% similarUnverifiedIn an A/B test on the same GPU, the traditional generative prompt had an average inference latency of 3,679.8ms, while the decision model (Decision Head) had 191.4ms.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1098282API
curl https://kongchang.com/api/v1/knowledge/claims/1098282MCP
get_claim(id=1098282)