[KongchangAI]
Unverified50% confidenceBenchmarkExact time

GPT-6.1 Sol called via Codex CLI achieved a perfect score of 82/82 in the evaluation, with larger chat models actually achieving higher accuracy.

1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/11/2026
First Seen
Valid until: 1/9/2027

Sources

Benchmarking 14 Decision Models: Microsoft Decision-1 Ranks 6th

Related Entities

GPT-6.1 SolmodelCodex CLIproduct

Related Claims

UnverifiedThe Copilot team found that Decision-1 is comparable to GPT5.6 Luna in measuring the quality of chat and agent responses while being 100 times faster.70% similar

Cite This Claim

Stable URI
https://kongchang.com/claim/998808
API
curl https://kongchang.com/api/v1/knowledge/claims/998808
MCP
get_claim(id=998808)