AI Paper Atlas

Research map / Benchmarks / C4

C4 leaderboard

16 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on C4. Best perplexity: 6.38 (BESA, ICLR 2024).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

C4 · perplexity

16 papers, each with its best reported number for its own method; lower is better.

#perplexity ↓MethodPaperTopic
16.38BESA
LLaMA2-70B
BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation
ICLR 2024 · Table 1
Pruning and efficient tuning
27.11CQ-2c8b
LLaMA-7b
KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization
NeurIPS 2024 · Table: Perplexity on C4
Quantization
37.262INT8 KV cache
Llama-2-7B
QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache
ICML 2025 · Table: Perplexity evaluations
Attention and transformers
47.33Proposed
Mixtral-8x7B
QoS-Efficient Serving of Multiple Mixture-of-Expert LLMs Using Partial Runtime Reconfiguration
ICML 2025 · Quality of Generated Output ta
Mixture of experts
57.68Non-uniform
LLaMA-7B
What Makes Quantization for Large Language Model Hard? An Empirical Study from the Lens of Perturbation
AAAI 2024 · Table: Comparison of uniform a
Language, safety and interpretability
67.72TransfusionTransfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model
ICLR 2025 · Table: controlled comparison w
Human and embodied modeling
78.1466PB-GPTQ 50%
LLaMA-7B
PB-LLM: Partially Binarized Large Language Models
ICLR 2024 · Table: Perplexity of C4, wikit
Language, safety and interpretability
89.3KDP + PEFT (Ours†)
LLaMA-2-7B
KDP: Simplifying Representation Dynamics in Kernel Space
ICLR 2026 · Table 2
RNNs and normalization
914.7AgileQ
BLOOM-7.1B
Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge
AAAI 2024 · Table: Perplexity of BLOOM on
Quantization
1019.51HCInfer
Qwen-30B-A3B (4-bit)
HCInfer: An Efficient Inference System via Heterogeneous Error Compensation for Resource-Constrained Devices
NeurIPS 2026 · Table 1
Quantization
6 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.