LLM Benchmarker Suite: leaderboard
FormulaMonks multi-benchmark suite averaging classic LLM tasks including MMLU, TriviaQA, GSM8K, HumanEval, BoolQ, HellaSwag, and Winogrande.
Metric: Average Score (%). Source: github.com. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 2 70B | 62.53 | #1201 |
| 2 | falcon-40B | 56.36 | #1442 |
| 3 | Llama 2 13B | 53.01 | #1436 |
| 4 | mpt-30B | 48.93 | #1476 |
| 5 | Llama 2 7B | 46.88 | #1520 |
| 6 | mpt-7B | 41.96 | #1619 |
| 7 | falcon-7B | 40.74 | #1598 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=llm-benchmarker-suite · How It Works · Data refreshed daily, snapshot 2026-10-20.