Klu LLM Leaderboard: leaderboard
Compare models from Anthropic, Google, OpenAI, DeepSeek, and more across key text-only benchmarks with regular updates.
Metric: Klu Index. Source: klu.ai. Saturation forecast: Estimated already saturated. 48 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4 Turbo | 100 | #404 |
| 2 | GPT-4 Turbo (Preview) | 100 | #397 |
| 3 | O1 Preview | 99 | #193 |
| 4 | Claude 3.5 Sonnet | 97 | #350 |
| 5 | Gemini 1.5 Pro | 96 | #445 |
| 6 | Claude 3 Opus | 91 | #571 |
| 7 | Gemini 1.5 Flash | 89 | #618 |
| 8 | Llama 3.1 405B | 89 | #466 |
| 9 | Mistral Large 2 (Jul) | 88 | #484 |
| 10 | Llama 3.1 70B | 86 | #592 |
| 11 | Gemma 2 27B | 83 | #806 |
| 12 | Claude 3 Haiku | 82 | #803 |
| 13 | Claude 3 Sonnet | 82 | #775 |
| 14 | GPT-4 (0613) | 79 | #491 |
| 15 | Mistral Large | 79 | #710 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=klu-llm-leaderboard · How It Works · Data refreshed daily, snapshot 2026-10-20.