AI Benchmark Model
Grok 4.3 (high)
Benchmark scores, pricing, speed, and model comparisons for Grok 4.3 (high).
Key scores
Grok 4.3 (high) is an artificial intelligence model developed by xAI, released on April 30, 2026. The model achieves an intelligence index of 53.2 and a coding index of 41. Performance metrics indicate an output speed of 123.966 tokens per second with a time to first token of 6.374 seconds. Pricing for the model is set at $1.25 per million tokens for input and $2.50 per million tokens for output, resulting in a blended rate of $1.56 per million tokens. Benchmark results include a GPQA score of 0.901, HLE of 0.35, SciCode of 0.473, IFBench of 0.813, LCR of 0.643, TerminalBench Hard of 0.379, and TAU2 of 0.977.
Benchmark results
7 tracked benchmark rows for Grok 4.3 (high).
TAU2 Other
97.7% GPQA Reasoning
90.1% IFBench Other
81.3% LCR Other
64.3% SciCode Other
47.3% TerminalBench Hard Other
37.9% HLE Other
35.0%
Comments (0)
to join the discussion
No comments yet
Be the first to share your thoughts!