Unverified50% confidenceFactExact time
OpenAI GPT-6 Luna's input discount on UplinkSwitch is only 37%, one of the few values in the table below 40%.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/17/2026
First Seen
Valid until: 10/31/2026
Sources
Related Entities
Related Claims
UnverifiedThe strongest configuration, GPT-5.5 paired with Codex, achieved a pass rate of only 28.0% on Harbor-Index67% similarUnverifiedIn the Frontier Code test, GPT-6 Luna Max achieved 66.6%, with a cost of only 22 cents per task.65% 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.65% similarUnverifiedGSM8K发布时GPT-3的zero-shot准确率仅约5%，加入few-shot示例也不超过35%63% similarUnverifiedCompared to GPT-6 Astra, SWE-2's score trails by a few percentage points, but its cost is only one-quarter of the latter's.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1057016API
curl https://kongchang.com/api/v1/knowledge/claims/1057016MCP
get_claim(id=1057016)