Model Releases
Prompt caching benchmark: high cache reuse doesn’t always mean lower cost
We benchmarked prompt caching across DeepSeek, GLM, GPT, and Claude using Harbor evals and Phoenix traces, so we could compare cache reuse, estimated cost, and latency on the same multi-turn shopping
We benchmarked prompt caching across DeepSeek, GLM, GPT, and Claude using Harbor evals and Phoenix traces, so we could compare cache reuse, estimated cost, and latency on the same multi-turn shopping assistant agent. The post Prompt caching benchmark: high cache reuse doesn’t always mean lower cost appeared first on Arize AI.
Related
- MMShopBench: A Real-Log Benchmark for Multimodal, Multi-Turn Shopping Agents
- Cost per successful task: Benchmarking Kimi K3, GPT-5.5, and 8 more AI models
- Grok 4.6 just matched Claude Fable 5 on Perplexity’s WANDR benchmark....at more than 60% lower cost Both score exactly 0.496 But the cost pe…
Source: Arize AI | 2026-10-02