AI Benchmark Model

Claude Haiku 5.5 (High)

Benchmark scores, pricing, speed, and model comparisons for Claude Haiku 5.5 (High).

Key scores

Intelligence37.8Index score
Speed176.4Tokens/sec

Claude Haiku 5.5 (High) records an intelligence index of 37.8 in Franklin's current Artificial Analysis-sourced data. Among the five listed Haiku 5.5 configurations, its aggregate result is above Medium and below Xhigh. Those measured positions describe the snapshot and do not promise the same outcome on each application task. Compare High with neighbouring settings using the same prompts and evaluation criteria. A higher aggregate index may help identify candidates for testing, but you still need to inspect correctness, consistency, response time, and costs separately. Keep any unreported task-specific measurements marked as unavailable. This profile provides context for the existing data rather than claiming that Franklin ran a new benchmark or verified a universal best setting.

No benchmark data available for this model.

Comparisons with Claude Haiku 5.5 (High)

Generated Franklin AI comparison pages for this model.

Model ComparisonClaude Haiku 5.5 (High) vs Claude Opus 5.5 (Max, Default Fallback)Haiku 5.5 High has lower listed prices and a shorter reported first-token delay than the Opus 5.5 entry. Opus has the higher aggregate intelligence index. The High label describes this Haiku configuration; it should notModel ComparisonClaude Haiku 5.5 (High) vs GPT-6 Astra (Max)Claude Haiku 5.5 High has lower listed token rates than GPT-6 Astra Max. Astra has the higher intelligence index, while Haiku has a shorter reported first-token delay and greater output throughput. These observations desModel ComparisonClaude Haiku 5.5 (High) vs GPT-6 Astra (Medium)Haiku 5.5 High has lower listed prices and higher output throughput than GPT-6 Astra Medium. Astra has the higher intelligence index and a shorter first-token delay in this snapshot. The two timing measures point in diff