Claude Haiku 5.5 vs Gemini 3.1 Pro Preview

Where it leads

• Higher Arena WebDev score, 1589 Elo vs 1447 Elo
• Higher FrontierMath Tiers 1-3 (v2) score, 75.1% vs 59.6%
• Longer responses, up to 128,000 vs 65,536 output tokens
• A cached-input rate, $0.01 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 Arena Text score, 1487 Elo vs 1425 Elo
• Higher GPQA Diamond score, 94.4% vs 89.6%
• Higher SimpleQA Verified score, 73.5% vs 23.8%
• Accepts audio and video input

Best for

• Multimodal reasoning and agentic coding evaluations

Watch out for

• This preview endpoint may change before becoming stable; production use should account for its published prompt-length price tiers