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. Saturation forecast: Estimated already saturated. 33 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4 (0613) | 77.78 | #491 |
| 2 | GPT-3.5 Turbo (0613) | 65.17 | #1118 |
| 3 | WizardLM-70B-V1.0 | 56.38 | #1236 |
| 4 | StableBeluga2 | 55.6 | #1078 |
| 5 | Llama 2 70B Chat | 48.18 | #1237 |
| 6 | vicuna-33B-v1.3 | 43.04 | #1347 |
| 7 | Mistral Instruct v0.1 7B | 42.66 | #1454 |
| 8 | MPT-30B-Chat | 41.24 | #1451 |
| 9 | Llama 2 13B Chat | 40.94 | #1465 |
| 10 | Nous-Hermes-13B | 38.49 | #1468 |
| 11 | Llama 2 7B Chat | 35.36 | #1499 |
| 12 | vicuna-7B-v1.3 | 34.5 | #1507 |
| 13 | falcon-40B Instruct | 31.75 | #1458 |
| 14 | mpt-7B-chat | 30.97 | #1556 |
| 15 | falcon-7B Instruct | 21.78 | #1622 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=fasteval · How It Works · Data refreshed daily, snapshot 2026-10-20.