Best-value AI models
The frontier contains models for which no eligible alternative is at least as capable and no more expensive, with a strict advantage in one of those measures. It helps you compare trade-offs between benchmark quality and cost.
Which should you choose?
No single benchmark covers every use case. Try your own prompts and compare accuracy, response time, input/output support, and the actual bill.
AI models
| Model | Intelligence score | Benchmark cost (USD) | Input price / 1M tokens (USD) | Output price / 1M tokens (USD) | Output speed |
|---|---|---|---|---|---|
| Granite 4.2 3BIBMBest value frontier | 9.10 | $14.9 | 0.03 | 0.12 | 221 tok/s |
| GPT-5.6 Luna (Non-reasoning)OpenAIBest value frontier | 15.50 | $23.0 | 0.20 | 1.20 | 151 tok/s |
| GPT-5.6 Luna (low)OpenAIBest value frontier | 21.00 | $27.0 | 0.20 | 1.20 | 143 tok/s |
| GPT-5.6 Luna (medium)OpenAIBest value frontier | 25.00 | $44.3 | 0.20 | 1.20 | 144 tok/s |
| GPT-5.6 Luna (high)OpenAIBest value frontier | 32.10 | $108 | 0.20 | 1.20 | 138 tok/s |
| GPT-5.6 Luna (xhigh)OpenAIBest value frontier | 34.60 | $179 | 0.20 | 1.20 | 153 tok/s |
| MiMo-V2.6-ProXiaomiBest value frontier | 46.30 | $207 | 0.43 | 0.87 | 124 tok/s |
| Muse Spark 1.3 (max)MetaBest value frontier | 48.10 | $2000 | 1.25 | 4.25 | 222 tok/s |
| GPT-6 Astra (medium)OpenAIBest value frontier | 49.60 | $2434 | 10.00 | 50.00 | 54 tok/s |
| GPT-6 Astra (high)OpenAIBest value frontier | 50.90 | $2925 | 10.00 | 50.00 | 54 tok/s |
| GPT-6 Astra (xhigh)OpenAIBest value frontier | 52.40 | $3803 | 10.00 | 50.00 | 55 tok/s |
| GPT-6 Astra (max)OpenAIBest value frontier | 52.70 | $5324 | 10.00 | 50.00 | 65 tok/s |
| Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)AnthropicBest value frontier | 53.20 | $9063 | 10.00 | 50.00 | 63 tok/s |
| Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)AnthropicBest value frontier | 53.40 | $13129 | 10.00 | 50.00 | 67 tok/s |
Guides
How we compare models
Intelligence uses the Artificial Analysis Intelligence Index. Benchmark cost is the total USD cost of running that test, including reasoning tokens; it is not a per-token API price. Rankings use the same dataset and calculations in every language. General benchmark scores do not measure performance in a particular language or task.