Unverified50% confidenceFactExact time
Obsidian-3 in its highest full-power mode dropped to a score of 45.5%, with the per-task cost soaring to 47 dollars.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/29/2026
First Seen
Valid until: 11/12/2026
Sources
Gemini 4 Carbon Tops the Intelligence Leaderboard, But Coding Agents Still Trail Claude Opus 5.5
bilibili进化中的阿陈10/29/2026
Related Entities
Related Claims
UnverifiedObsidian 3, a model suspected to be Fable 5.5, scored 46.8% on the Frontier Code 2.0 benchmark at high reasoning intensity, only narrowly leading Opus 5.5's 45.5%.65% similarUnverifiedIn that benchmark test, each task consumed about 550,000 tokens, whereas the comparison Opus 5.5 low tier consumed only about 30,000 tokens.56% similarUnverifiedTEMPEST outperforms the best classical model by 17.9 percentage points and the strongest triplet-loss baseline by 58.4 percentage points.56% similarUnverifiedVals measured Gemini 4 Argon's cost per test at $15.68, lower than Claude Sonnet 5.5's $21.34 and Opus 5.5's $32.14, making it the lowest in the group.56% similarUnverifiedOn the Deep Squeeze test, the old model scored 49%, while Gemini 3.7 Flash jumped to 65.3%.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1111475API
curl https://kongchang.com/api/v1/knowledge/claims/1111475MCP
get_claim(id=1111475)