FastEval — leaderboard
Aggregate LLM evaluation report combining reasoning, coding, and chat benchmarks into a total score from the FastEval project.
Metric: Total Score. Source: fasteval.github.io. Status: saturated. 33 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4 (0613) | 77.78 |
| 2 | GPT-3.5 Turbo (0613) | 65.17 |
| 3 | GPT-3.5 Turbo (0301) | 63.67 |
| 4 | StableBeluga2 | 55.6 |
| 5 | Llama 2 70B Chat | 48.18 |
| 6 | WizardCoder-Python-34B-V1.0 | 47.15 |
| 7 | vicuna-33B-v1.3 | 43.04 |
| 8 | Mistral 7B Instruct (v0.1) | 42.66 |
| 9 | Llama 2 13B Chat | 40.94 |
| 10 | Llama 2 7B Chat | 35.36 |
| 11 | vicuna-7B-v1.3 | 34.5 |
| 12 | falcon-40B Instruct | 31.75 |
| 13 | mpt-7B-chat | 30.97 |
| 14 | falcon-7B Instruct | 21.78 |
Interactive version: theaggregate.ai/benchmark?slug=fasteval · How the rankings work · Data refreshed daily, snapshot 2026-07-22.