Best AI Models by Price and Performance

The most SI Score per dollar, using a blended price of input and output tokens at a 3:1 mix.

How this list is ranked. Ranked by value score = SI Score ÷ (blended price + $0.25), where blended price = 0.75 × input + 0.25 × output per 1M tokens (a typical 3:1 mix). The $0.25 floor keeps free tiers from exploding the ratio.

  1. 1 Gemma 4 26B A4B IT Googleprovisional 253.6 63.4 $0.00 262K
  2. 2 Gemma 4 31B IT Googleprovisional 252.0 63.0 $0.00 262K
  3. 3 Hy3 Tencentprovisional 242.8 60.7 $0.00 256K
  4. 4 GLM-4.7-Flash Z.aiprovisional 213.2 53.3 $0.00 200K
  5. 5 Qwen3.5 Flash Alibaba / Qwenprovisional 173.2 59.5 $0.03 1M
  6. 6 Qwen3.5 35B-A3B Alibaba / Qwenprovisional 153.9 62.7 $0.06 262K
  7. 7 GPT-6 Luna OpenAI 136.9 61.6 $0.10 1.1M
  8. 8 GLM-5.3-Flash Z.aiprovisional 135.8 66.2 $0.15 1M
  9. 9 MiMo-V2.5 Xiaomiprovisional 132.7 56.4 $0.14 1M
  10. 10 Step 3.5 Flash StepFunprovisional 132.5 53.0 $0.10 256K
  11. 11 Claude Haiku 5.5 Anthropic 132.0 59.4 $0.10 1M
  12. 12 MiMo-V2.6-Flash Xiaomiprovisional 131.3 55.8 $0.14 1M
  13. 13 DeepSeek V4.1 Flash DeepSeek 129.2 66.2 $0.15 1M
  14. 14 Qwen3 30B A3B Alibaba / Qwenprovisional 119.9 52.6 $0.11 131K
  15. 15 GPT-5 Nano OpenAI 100.9 39.1 $0.05 400K

Updated Oct 9, 2026. Task lists rank on one stated measure rather than the blended SI Score. See the methodology for how pillars and confidence are computed; a dash means the source has not reported that value.

What changed

All releases · RSS feed

Alerts on this device

What to be alerted about
RSS feed