Unverified50% confidenceBenchmarkExact time
On the Bing website, opencli instead used 31% more tokens than claude-in-chrome (353 vs 270), but this row has a sample size of fewer than 30 calls, so the conclusion is for reference only.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/15/2026
First Seen
Valid until: 10/29/2026
Sources
Related Entities
Related Claims
UnverifiedThe median tokens per call for opencli is 397, roughly on par with claude-in-chrome's text-only calls (373), with the entire gap between the two coming from screenshots.70% similarUnverifiedIn an evaluation of 30 answerable questions, off-the-shelf small models under 350MB achieved faithfulness (all assertions can be found in the passages) at most 3 times.67% similarUnverifiedOn the 35 prompts that the router kept local, Llama 3.2 1B's answers were judged acceptable 30 times (86%, average 4.4/5); on the 23 text prompts sent to the cloud, the same model was acceptable only 4 times (17%, average 2.0/5).64% similarUnverifiedOn pure reasoning tasks, Qwen3 27B scores only 30.8 on HLE, notably behind Opus's score of 40.0.63% similarUnverifiedCaveman's fixed benchmark test results from 54 runs show a 33.2% reduction in input tokens, with all 18/18 correctness checks passing.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1033228API
curl https://kongchang.com/api/v1/knowledge/claims/1033228MCP
get_claim(id=1033228)