Explore Franklin AI

Claude Opus 4.7 (Max)

Benchmark scores, pricing, speed and comparisons for Claude Opus 4.7 (Max).

Key scores

Intelligence40.7Index score
Coding73.6Index score
Speed54.4Tokens/sec

Claude Opus 4.7, developed by Anthropic and released on April 16, 2026, is an adaptive reasoning model designed for high-effort tasks. In standardized evaluations, the model achieved an intelligence index of 57.3 and a coding index of 52.5. Performance metrics indicate an output speed of 48.002 tokens per second with a time to first token of 21.112 seconds. Benchmark results include 0.914 on GPQA, 0.396 on HLE, 0.545 on SciCode, 0.586 on IFBench, 0.703 on LCR, 0.515 on TerminalBench Hard, and 0.885 on TAU2. Pricing for this model is set at $6.25 per million input tokens and $25.00 per million output tokens, resulting in a blended cost of $10.94 per million tokens.

No benchmark data available for this model.