Expired50% confidenceBenchmarkExact time
On the Exploit Bench cybersecurity vulnerability analysis test, SOL performs comparably to Anthropic's Codex, but produces only about one-third the output token count of the latter.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/11/2026
First Seen
Valid until: 10/9/2026(expired)
Sources
GPT-5.6三款模型深度实测：SOL/TERRA/LUNA性能与定价全解析
bilibili薛定猫AI7/9/2026
Related Claims
UnverifiedIn the ExploitBench test, Sol scored approximately 76%, slightly behind Fable 5's 78%, but Sol consumed only about 120,000–130,000 tokens while Fable 5 used approximately 350,000 tokens.63% similarUnverifiedOn the Exploit Bench cybersecurity benchmark, Sol scores approximately 76% and Mythos 5 approximately 78%.62% similarUnverifiedThe review results show that Opus 5 frequently kills the wrong process (often mistakenly killing the T3 Code instance it is running in), and Sol (GPT) has approximately a 40% probability of submitting a draft PR.59% similarUnverifiedSol scored 9019 points on the Terminal Bench 2.1 programming benchmark.56% similarUnverified在SWE-Bench基准测试中，Codex得分在69-80分之间55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/488169API
curl https://kongchang.com/api/v1/knowledge/claims/488169MCP
get_claim(id=488169)