| GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models | ✓ Link | 90.0 | GLM-4.5 (355B) | 2025-08-08 |
| Introducing Claude 3.5 Sonnet | | 88.7 | Claude 3.5 Sonnet | 2024-06-20 |
| GPT-4o as the Gold Standard: A Scalable and General Purpose Approach to Filter Language Model Pretraining Data | | 87 | GPT-4 o1(300b) | 2024-10-03 |
| Introducing the next generation of Claude | | 86.8 | Claude 3 Opus | 2024-03-04 |
| Introspective Diffusion Language Models | ✓ Link | 86.8 | I-DLM-32B | 2026-04-13 |
| Llama 3 Meets MoE: Efficient Upcycling | ✓ Link | 86.6 | Llama 3.1 (405B) | 2024-12-13 |
| Motif 3: Technical Report | ✓ Link | 86.2 | Motif 3 Base (5-shot) | 2026-08-10 |
| Llama 3 Meets MoE: Efficient Upcycling | ✓ Link | 86.0 | Llama 3.1 (70B) | 2024-12-13 |
| Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context | ✓ Link | 85.9 | Gemini 1.5 Pro (5-shot) | 2024-03-08 |
| Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters | ✓ Link | 85.8 | Step-3.5-Flash Base | 2026-02-11 |
| Qwen2 Technical Report | ✓ Link | 84.2 | Qwen2-72B | 2024-07-15 |
| Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models | ✓ Link | 84.2 | Nemotron-H-56B-Base (5-shot) | 2025-04-04 |
| Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance | ✓ Link | 84.05 | Falcon-H1-34B-Instruct (5-shot) | 2025-07-30 |
| | 83.7 | Gemini Ultra (5-shot) | |
| Qwen2 Technical Report | ✓ Link | 82.3 | Qwen2-72B-Instruct | 2024-07-15 |
| The Claude 3 Model Family: Opus, Sonnet, Haiku | | 79 | Claude 3 Sonnet (5-shot) | 2024-03-04 |
| Introducing the next generation of Claude | | 79.0 | Claude 3 Sonnet | 2024-03-04 |
| Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone | ✓ Link | 78.9 | Phi-3.5-MoE (5-shot) | 2024-04-22 |
| Liquid Foundation Models: Our First Series of Generative AI Models | | 78.76 | LFM-40B Preview (5-shot) | 2024-09-30 |
| DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model | ✓ Link | 77.8 | DeepSeek-V2 Chat (RL) (5-shot) | 2024-05-07 |
| | 77.5 | Qwen1.5 72B (5-shot) | |
| Apertus 1.5: From Open Text Models to Open Multimodal Reasoners | | 77.2 | Apertus 1.5 70B | 2026-10-11 |
| MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction | ✓ Link | 77.0 | MiniCPM-o 4.5-Instruct | 2026-04-30 |
| Encoder-Decoder Gemma: Improving the Quality-Efficiency Trade-Off via Adaptation | ✓ Link | 76.7 | T5Gemma 9B-9B PrefixLM IT | 2025-04-08 |
| Qwen2 Technical Report | ✓ Link | 76.5 | Qwen2-57B-A14B | 2024-07-15 |
| Qwen2 Technical Report | ✓ Link | 75.4 | Qwen2-57B-A14B-Instruct | 2024-07-15 |
| The Claude 3 Model Family: Opus, Sonnet, Haiku | | 75.2 | Claude 3 Haiku (5-shot) | 2024-03-04 |
| Introducing the next generation of Claude | | 75.2 | Claude 3 Haiku | 2024-03-04 |
| Gemma 2: Improving Open Language Models at a Practical Size | ✓ Link | 75.2 | Gemma 2 27B (5-shot) | 2024-07-31 |
| Improved Large Language Diffusion Models | ✓ Link | 74.8 | iLLaDA 8B Base | 2026-06-24 |
| PRISM: PRIvileged Sibling-guided Multi-Agent Topology Design | | 73.94 | PRISM | 2026-09-29 |
| The Llama 3 Herd of Models | ✓ Link | 73.7 | DBRX Instruct 132B (5-shot) | 2024-07-31 |
| Scaling Instruction-Finetuned Language Models | ✓ Link | 73.5 | llama 2(65b) | 2022-10-20 |
| Aria: An Open Multimodal Native Mixture-of-Experts Model | ✓ Link | 73.3 | Aria (5-shot) | 2024-10-08 |
| The Llama 3 Herd of Models | ✓ Link | 73.0 | Llama 3.1 8B (CoT) | 2024-07-31 |
| Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models | ✓ Link | 72.8 | Nemotron-H-8B-Base (5-shot) | 2025-04-04 |
| Improved Large Language Diffusion Models | ✓ Link | 71.6 | iLLaDA 8B Instruct | 2026-06-24 |
