Unverified50% confidenceFactExact time
After fixing the bug in the zoom tool and raising the per-round token limit, Anthropic re-ran the old model, and Claude Opus 4.7's OSWorld score rose from 78.0% to 82.8%, with no change to the model itself.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedThrough a series of strategy adjustments, the usage cost of Opus 5 can be reduced by up to 80%, while still outperforming Opus 4.8 on some benchmarks.61% similarUnverifiedOpus 5.5 achieved 81.8% on the Computer Use benchmark, slightly above Fable 5.1's 80.7%.60% similarUnverifiedAll models averaged 0.91 on explicit memory updates but only 0.67 on implicit updates; Opus 5.5 and Gemini 3.1 Pro caught every implicit change, while gpt-oss-20b caught zero.60% similarUnverifiedIn a 2024 study, Anthropic found that model performance did not decline after compressing 80% of the system prompt.60% similarUnverifiedThe second stage continued evolving on the out-of-distribution benchmark Claw-Eval, raising the score from 66.17 to 68.06, surpassing Codex.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1009490API
curl https://kongchang.com/api/v1/knowledge/claims/1009490MCP
get_claim(id=1009490)