GPT-5.6 Sol trails Fable 5 by 1 point on benchmark, at one-third the cost
Decision Brief
What changedOpenAI's GPT-5.6 Sol scores 59 on comprehensive benchmark, just 1 point below Claude Fable 5, with task cost at $1.04 vs. $3.12.
Why it mattersSol leads in agentic coding, challenging Anthropic's pricing for developers and enterprises.
Who should careTeams building on model APIs
Affected stackClaudeOpenAI
Source confidenceMedium · Reliable media or first-hand reporting
According to The Decoder, OpenAI's GPT-5.6 Sol scored 59 on the Artificial Analysis Intelligence Index, only 1 point lower than Anthropic's Claude Fable 5. Task cost is just $1.04—a third of Fable 5's. In agentic coding tasks, Sol outperformed all competitors. This cost-performance ratio directly pressures Anthropic-dependent developers and enterprises. The same performance at a fraction of the price may drive users to OpenAI, while Anthropic faces pressure to cut prices further.
Summary basis: official / RSS sourceCompiled from the source scope noted above; the original remains authoritative.
Sources
- The Decoder：AI News
- The Decoder：AI News
留言
登入后即可留言，和其他 builder 交换实测心得。
还没有留言，抢头香。