Unverified50% confidenceBenchmarkExact time
In the long-context test GraphWalks, Neon scored 95.2% while Opus scored only 66.8%.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/19/2026
First Seen
Valid until: 12/3/2026
Sources
Related Entities
Related Claims
UnverifiedIn single-latent ablation experiments, the proportion of cases where the sign predicted by gradients matched the true sign reached 91%–97%, whereas the direction of change suggested by probes was correct only 17%–35% of the time.67% similarUnverifiedThe Artificial Analysis page shows that in Neon's top setting the first character appears only 56.51 seconds after the question is asked, and its performance rank is only 73rd among 95 models.66% similarUnverifiedUnder the paired-bootstrap 95% confidence interval, the lower bounds are 5.0 and 3.1 percentage points respectively, both positive, indicating the improvements are statistically significant.66% similarUnverifiedOn the temporal split test set (878 comparisons from 655 trials), a gradient-boosted emulator trained on registry data eliminated about one-fifth of the error of a simple baseline.65% similarUnverifiedDuring testing, cases emerged where a model claimed 95% confidence in a move but scored 0 points according to the evaluation criteria.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1188108API
curl https://kongchang.com/api/v1/knowledge/claims/1188108MCP
get_claim(id=1188108)