JustEval — leaderboard
Metric: Avg Score (1-5). Source: allenai.github.io. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Yi 34B (Chat) | 4.87 |
| 2 | tulu-2-dpo-70B | 4.82 |
| 3 | GPT-4 (0613) | 4.8 |
| 4 | GPT-4 (0314) | 4.79 |
| 5 | GPT-3.5 Turbo | 4.75 |
| 6 | Llama 2 70B Chat | 4.72 |
| 7 | Llama 2 70B Chat GPTQ | 4.67 |
| 8 | tulu-2-dpo-7B | 4.67 |
| 9 | Yi 6B (Chat) | 4.58 |
| 10 | Llama 2 7B Chat | 4.47 |
| 11 | Vicuna-7B | 4.46 |
| 12 | Mistral 7B Instruct | 4.44 |
Interactive version: theaggregate.ai/benchmark?slug=justeval · How the rankings work · Data refreshed daily, snapshot 2026-07-22.