| Encoder-Decoder Gemma: Improving the Quality-Efficiency Trade-Off via Adaptation | ✓ Link | 71.3 | T5Gemma 9B-9B PrefixLM | 2025-04-08 |
| Mixtral of Experts | ✓ Link | 70.6 | Mixtral 8x7B (5-shot) | 2024-01-08 |
| GPT-4 Technical Report | ✓ Link | 70.0 | GPT-3.5 Turbo | 2023-03-15 |
| Dream 7B: Diffusion Large Language Models | | 69.5 | Dream 7B (5-shot) | 2025-08-21 |
| Introducing LFM-7B: Setting New Standards for Efficient Language Models | | 69.34 | LFM-7B (5-shot) | 2025-01-20 |
| PaLM: Scaling Language Modeling with Pathways | ✓ Link | 69.3 | PaLM 540B | 2022-04-05 |
| Pixtral 12B | ✓ Link | 69.2 | Pixtral 12B (5-shot) | 2024-10-09 |
| LLaMA: Open and Efficient Foundation Language Models | ✓ Link | 68.9 | LLaMA 65B (fine-tuned) | 2023-02-27 |
| Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging | ✓ Link | 68.32 | DTS-D (Qwen-14B) | 2025-12-01 |
| Training Compute-Optimal Large Language Models | ✓ Link | 67.5 | chatgpt/gpt3.5(20B) | 2022-03-29 |
| Jamba: A Hybrid Transformer-Mamba Language Model | ✓ Link | 67.4 | Jamba (5-shot) | 2024-03-28 |
| Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs | ✓ Link | 67.3 | Phi-4-Mini (5-shot) | 2025-02-24 |
| The Zamba2 Suite: Technical Report | ✓ Link | 67.2 | Zamba2-7B (5-shot) | 2024-11-22 |
| Dream 7B: Diffusion Large Language Models | | 67.0 | Dream-Instruct 7B (4-shot) | 2025-08-21 |
| Towards Looped Models Done Right, Part I: Topology, Input Injection, Recurrent-State Design | ✓ Link | 66.81 | Huginn MoE (8.0B resident, 0.8B active) | 2026-10-16 |
| Large Language Diffusion Models | ✓ Link | 65.9 | LLaDA 8B Base (5-shot) | 2025-02-14 |
| Large Language Diffusion Models | ✓ Link | 65.5 | LLaDA 8B Instruct (5-shot) | 2025-02-14 |
| Stepped MoE: Segment-Level Routing with Configurable Inference Complexity | | 65.0 | Flexible S-MoE 4B/20B | 2026-10-05 |
| LFM2 Technical Report | ✓ Link | 64.84 | LFM2-8B-A1B (5-shot) | 2025-11-28 |
| Gemma: Open Models Based on Gemini Research and Technology | ✓ Link | 64.3 | Gemma 7B (5-shot) | 2024-03-13 |
| Nemotron-4 15B Technical Report | ✓ Link | 64.2 | Nemotron-4 15B | 2024-02-26 |
| 2 OLMo 2 Furious | ✓ Link | 63.7 | OLMo 2 7B | 2024-12-31 |
| LLaMA: Open and Efficient Foundation Language Models | ✓ Link | 63.4 | LLaMA 65B (5-shot) | 2023-02-27 |
| Llama 3.2: Revolutionizing edge AI and vision with open, customizable models | ✓ Link | 63.4 | Llama 3.2 3B Instruct | 2024-09-25 |
| Llama 2: Open Foundation and Fine-Tuned Chat Models | ✓ Link | 62.6 | LLaMA 2 34B (5-shot) | 2023-07-18 |
| daVinci-LLM:Towards the Science of Pretraining | ✓ Link | 62.53 | daVinci-LLM-3B | 2026-03-28 |
| Mixtral of Experts | ✓ Link | 62.5 | Mistral 7B (5-shot) | 2024-01-08 |
| Falcon Mamba: The First Competitive Attention-free 7B Language Model | ✓ Link | 62.11 | Falcon Mamba 7B (5-shot) | 2024-10-07 |
| RecurrentGemma: Moving Past Transformers for Efficient Open Language Models | ✓ Link | 60.5 | RecurrentGemma-9B (5-shot) | 2024-04-11 |
| Mistral 7B | ✓ Link | 60.1 | Mistral 7B (5-shot) | 2023-10-10 |
| Scaling Language Models: Methods, Analysis & Insights from Training Gopher | ✓ Link | 60.0 | Gopher 280B (5-shot) | 2021-12-08 |
| Scaling Instruction-Finetuned Language Models | ✓ Link | 59.5 | GPT-3 Davinci 175B (CoT) | 2022-10-20 |
| Falcon2-11B Technical Report | | 58.37 | Falcon2-11B (5-shot) | 2024-07-20 |
| LLaMA: Open and Efficient Foundation Language Models | ✓ Link | 57.8 | LLaMA 33B (5-shot) | 2023-02-27 |
| Zamba: A Compact 7B SSM Hybrid Model | ✓ Link | 57.72 | Zamba 7B (5-shot) | 2024-05-26 |
| Byte Latent Transformer: Patches Scale Better Than Tokens | ✓ Link | 57.4 | BLT-Entropy 8B (5-shot) | 2024-12-13 |
| The Falcon Series of Open Language Models | | 57.0 | Falcon 40B | 2023-11-28 |
