AGIEval is an AI benchmark used to evaluate model capabilities. Review its overview, metrics, official resources, and model leaderboard results on DataLearnerAI.
Browse the latest scores, model modes, release dates, and parameter sizes for AGIEval.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Rank | Model | License | |||
|---|---|---|---|---|---|
 baichuan3 Standard Mode | 73.16 | 2024-01-29 | Unknown | Closed | |
 Qwen-72B Standard Mode | 62.50 | 2023-11-30 | 72B | Free Commercial | |
 YAYI2-30B Standard Mode | 62.00 | 2023-12-22 | 30B | Commercial | |
4 |  XVERSE-65B Standard Mode | 61.80 | 2023-11-05 | 65B | Free Commercial |
5 |  Orion-14B-Base Standard Mode | 54.70 | 2024-01-22 | 14B | Free Commercial |
6 |  LLaMA2 70B Standard Mode | 54.20 | 2023-07-18 | 70B | Free Commercial |
7 |  ChatGLM3-6B-Base Standard Mode | 53.70 | 2023-10-27 | 6B | Free Commercial |
8 | XVERSE-13B-Chat Standard Mode | 48.30 | 2023-08-22 | 13B | Free Commercial |
9 | Baichuan2-13B-Base Standard Mode | 48.17 | 2023-09-06 | 13B | Free Commercial |
10 | LLaMA 65B Standard Mode | 47.60 | 2023-02-24 | 65B | Non-Commercial |
11 | LLaMA2 34B Standard Mode | 43.40 | 2023-07-18 | 34B | Free Commercial |
12 |  Mistral 7B Standard Mode | 43.00 | 2023-09-27 | 7.3B | Free Commercial |
13 | Baichuan2-7B-Base Standard Mode | 42.73 | 2023-09-06 | 7B | Free Commercial |
14 |  InternLM Chat 7B 8K Standard Mode | 42.50 | 2023-06-03 | 7B | Free Commercial |
15 | LLaMA 33B Standard Mode | 41.70 | 2023-02-24 | 33B | Non-Commercial |
16 | XVERSE-13B Standard Mode | 41.40 | 2023-08-06 | 13B | Free Commercial |
17 | LLaMA2 13B Standard Mode | 39.10 | 2023-07-18 | 13B | Free Commercial |
18 | InternLM 7B Standard Mode | 37.60 | 2023-06-03 | 7B | Free Commercial |
19 | Baichuan 7B Standard Mode | 34.44 | 2023-06-19 | 7B | Free Commercial |
20 | LLaMA 13B Standard Mode | 33.90 | 2023-02-24 | 13B | Non-Commercial |
21 | LLaMA2 7B Standard Mode | 29.30 | 2023-07-18 | 7B | Free Commercial |
22 |  Ziya-LLaMA-13B-Pretrain-v1 Standard Mode | 27.20 | 2023-06-01 | 13B | Non-Commercial |
23 |  MOSS Standard Mode | 26.80 | 2023-02-20 | 16B | Free Commercial |
24 |  Aquila-7B Standard Mode | 25.58 | 2023-06-10 | 7B | Free Commercial |
25 |  Pythia Standard Mode | 25.30 | 2023-04-03 | 12B | Free Commercial |
26 | OPT Standard Mode | 24.20 | 2022-05-02 | 175B | Non-Commercial |
27 |  OpenLLaMA 13B Standard Mode | 24.00 | 2023-06-15 | 13B | Free Commercial |
28 | LLaMA 7B Standard Mode | 23.90 | 2023-02-24 | 7B | Non-Commercial |
