[KongchangAI]
Unverified50% confidenceBenchmarkExact time

GPT-5.6 Sol achieved a record-high score of 73% on the DeepSWE benchmark Max tier at a cost of $22 per task, while the competing product Fable scored $839 on the corresponding tier.

1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/24/2026
First Seen
Valid until: 10/22/2026

Sources

GPT-5.6深度评测：Sol、Terra、Luna三模型选型完全指南
youtubeTheo - t3․gg7/12/2026

Related Claims

UnverifiedGPT 5.5's output price is $53 per million tokens, approximately 16 times that of DeepSeek V4 Pro.74% similarUnverifiedOn the DeepSWE benchmark, the per-task cost across reasoning tiers is $1 at Low, $1.86 at Medium, $3.47 at High, $4.70 at X-High, and $8.39 at Max.72% similar

Cite This Claim

Stable URI
https://kongchang.com/claim/607381
API
curl https://kongchang.com/api/v1/knowledge/claims/607381
MCP
get_claim(id=607381)