Expired50% confidenceBenchmarkExact time
In the same task test, Claude Opus 4 (Ultra mode) took approximately 1 hour and cost $21.27.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/24/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/22/2026(expired)
Sources
开源模型能替代Claude吗？GLM 5.2 vs DeepSeek实测对比
bilibili程序员-智能译站7/10/2026
Related Claims
UnverifiedIn a Crossy Road-style game generation test, Fugu Ultra took 22 minutes, consumed approximately 90,000 tokens, and cost about $7.32, while Claude Opus 4 took 79 minutes, consumed approximately 940,000 tokens, and cost about $37.85.73% similarUnverifiedThe cost of processing a single record with Claude Code + Opus 4.7 is approximately £1 (around ¥10 RMB), with a processing time of approximately 10 minutes per record72% similarUnverifiedUsing the flagship model Claude Opus to complete a task involving 20 tool calls with an average context of 10,000 tokens per round, the input cost alone could exceed $3.72% similarVerified本次对 Claude Opus 4.8 的多场景深度测试总计花费约 50 美元 Token 费用71% similarUnverifiedClaude Opus 4 may consume several dollars per session, and using it four or five times a day could result in monthly programming costs reaching hundreds to thousands of dollars.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/606453API
curl https://kongchang.com/api/v1/knowledge/claims/606453MCP
get_claim(id=606453)