AI Benchmark Model
DeepSeek V4 Pro (Reasoning, Max Effort)
Benchmark scores, pricing, speed, and model comparisons for DeepSeek V4 Pro (Reasoning, Max Effort).
Key scores
DeepSeek V4 Pro (Reasoning, Max Effort) is an artificial intelligence model released by DeepSeek on April 24, 2026. The model holds an intelligence index of 51.5 and a coding index of 47.5. Performance metrics indicate an output speed of 29.718 tokens per second with a time to first token of 1.248 seconds. Pricing for the model is set at $1.74 per 1 million input tokens and $3.48 per 1 million output tokens, resulting in a blended rate of $2.17 per 1 million tokens. Benchmark results include a GPQA score of 0.888, HLE score of 0.359, SciCode score of 0.5, IFBench score of 0.7646, LCR score of 0.6633, TerminalBench Hard score of 0.4621, and TAU2 score of 0.9620.
Benchmark results
7 tracked benchmark rows for DeepSeek V4 Pro (Reasoning, Max Effort).
TAU2 Other
96.2% GPQA Reasoning
88.8% IFBench Other
76.5% LCR Other
66.3% SciCode Other
50.0% TerminalBench Hard Other
46.2% HLE Other
35.9%
Comments (0)
to join the discussion
No comments yet
Be the first to share your thoughts!