AI Benchmark Model
Claude Opus 4.6 (Adaptive Reasoning, Max Effort)
Benchmark scores, pricing, speed, and model comparisons for Claude Opus 4.6 (Adaptive Reasoning, Max Effort).
Key scores
Claude Opus 4.6, developed by Anthropic and released on February 5, 2026, is an adaptive reasoning model designed for high-effort tasks. The model achieves an intelligence index of 52.9 and a coding index of 48.1. Performance metrics indicate an output speed of 45.825 tokens per second with a time to first token of 15.732 seconds. Pricing is structured at $6.25 per million input tokens and $25.00 per million output tokens, resulting in a blended rate of $10.94 per million tokens. Benchmark results include a GPQA score of 0.896, HLE of 0.367, SciCode of 0.519, IFBench of 0.531, LCR of 0.707, TerminalBench Hard of 0.462, and a TAU2 score of 0.921.
Benchmark results
7 tracked benchmark rows for Claude Opus 4.6 (Adaptive Reasoning, Max Effort).
TAU2 Other
92.1% GPQA Reasoning
89.6% LCR Other
70.7% IFBench Other
53.1% SciCode Other
51.9% TerminalBench Hard Other
46.2% HLE Other
36.7%
Comments (0)
to join the discussion
No comments yet
Be the first to share your thoughts!