Claude Haiku 5.5 vs Grok 4.20

Where it leads

• Lower input and output prices, $0.10 and $0.50 vs $1.25 and $2.50 per 1M tokens
• Higher GPQA Diamond score, 89.6% vs 89.3%
• Higher FrontierMath Tiers 1-3 (v2) score, 75.1% vs 44.9%
• Cheaper cached input, $0.01 vs $0.20 per 1M tokens
• Batch pricing, $0.05 input and $0.25 output per 1M tokens

Best for

• High-volume classification, extraction and routing under the 100,000-token line
• Cost-sensitive fan-out steps where a frontier model is overkill

Watch out for

• Priced by prompt length, and it is a cliff rather than a taper: a request whose prompt passes 100,000 tokens is billed at $0.50 input and $2.50 output for the whole request, five times the short rate
• Cache reads and cache writes both count toward that 100,000-token measurement, so a large cached prefix can tip a request into the higher band on its own
• It is the only current Claude model whose 1M window is not priced uniformly; every other 4.6-and-later model bills a 900k request at the same rate as a 9k one

Where it leads

• Higher SimpleQA Verified score, 30.2% vs 23.8%

Best for

• Comparing single-agent and multi-agent reasoning on long-context workloads

Watch out for

• The published base rates double when requests reach the provider's 200,000-token long-context threshold