Expired50% confidenceBenchmarkExact time
Sol scored 80 in the coding agent index under full reasoning mode, setting a new SOTA and surpassing Faber-5 by 2.8 points.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/23/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/21/2026(expired)
Sources
GPT-5.6 Three-Model Showdown: Sol vs Terra vs Luna — Which One Should You Pick?
bilibili麦冬AI实验室7/11/2026
Related Claims
UnverifiedCiting a third-party programming benchmark, OpenAI states that Sol scored 80 points, 2.8 points higher than Claude's comparable model.72% similarUnverifiedIn the agent ultimate exam covering long-horizon workflows across 55 professional domains, Sol scored 53.6, surpassing the benchmarked Fable 5 by 13.1 points.67% similarUnverifiedOn the Exploit Bench cybersecurity benchmark, Sol scores approximately 76% and Mythos 5 approximately 78%.65% similarUnverifiedThe standard version of Sol scored 88.8% on the Terminal Bench 2.1 benchmark, which improved to 91.9% with Ultra mode enabled.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/602520API
curl https://kongchang.com/api/v1/knowledge/claims/602520MCP
get_claim(id=602520)