Unverified50% confidenceBenchmarkExact time
On the independent Intelligence Index (version 4.3), Terra scored 48, while Shou (the flagship) scored 52 and Opus 5.5 scored 58 under the same methodology.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/1/2026
First Seen
Valid until: 11/15/2026
Sources
Related Entities
Related Claims
UnverifiedIn a third-party Artificial Analysis evaluation, GPT-6.1 Terra's composite intelligence index was 48, 4 points lower than GPT-6.1 Soul.77% similarPartially VerifiedGemini 4 Carbon scored 59 on the Artificial Analysis Intelligence Index.68% similarPartially VerifiedOn the fifth edition of the Comprehensive Intelligence leaderboard, Gemini 4 Carbon scored 59 points, ranking first and overtaking Claude Opus 5.5, 9 points higher than Argon.67% similarUnverifiedOpenAI's internal high-difficulty fact test shows that 5.6 Terra's error rate at low reasoning effort was as high as 53.6%, while GPT-6.1 Terra cut the error rate to 16.7%, and further reduced it to 4.3% at maximum reasoning.66% similarUnverifiedIn Paul Well-Hurren's bug-fixing test, Terra's highest level scored 40.7, versus 32 for the previous generation's highest level; however, Terra's ultra-high level scored only 11.3 and its high level 9.7, lower than the previous generation at the same levels.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1121970API
curl https://kongchang.com/api/v1/knowledge/claims/1121970MCP
get_claim(id=1121970)