Fastest AI Models
Top AI models by generation speed — maximum throughput via API.
| # | Model | Score |
|---|---|---|
 GPT OSS 20B | 43.6% | |
GPT OSS 120B | 52.0% | |
GPT-5 nano | 50.1% | |
| 4 |  Step-3.5-Flash | 78.6% |
| 5 |  Qwen3 32B | 72.0% |
| 6 | GPT-5.4 mini | 59.1% |
| 7 |  Gemini 3 Flash | 63.0% |
| 8 |  Claude Opus 4.5 | 75.3% |
| 9 | GPT-5.4 nano | 55.8% |
| 10 | GPT-5.1 Codex | 64.3% |
| 11 | GPT-5.1 Instant | 77.9% |
| 12 | GPT-5 mini | 60.0% |
| 13 | GPT-4.1 nano | 34.2% |
| 14 |  Llama 3.1 8B Instruct | 61.3% |
| 15 |  Mistral Large 3 (675B Instruct 2512) | 47.9% |
Want a detailed comparison of the leaders? → GPT OSS 20B vs GPT OSS 120B
Other Collections
Coding
Top AI models for writing code, debugging, and solving real-world development tasks.
Math
Top AI models for solving mathematical problems and computations.
Reasoning
Top AI models for reasoning tasks, analysis, and expert knowledge.
Cheap
Top AI models with the lowest API prices — maximum quality for minimum cost.
Multimodal
Top AI models with support for text, images, audio, and video.
Large Context
Top AI models with the largest context window — for working with long documents.
General Knowledge
Top AI models on the MMLU benchmark — broad knowledge across dozens of subjects.
Function Calling
Top AI models for function calling and agentic tool use.
Image Analysis
Top AI models for analyzing charts, diagrams, and visual data.
Free
AI models with free API access — open source and free-tier providers.
AI Agents
Top AI models for building autonomous agents with tool use and planning.
Ranking updated in 2026 based on official benchmarks and independent tests. See also model comparisons and the full catalog.