Rankings
Best for Chatbots
Fast, cost-efficient models ideal for real-time conversational applications.
Models ranked
1388
Top context
33K
Qwen2 5 Coder 7b
Leading provider
Openai
240 models in this ranking
Leaderboard
Tap any row to see full specs and comparisons.
| Rank | Model | Context | Max output | Input $/M | Chat score |
|---|---|---|---|---|---|
| 1 | Qwen2 5 Coder 7bAlibaba | 33K | — | $0.010/M | fast |
| 2 | Llama3 2 11b VisionMeta | 131K | 131K | $0.015/M | fast |
| 3 | Llama3 2 3bMeta | 131K | 131K | $0.015/M | fast |
| 4 | Granite 4.0 MicroIbm | 131K | 131K | $0.017/M | balanced |
| 5 | Mistral NemoMistral | 131K | 4K | $0.019/M | balanced |
| 6 | Mistral Nemo Instruct 2407Mistral | 131K | 131K | $0.019/M | balanced |
| 7 | Meta Llama 3 1 8bMeta | 128K | 2K | $0.020/M | fast |
| 8 | Llama 3 2 3bMeta | 131K | 131K | $0.020/M | fast |
| 9 | Llama Guard 3 8BMeta | 131K | 131K | $0.020/M | fast |
| 10 | Meta Llama 3 1 8b InstructMeta | 131K | 131K | $0.020/M | fast |
| 11 | Qwen2 Vl 7bAlibaba | 131K | 131K | $0.020/M | fast |
| 12 | Llama 3 1 8bMeta | 131K | 16K | $0.020/M | fast |
| 13 | Llama 3 2 1bMeta | 128K | 128K | $0.020/M | fast |
| 14 | Gemma 4 E4b ItGoogle | 131K | — | $0.020/M | balanced |
| 15 | Llama3 1 8bMeta | 128K | 128K | $0.025/M | fast |
| 16 | Hermes3 8bNous Research | 131K | 131K | $0.025/M | fast |
| 17 | Deepseek R1 Distill Llama 8bMeta | 131K | — | $0.025/M | fast |
| 18 | Qwen3.7 FlashAlibaba | 1M | 66K | $0.030/M | fast |
| 19 | Meta Llama 3 8bMeta | 8K | 8K | $0.030/M | fast |
| 20 | Granite 3 3 8bIbm | 8K | — | $0.030/M | fast |
| 21 | gpt-oss-20bOpenai | 131K | 131K | $0.030/M | balanced |
| 22 | Qwen3 4b Fp8Alibaba | 128K | 20K | $0.030/M | balanced |
| 23 | Deepseek OcrDeepseek | 8K | 8K | $0.030/M | balanced |
| 24 | Deepseek Ocr 2Deepseek | 8K | 8K | $0.030/M | balanced |
| 25 | Llama Prompt Guard 2 22mMeta | 1K | 1K | $0.030/M | balanced |
Showing 25 of 1388 models
More rankings
Explore other model leaderboards.
Largest Context Window
Models ranked by maximum context window size.
Best for RAG
Models best suited for Retrieval-Augmented Generation workloads.
Best for AI Agents
Models with the capabilities needed to power autonomous agent workflows.
Best for Document Processing
Models with large enough context to process long documents in one pass.
Best Value per Context Token
Models offering the most context window per dollar of input cost.
Best Multimodal
Vision-capable models with the largest context windows.
Best Reasoning
Models with extended thinking or strong reasoning capabilities.