Unverified50% confidenceBenchmarkExact time
On the same 100 samples, the GraphSAGE graph neural network baseline correctly classified 67 samples, outperforming Gemma 4 31B's 55.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedIn 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.64% similarUnverifiedThe model gave the correct answer of 34 in a multimodal image recognition test counting pencils, at a speed of 55 tokens per second at that time.64% similarUnverifiedIn a test recognizing an electronic invoice containing 28 items of information, both Ornith 9B and 35B completely extracted all 28 fields with a 100% match rate.63% similarUnverifiedgpt-oss-20b's weakness is source attribution—out of 60 questions, it fully listed all sources only 52 times.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1007680API
curl https://kongchang.com/api/v1/knowledge/claims/1007680MCP
get_claim(id=1007680)