Unverified50% confidenceBenchmarkExact time
Gemini 3.7 Flash answered all 169 returned items correctly in the sufficiency task, but 23 calls yielded no result after three attempts; counting those as failures reduces the number of passing families from a perfect score to 28 out of 48.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedWhen asked directly whether the total was visible, Claude, Gemini 3 Flash, and Flash-Lite answered across all 48 receipts that the total was not visible and could not be calculated, yet when asked directly for the total, they still fabricated one 21–44% of the time.68% similarUnverifiedFabrication rates when the total is fully obscured: Claude Sonnet 5 at 38%, Gemini 3 Flash at 21%, Gemini 3.1 Flash-Lite at 44%, GPT-5.4 nano at 73%; fabrication rates when the total is half-obscured: Claude at 92%, the other three models all at 100%.67% similarUnverifiedOn the Frontier Code programming benchmark, the old model scored 34.4%, while Gemini 3.7 Flash improved to 43.6%.66% similarUnverified在285次实测运行中，Gemini取得283次语义通过、2次语义部分通过、0次可复现语义失败65% similarUnverifiedIn EvoMap's benchmark test, sub-agents actually found 373 correct answers, but after the main agent merged the results, only 217 were retained in the final output.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1003880API
curl https://kongchang.com/api/v1/knowledge/claims/1003880MCP
get_claim(id=1003880)