Unverified50% confidenceBenchmarkExact time
GPT-6.1 Terra comprehensively surpasses the previous generation on the visual reasoning benchmark MMMU Pro, and on the desktop operation benchmark OS World 2.1 it reaches the previous generation's top-tier score at medium reasoning effort.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/1/2026
First Seen
Valid until: 11/15/2026
Sources
GPT-6.1 Terra Launches at Rock-Bottom Price: Do Flagship Work for a Tenth of the Cost
bilibili东海与西海10/27/2026
Related Entities
Related Claims
UnverifiedGPT-6.1 Terra shows clear improvements over the previous-generation Terra in visual reasoning, factual accuracy, and coding ability.74% similarUnverifiedThe core selling point of GPT-6.1 Terra is the popularization of computer operation capability, rather than parameter scale or benchmark scores.74% similarUnverifiedIn the visual reasoning chart, GPT-6.1 Terra reaches 85.5% at the highest effort.72% similarUnverifiedGPT 6.1 Terra is clearly inferior to the flagship GPT 6 Astro in visual creativity, game feel, 3D modeling and other dimensions.72% similarUnverifiedOn the offline OS World 2.1 desktop operation benchmark, GPT-6.1 Terra reaches 74.2%.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1122054API
curl https://kongchang.com/api/v1/knowledge/claims/1122054MCP
get_claim(id=1122054)