AI Benchmark Model
Granite 4.2 30B
Benchmark scores, pricing, speed, and model comparisons for Granite 4.2 30B.
Key scores
Granite 4.2 30B is an artificial intelligence model developed by IBM and released on August 25, 2026. In technical evaluations, the model achieved an intelligence index of 23.7 and a coding index of 29.9. Performance metrics indicate an output speed of 77.292 tokens per second with a time to first token of 0.239 seconds. Benchmark results for the model include a GPQA score of 0.644, an HLE score of 0.112, a SciCode score of 0.366, and an LCR score of 0.467. Pricing for the model is structured at $0.16 per million tokens for input and $0.65 per million tokens for output, resulting in a blended rate of $0.28 per million tokens.
Benchmark results
4 tracked benchmark rows for Granite 4.2 30B.
GPQA Reasoning
64.4% LCR Other
46.7% SciCode Other
36.6% HLE Other
11.2%
Comments (0)
to join the discussion
No comments yet
Be the first to share your thoughts!