No Guarantees from “The Benchmark Didn’t Move”
These recent papers are also relevant:
“Silent Failures in Quantized LLM Reasoning: A Taxonomy-Based Analysis of Hollow Convergence and Failure Mode Shifts” https://arxiv.org/abs/2607.09999
“Quantization Inflates Reasoning: Token Inflation as a Hidden Cost of Low-Bit Reasoning Models” https://arxiv.org/abs/2606.25519
These recent papers are also relevant:
“Silent Failures in Quantized LLM Reasoning: A Taxonomy-Based Analysis of Hollow Convergence and Failure Mode Shifts” https://arxiv.org/abs/2607.09999
“Quantization Inflates Reasoning: Token Inflation as a Hidden Cost of Low-Bit Reasoning Models” https://arxiv.org/abs/2606.25519