Frontier models ranked by benchmark intelligence — reasoning, coding, math and knowledge evals — with real-world request volume shown alongside. Sort by quality to find the strongest model, or by requests to see what the market actually runs.
| # | Model | Provider | Intelligence | Coding | Requests | Share |
|---|---|---|---|---|---|---|
| 1 | Claude Opus 5 anthropic/claude-opus-5 | Anthropic | 60.7 | 78.0 | — | — |
| 2 | Claude Fable 5 anthropic/claude-fable-5 | Anthropic | 59.9 | 76.5 | 242 | 0% |
| 3 | GPT-5.6 Sol openai/gpt-5.6-sol | OpenAI | 58.9 | 77.4 | — | — |
| 4 | Kimi K3 moonshot/kimi-k3 | Moonshot | 57.1 | 76.2 | — | — |
| 5 | Claude Opus 4.8 anthropic/claude-opus-4.8 | Anthropic | 55.7 | 74.3 | 37 | 0% |
| 6 | GPT-5.6 Terra openai/gpt-5.6-terra | OpenAI | 55.0 | 76.7 | — | — |
| 7 | GPT-5.5 openai/gpt-5.5 | OpenAI | 54.8 | 74.9 | 35.2K | 3.1% |
| 8 | Grok 4.5 xai/grok-4.5 | xAI | 53.8 | 72.4 | — | — |
| 9 | Claude Opus 4.7 anthropic/claude-opus-4.7 | Anthropic | 53.5 | 73.6 | 1 | 0% |
| 10 | Claude Sonnet 5 anthropic/claude-sonnet-5 | Anthropic | 53.4 | 71.5 | — | — |
| 11 | GPT-5.4 openai/gpt-5.4 | OpenAI | 51.4 | 71.1 | 19.2K | 1.7% |
| 12 | GPT-5.6 Luna openai/gpt-5.6-luna | OpenAI | 51.2 | 71.4 | — | — |
| 13 | Glm-5.2 zai-org/glm-5.2 | Zai-org | 51.1 | 68.8 | 16.1K | 1.4% |
| 14 | Gemini 3.5 Flash google/gemini-3.5-flash | 50.2 | 70.1 | — | — | |
| 15 | Gemini 3.6 Flash google/gemini-3.6-flash | 50.1 | 69.2 | — | — | |
| 16 | Claude Sonnet 4.6 anthropic/claude-sonnet-4.6 | Anthropic | 47.2 | 63.0 | — | — |
| 17 | Gemini 3.1 Pro google/gemini-3.1-pro | 46.5 | 68.8 | 40.7K | 3.5% | |
| 18 | MiniMax M3 minimax/m3 | MiniMax | 44.4 | 58.6 | — | — |
| 19 | DeepSeek V4 Pro deepseek/deepseek-v4-pro | Deepseek | 44.3 | 59.4 | 57.9K | 5% |
| 20 | Kimi-K2.6 moonshot/kimi-k2.6 | Moonshot | 44.2 | 61.8 | 9.4K | 0.8% |
| 21 | Claude Opus 4.6 anthropic/claude-opus-4.6 | Anthropic | 43.7 | — | — | — |
| 22 | Kimi-K2.7-Code moonshot/kimi-k2.7-code | Moonshot | 41.9 | 60.8 | 4.3K | 0.4% |
| 23 | Claude Opus 4.5 anthropic/claude-opus-4.5 | Anthropic | 40.8 | — | 1 | 0% |
| 24 | GPT-5.4 Mini openai/gpt-5.4-mini | OpenAI | 40.0 | 56.1 | 60.6K | 5.3% |
| 25 | GPT-5.4 Nano openai/gpt-5.4-nano | OpenAI | 38.2 | 56.1 | 14.7K | 1.3% |
| 26 | MiniMax M2.7 minimax/m2.7 | MiniMax | 38.1 | 52.6 | — | — |
| 27 | Gemini 3 Flash google/gemini-3-flash | 37.8 | — | 248.8K | 21.6% | |
| 28 | Grok 4.3 xai/grok-4.3 | xAI | 37.6 | 42.2 | 34.4K | 3% |
| 29 | GPT-5.1 openai/gpt-5.1 | OpenAI | 36.9 | 49.4 | — | — |
| 30 | Gemini 3.5 Flash-Lite google/gemini-3.5-flash-lite | 36.5 | 49.3 | — | — | |
| 31 | Grok 4.20 Non-Reasoning xai/grok-4.20-0309-non-reasoning | xAI | 36.5 | — | — | — |
| 32 | Grok 4.20 Reasoning xai/grok-4.20-0309-reasoning | xAI | 36.5 | — | — | — |
| 33 | Claude Sonnet 4.5 anthropic/claude-sonnet-4.5 | Anthropic | 36.4 | 52.1 | 1 | 0% |
| 34 | GPT-5 openai/gpt-5 | OpenAI | 34.7 | 37.8 | 2.9K | 0.3% |
| 35 | Qwen 3.5 397B A17B alibaba/qwen3.5-397b-a17b | Alibaba | 33.7 | 48.2 | 242 | 0% |
| 36 | Grok 4 xai/grok-4 | xAI | 33.3 | — | — | — |
| 37 | Qwen 3 Max alibaba/qwen3-max | Alibaba | 31.7 | — | 484 | 0% |
| 38 | GPT-5 Mini openai/gpt-5-mini | OpenAI | 30.9 | — | 34.8K | 3% |
| 39 | O3 openai/o3 | OpenAI | 30.4 | — | 139 | 0% |
| 40 | Claude Haiku 4.5 anthropic/claude-haiku-4.5 | Anthropic | 29.6 | 43.9 | 2.9K | 0.2% |
| Provider | Models | Requests |
|---|---|---|
| 11 | 766.6K | |
| OpenAI | 27 | 246.4K |
| Deepseek | 2 | 57.9K |
| xAI | 7 | 35.0K |
| Zai-org | 2 | 16.1K |
| Moonshot | 3 | 13.6K |
| Anthropic | 11 | 3.7K |
| Mistral | 1 | 2.6K |
| Ibm-granite | 1 | 2.4K |
| Meta | 5 | 1.7K |
| Black Forest Labs | 9 | 1.1K |
| Inworld | 2 | 947 |
Intelligence and coding scores come from Artificial Analysis evals baked into the catalog on every release; request volume is real aggregate demand across the open model ecosystem, refreshed daily. For the full benchmark + pricing table, see the model leaderboard.