| | 56.7 | Qwen 7B (5-shot) | |
| Llama 2: Open Foundation and Fine-Tuned Chat Models | ✓ Link | 54.8 | LLaMA 2 13B (5-shot) | 2023-07-18 |
| OLMoE: Open Mixture-of-Experts Language Models | ✓ Link | 54.1 | OLMoE-1B-7B (5-shot) | 2024-09-03 |
| PaLM: Scaling Language Modeling with Pathways | ✓ Link | 53.7 | PaLM 62B | 2022-04-05 |
| Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM | ✓ Link | 53.2 | Branch-Train-MiX 4x7B (sampling top-1 experts) | 2024-03-12 |
| BitNet b1.58 2B4T Technical Report | ✓ Link | 53.17 | BitNet b1.58 2B4T | 2025-04-16 |
| Galactica: A Large Language Model for Science | ✓ Link | 52.6 | GAL 120B (zero-shot) | 2022-11-16 |
| Sumi: Open Uniform Diffusion Language Model from Scratch | ✓ Link | 51.1 | Sumi-7B (5-shot) | 2026-06-17 |
| TimeBraid: Unifying Time Series and Language for Understanding and Forecasting | ✓ Link | 50.68 | TimeBraid-2.5B | 2026-09-24 |
| Power Scheduler: A Batch Size and Token Number Agnostic Learning Rate Scheduler | ✓ Link | 49.2 | PowerLM-3B | 2024-08-23 |
| Atlas: Few-shot Learning with Retrieval Augmented Language Models | ✓ Link | 47.9 | Atlas (5-shot) | 2022-08-05 |
| Scaling Instruction-Finetuned Language Models | ✓ Link | 45.5 | Flan-T5-XL 3B (CoT) | 2022-10-20 |
| Llama 2: Open Foundation and Fine-Tuned Chat Models | ✓ Link | 45.3 | LLaMA 2 7B (5-shot) | 2023-07-18 |
| Scaling Instruction-Finetuned Language Models | ✓ Link | 45.1 | Flan-T5-Large 780M | 2022-10-20 |
| GLM-130B: An Open Bilingual Pre-trained Model | ✓ Link | 44.8 | GLM-130B | 2022-10-05 |
| How Depth Growth and Looping Shape In-Context Learning in Language Models | | 40.86 | LIDAS (1.7B) | 2026-10-22 |
| Scaling Instruction-Finetuned Language Models | ✓ Link | 40.5 | Flan-T5-Large 780M (CoT) | 2022-10-20 |
| Scaling Instruction-Finetuned Language Models | ✓ Link | 39.7 | GPT-3 Davinci 175B (5-shot) | 2022-10-20 |
| UL2: Unifying Language Learning Paradigms | ✓ Link | 39.2 | UL2 20B (5-shot) | 2022-05-10 |
| BloombergGPT: A Large Language Model for Finance | ✓ Link | 39.2 | Bloomberg GPT 50B (5-shot) | 2023-03-30 |
| BloombergGPT: A Large Language Model for Finance | ✓ Link | 39.1 | BLOOM 176B (5-shot) | 2023-03-30 |
| RecurrentGemma: Moving Past Transformers for Efficient Open Language Models | ✓ Link | 38.4 | RecurrentGemma-2B (5-shot) | 2024-04-11 |
| Textbooks Are All You Need II: phi-1.5 technical report | ✓ Link | 37.9 | phi-1.5-web 1.3B | 2023-09-11 |
| BloombergGPT: A Large Language Model for Finance | ✓ Link | 36 | OPT 66B (5-shot) | 2023-03-30 |
| Scaling Instruction-Finetuned Language Models | ✓ Link | 35.9 | Flan-T5-Base 250M | 2022-10-20 |
| Scaling Instruction-Finetuned Language Models | ✓ Link | 33.7 | Flan-T5-Base 250M (CoT) | 2022-10-20 |
| GPT-NeoX-20B: An Open-Source Autoregressive Language Model | ✓ Link | 33.6 | GPT-NeoX 20B (5-shot) | 2022-04-14 |
| | 31 | RWKV v5 Eagle 7B | |
| MiLe Loss: a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models | ✓ Link | 29.68 | LLaMA7B-MiLe-Loss(5-shot) | 2023-10-30 |
| Scaling Language Models: Methods, Analysis & Insights from Training Gopher | ✓ Link | 29.5 | Gopher 7.1B (5-shot) | 2021-12-08 |
| Scaling Instruction-Finetuned Language Models | ✓ Link | 28.7 | Flan-T5-Small 80M | 2022-10-20 |
| The Falcon Series of Open Language Models | | 28.0 | Falcon 7B (5-shot) | 2023-11-28 |
| Scaling Language Models: Methods, Analysis & Insights from Training Gopher | ✓ Link | 27.3 | Gopher 1.4B (5-shot) | 2021-12-08 |
| Scaling Language Models: Methods, Analysis & Insights from Training Gopher | ✓ Link | 25.7 | Gopher 417M (5-shot) | 2021-12-08 |
| PaLM: Scaling Language Modeling with Pathways | ✓ Link | 25.3 | PaLM 8B | 2022-04-05 |