| Paper | Code | 2k | 4k | 8k | 16k | 32k | 64k | 128k | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|---|---|---|
| GPT-4 Technical Report | ✓ Link | 18.5 | 15.5 | 7.5 | 3.5 | 6.0 | 6.0 | 6.0 | GPT-4-Turbo-1106 | 2023-03-15 |
| GPT-4 Technical Report | ✓ Link | 15.5 | 16.5 | 8.5 | 5.5 | 2.0 | 4.0 | 2.0 | GPT-4-Turbo-0125 | 2023-03-15 |
| Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena | ✓ Link | 5.4 | 5.0 | 2.4 | 3.1 | Vicuna-13b-v1.5-16k | 2023-06-09 | |||
| Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena | ✓ Link | 5.3 | 5.0 | 3.1 | 2.5 | LongChat-7b-v1.5-32k | 2023-06-09 | |||
| Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena | ✓ Link | 5.3 | 2.2 | 2.3 | 1.7 | Vicuna-7b-v1.5-16k | 2023-06-09 | |||
| InternLM2 Technical Report | ✓ Link | 5.1 | 3.9 | 5.1 | 4.3 | InternLM2-7b | 2024-03-26 | |||
| []() | 5.0 | 5.0 | 4.5 | 3.0 | 0.0 | 0.0 | Claude-2 | |||
| []() | 4.0 | 4.5 | 4.5 | 5.5 | GPT-3.5-Turbo-1106 | |||||
| GLM-130B: An Open Bilingual Pre-trained Model | ✓ Link | 2.3 | 2.4 | 2.0 | 0.7 | ChatGLM3-6b-32k | 2022-10-05 | |||
| GLM-130B: An Open Bilingual Pre-trained Model | ✓ Link | 0.9 | 0.2 | 0.7 | 0.9 | ChatGLM2-6b-32k | 2022-10-05 |