Unverified50% confidenceFactExact time
Resolve has 16 problems, and the final score is the number of fully solved problems out of 16, ranging from 0 to 1.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedA total of 23 models received scores on both the resolve and resolve-plus tasks.67% similarUnverifiedIn the final test, Arm A answered all 36 answers correctly, Arm B answered 25 correctly; both groups got 17 answers correct on the first try.63% 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.60% similarUnverifiedAmong all 16 configurations across 4 tasks × 4 models, not a single one passed the qualification threshold.59% similarUnverifiedMultiplying the value of the least significant bit obtained from x & (-x) by the 32-bit de Bruijn constant 0x077CB531 and then right-shifting by 27 bits yields a 5-bit index that uniquely corresponds to a bit position in a precomputed lookup table.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1007720API
curl https://kongchang.com/api/v1/knowledge/claims/1007720MCP
get_claim(id=1007720)