Cost vs Capability
Every model plotted by price (x) against capability (y). The x-axis is inverted — cheaper to the right — and defaults to the cheapest modeled USD per task. The global toggle restores raw list prices per million tokens using your chosen fixed input/output blend; the y-axis is your chosen benchmark score. The best value sits in the upper-right.
Up & to the right is better: more capability for less money. The green Pareto frontier marks and connects the best-value models — those no other model beats on both price and capability. Click any point to open the model detail.
Adjusted costs are modeled USD per task: AA output tokens × OpenRouter usage I/O (Chutes global fallback). These are general usage and benchmark proxies for coding-agent work. Missing AA data assumes 1,000 output tokens/task; unknown cache hit assumes 0%; unmeasured additional cache writes assume 0 tokens. Click any underlined price for exact inputs, dates and assumptions. Raw list prices use the selected fixed input/output blend, in USD per million tokens.
Model prices and scores (accessible table, 30 rows)
| Model | Composite (coverage-neutral, dominance-safe percentiles, 0–100) · 5 fixed inputs; Coding Agent v1.4 | Adjusted $/task |
|---|---|---|
| Kimi K2.5 Moonshot AI · open | 50.8 | |
| Kimi K2.6 Moonshot AI · open | 61.9 | |
| DeepSeek V4 Pro DeepSeek · open | 60.0 | |
| GLM-5.2 Z.ai · open | 70.9 | |
| GPT-5.4 OpenAI | 65.4 | |
| Claude Opus 4.7 Anthropic | 77.4 | |
| Claude Opus 4.6 Anthropic | 70.8 | |
| GLM-5.3-Flash Z.ai · open | 77.4 | |
| MiMo-V2.5-Pro Xiaomi · open | 60.1 | |
| Claude Sonnet 4.6 Anthropic | 60.3 | |
| GPT-5.6 Luna OpenAI | 70.8 | |
| Kimi K2.7 Code Moonshot AI · open | 60.2 | |
| GPT-5.6 Sol OpenAI | 77.5 | |
| GPT-5.6 Terra OpenAI | 65.4 | |
| MiniMax-M3 MiniMax · open | 66.6 | |
| GLM-5.1 Z.ai · open | 56.5 | |
| GLM-5.3 Z.ai · open | 87.1 | |
| Grok 4.5 xAI | 82.8 | |
| DeepSeek V4 Pro 0813 DeepSeek · open | 65.4 | |
| Muse Spark 1.2 Meta | 78.7 | |
| Grok 4.6 xAI | 91.2 | |
| Muse Spark 1.3 Meta | 95.4 | |
| Kimi K3 Moonshot AI · open | 92.4 | |
| GPT-5.5 OpenAI | 65.5 | |
| GPT-6 Astra OpenAI | 96.0 | |
| Claude Opus 5 Anthropic | 95.7 | |
| Claude Opus 4.8 Anthropic | 84.3 | |
| Claude Sonnet 5 Anthropic | 85.8 | |
| Claude Fable 5.1 Anthropic | 100.0 | |
| Claude Fable 5 Anthropic | 93.7 |