Top benchmarked models and their cheapest blended price
Snapshot of the 25 highest-ranked models (Artificial Analysis Intelligence Index, 412 benchmarked models total). The interactive table above adds use-case tabs, live token-mix pricing, and capability-per-dollar value ranking.
| Model | Creator | AA Intelligence | AA Agentic | AA Coding | LiveBench Reasoning | Design Arena Elo | From $/M |
|---|---|---|---|---|---|---|---|
| anthropic/claude-sonnet-4-6 | anthropic | — | — | — | 84.8 | — | $3.06 |
| zai-org/GLM-5.2 | z-ai | — | 38.4 | 68.8 | 78.6 | 1290 | $0.046 |
| SpaceXAI: Grok Build 0.1 | x-ai | — | — | 51.5 | 76.4 | — | $0.229 |
| Qwen: Qwen3.6 Plus | qwen | — | — | 54.5 | 75.8 | 1242 | $0.068 |
| deepseek-ai/DeepSeek-V4-Flash | deepseek | — | 22.2 | 56.2 | 70.6 | 1206 | $0.008 |
| Anthropic: Claude Opus 5.5 | anthropic | 58.4 | — | — | — | 1466 | $0.419 |
| Anthropic: Claude Opus 5.5 (fast) | anthropic | 58.4 | — | — | — | 1466 | $0.838 |
| Anthropic: Claude Opus 5.5 (batch) | anthropic | 58.4 | — | — | — | 1466 | $0.21 |
| gpt-6-astra | openai | 56.9 | 51 | 76.9 | — | — | $1.32 |
| OpenAI: GPT-6 Astra (flex) | openai | 56.9 | 51 | 76.9 | — | — | $0.766 |
| OpenAI: GPT-6 Astra (fast) | openai | 56.9 | 51 | 76.9 | — | — | $3.065 |
| OpenAI: GPT-6 Astra (ultrafast) | openai | 56.9 | 51 | 76.9 | — | — | $9.195 |
| OpenAI: GPT-6 Astra (batch) | openai | 56.9 | 51 | 76.9 | — | — | $0.766 |
| gpt-6.1-sol | openai | 54.5 | — | — | — | 1437 | $0.197 |
| OpenAI: GPT-6.1 Sol (flex) | openai | 54.5 | — | — | — | 1437 | $0.105 |
| OpenAI: GPT-6.1 Sol (fast) | openai | 54.5 | — | — | — | 1437 | $0.419 |
| OpenAI: GPT-6.1 Sol (ultrafast) | openai | 54.5 | — | — | — | 1437 | $1.257 |
| OpenAI: GPT-6.1 Sol (batch) | openai | 54.5 | — | — | — | 1437 | $0.105 |
| Anthropic: Claude Sonnet 5.5 | anthropic | 54.2 | — | — | — | 1412 | $0.21 |
| Anthropic: Claude Sonnet 5.5 (batch) | anthropic | 54.2 | — | — | — | 1412 | $0.105 |
| OpenAI: GPT-6.1 Terra (flex) | openai | 51 | — | — | — | — | $0.052 |
| OpenAI: GPT-6.1 Terra | openai | 51 | — | — | — | — | $0.105 |
| OpenAI: GPT-6.1 Terra (fast) | openai | 51 | — | — | — | — | $0.21 |
| OpenAI: GPT-6.1 Terra (batch) | openai | 51 | — | — | — | — | $0.052 |
| anthropic/claude-opus-5 | anthropic | 50.8 | 56.5 | 78 | — | 1358 | $0.766 |
Catalog snapshot . Scores from Artificial Analysis, LiveBench and Design Arena. "From $/M" is the cheapest provider's blended rate at 2.5% input, 97% cached input, 0.5% output. This is a catalog snapshot, not the date every benchmark was measured. See the benchmark FAQ for what each score measures.
Frequently asked questions
Where are the full FAQ lists?
All questions — choosing a model and provider, text/token pricing, image and video generation pricing, and plain-language benchmark explainers — live on the consolidated FAQ page.