Price-performance leaders in 2026
Models ranked by average benchmark score per dollar of blended token cost, limited to models scoring at least 60. 452 models qualify.
What the data shows
The leader scores 60.1 at $2.33 blended per million tokens. That ratio is a rough value signal, not a quality guarantee: a model can be efficient and still fail your task.
Value rankings are sensitive to the score floor and the price blend. Change either and the order moves.
How to read the ranking
- Use the ranking to find candidates, not to pick a winner.
- Check the benchmark that matches your workload.
- Include retry and output costs in the estimate.
- Test the top value candidate against a premium model.
Price-performance leaders
| # | Model | Provider | Input / 1M | Output / 1M | Context | Avg score |
|---|---|---|---|---|---|---|
| 1 | Llama 3.3 8B | Meta AI | $1.26 | $5.56 | 8,192 | 60.1 |
| 2 | Llama 4 Scout 7B | Meta AI | $1.30 | $5.58 | 32,768 | 60.0 |
| 3 | StableLM 2 Base | Stability AI | $1.49 | $5.44 | 8,192 | 61.9 |
| 4 | GPT-NeoX Instruct | EleutherAI | $1.52 | $5.60 | 16,384 | 62.6 |
| 5 | Pythia Instruct | EleutherAI | $1.41 | $5.70 | 8,192 | 60.8 |
| 6 | GLM-4.5 7B | Zhipu AI | $1.32 | $5.93 | 8,192 | 60.2 |
| 7 | Magistral 8B | Mistral AI | $1.33 | $6.03 | 4,096 | 60.0 |
| 8 | Kimi K1.5 8B | Moonshot AI | $1.54 | $5.98 | 8,192 | 62.2 |
| 9 | Llama 4 Scout 8B | Meta AI | $1.46 | $6.51 | 8,192 | 61.2 |
| 10 | GLM-4.5 8B | Zhipu AI | $1.46 | $6.70 | 32,768 | 61.3 |
| 11 | Zephyr Instruct | Hugging Face | $1.66 | $6.50 | 4,096 | 62.4 |
| 12 | Zephyr | Hugging Face | $1.61 | $6.84 | 8,192 | 62.8 |
| 13 | MiniMax-M2 7B | MiniMax | $1.44 | $7.00 | 8,192 | 60.8 |
| 14 | GLM-4.6 7B | Zhipu AI | $1.52 | $6.98 | 16,384 | 61.8 |
| 15 | Qwen3 8B | Alibaba Cloud | $1.66 | $6.65 | 8,192 | 61.9 |
| 16 | Qwen3-Coder 8B | Alibaba Cloud | $1.43 | $7.30 | 32,768 | 61.3 |
| 17 | Mistral Large 3 8B | Mistral AI | $1.62 | $6.82 | 16,384 | 61.6 |
| 18 | DeepSeek-V3.2 7B | DeepSeek | $1.75 | $6.84 | 4,096 | 63.2 |
| 19 | Mistral Large 3 7B | Mistral AI | $1.44 | $7.37 | 32,768 | 61.1 |
| 20 | SmolLM3 Base | Hugging Face | $1.38 | $7.55 | 16,384 | 60.4 |
Methodology
This story uses the AI & LLM Index dataset: 600 models, 40 providers and 12 benchmarks. Prices are listed per million tokens. Scores are modelled estimates on a 0–100 scale and are not official benchmark results. Figures are rounded for readability.
Related
FAQ
What does the Price-performance leaders in 2026 data show?
Models ranked by average benchmark score per dollar of blended token cost, limited to models scoring at least 60. 452 models qualify.
Are the numbers official?
No. Prices and scores are compiled for this demo index. Benchmark values are modelled estimates, not official results. Verify figures with the provider or benchmark owner before making decisions.
How should I use this ranking?
Use it to form a shortlist. Check the specific model pages, compare price and context, and test the shortlist on your own examples before committing.