Unverified50% confidenceBenchmarkExact time
In the coding agent index, Codex (Sol) scored 57 and Grok Build scored 56.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/5/2026
First Seen
Valid until: 10/19/2026
Sources
Related Entities
Related Claims
UnverifiedIn 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.69% similarUnverifiedIn a certain programming benchmark, OpenAI's GPT-5.5 scored 76% in the benchmark's built-in Harness, but only 57% within Codex internally.66% similarPartially VerifiedOpus 5.5 scored 66 on the Terminal agent benchmark, higher than Sonnet's 55 and Astra's 57.9.65% similarUnverifiedWith RSIGame applied on top, the score rose to 61.38, surpassing Codex+GPT 5.5's one-shot generation score of 50.26, with total token usage reduced by 2.6 times.65% similarUnverifiedIn an office automation evaluation covering 47 tool types and 55 industries, Sol scored 33.2% and 56.4%, respectively.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/976457API
curl https://kongchang.com/api/v1/knowledge/claims/976457MCP
get_claim(id=976457)