AI Benchmark Model

Claude Haiku 5.5 (Medium)

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

Key scores

Intelligence34.5Index score
Speed168.7Tokens/sec

Claude Haiku 5.5 (Medium) has an intelligence index of 34.5 in Franklin's current Artificial Analysis-sourced records. The captured aggregate result falls between the Low and High configurations. It does not show that Medium is the best balance for every workload; that decision needs task results and the relevant price and response-time measurements. Include Medium in a configuration comparison when you want to see whether a higher setting produces a useful improvement on your prompts. Keep the input set and acceptance criteria fixed. Evaluate correctness, consistency, and response behaviour separately instead of treating the headline index as a complete answer. This profile describes the stored measurements and does not substitute for a new application-level test.

No benchmark data available for this model.

Comparisons with Claude Haiku 5.5 (Medium)

Generated Franklin AI comparison pages for this model.

Model ComparisonClaude Haiku 5.5 (Medium) vs Claude Opus 5.5 (Max, Default Fallback)Claude Haiku 5.5 Medium is listed at lower token rates than Claude Opus 5.5. Opus has the higher intelligence index, while Haiku has a shorter reported first-token delay and higher output throughput in the captured recorModel ComparisonClaude Haiku 5.5 (Medium) vs GPT-6 Astra (Max)Claude Haiku 5.5 Medium has lower listed rates than GPT-6 Astra Max and a lower intelligence index. The recorded Haiku timing values also show a shorter first-token delay and higher output throughput. This pair comparesModel ComparisonClaude Haiku 5.5 (Medium) vs GPT-6 Astra (Medium)Haiku 5.5 Medium has lower listed token prices and higher reported output throughput than GPT-6 Astra Medium. Astra has the higher intelligence index and the shorter reported first-token delay. Matching the Medium labels