Expired85% confidenceFactTime unknown
In Artificial Analysis's coding agent index, Composer 2 scored 48 and Composer 2.5 scored 63 in the Cursor Client
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedComposer 2.5 currently ranks eighth on the comprehensive AI benchmark leaderboard, performing well in code writing, debugging, and logical reasoning, but falling slightly short in the creativity dimension.78% similarUnverifiedComposer 2.5 currently ranks eighth on the comprehensive AI benchmark leaderboard.71% similarUnverifiedIn the Terminal Bench 2.0 benchmark, Composer 2 scored 61.7%.65% similarUnverifiedMusk reposted evaluation data related to Composer 2.5.64% similarVerifiedComposer 2.5 scored 63.2% on Cursor Bench V3.1, while Opus 4.7 scored 61.6% under the default configuration and GPT 5.5 scored 59.2%.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/10195API
curl https://kongchang.com/api/v1/knowledge/claims/10195MCP
get_claim(id=10195)