Expired50% confidenceBenchmarkExact time
Luna surpassed Opus 4.8 on the Artificial Analysis coding agent index.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/11/2026
First Seen
Valid until: 10/9/2026(expired)
Sources
Related Claims
UnverifiedGemini 3.5 Pro scored 42 on the ARC-AGI-2 general intelligence evaluation, far surpassing competitors from the same period66% similarUnverifiedLuna is positioned as a cheap and fast model to be called by smarter agents or used for tasks such as bulk data processing and title generation, rather than being manually selected by developers.65% similarUnverifiedIn graduate-level reasoning and Agent tool-use benchmarks, Opus 4 is largely in the lead, though Gemini 2.5 Pro comes very close on some items.65% similarUnverifiedArtificial Analysis gave Gemini 3.7 Flash an intelligence index of 56, which is 4 points higher than 3.6 Flash.64% similarUnverifiedOn the AI model capability leaderboard, Claude Opus 5 leads the intelligence ranking with 63 points and dominates the agent ranking, while Gemini 3.7 Flash enters the intelligence ranking at ninth place with 56 points.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/483178API
curl https://kongchang.com/api/v1/knowledge/claims/483178MCP
get_claim(id=483178)