AMA

Value ranking

Best value on Chatbot Arena Elo

Crowdsourced pairwise human preference rankings of LLM responses. Higher Elo means more frequently preferred by users.

“Value” is normalized benchmark score (0–100 for this leaderboard cohort) divided by input price per million tokens. Higher means more capability per dollar on this axis only — always sanity-check latency, context length, and your real workload.

  1. 1
    GPT-5 nano
    OpenAI
    1024.40
    51.2 / $0.05/M
  2. 2
    Gemini 2.0 Flash
    Google
    621.70
    62.2 / $0.10/M
  3. 3
    Gemini 1.5 Flash
    Google
    538.27
    40.4 / $0.08/M
  4. 4
    Qwen3 235B (Thinking)
    Alibaba (Qwen)
    407.20
    81.4 / $0.20/M
  5. 5
    Qwen3 235B
    Alibaba (Qwen)
    329.70
    65.9 / $0.20/M
  6. 6
    DeepSeek V3 (Thinking)
    DeepSeek
    314.07
    84.8 / $0.27/M
  7. 7
    DeepSeek V3
    DeepSeek
    312.48
    84.4 / $0.27/M
  8. 8
    Gemini 3 Flash
    Google
    307.70
    92.3 / $0.30/M
  9. 9
    Gemini 2.5 Flash
    Google
    275.40
    82.6 / $0.30/M
  10. 10
    GPT-5 mini
    OpenAI
    274.20
    68.5 / $0.25/M
  11. 11
    GPT-4o mini
    OpenAI
    268.60
    40.3 / $0.15/M
  12. 12
    Llama 4 Scout
    Meta
    213.72
    38.5 / $0.18/M
  13. 13
    GLM-4.6
    Zhipu AI (GLM)
    180.26
    90.1 / $0.50/M
  14. 14
    GLM-4.7
    Zhipu AI (GLM)
    175.54
    87.8 / $0.50/M
  15. 15
    DeepSeek R1
    DeepSeek
    156.51
    86.1 / $0.55/M
  16. 16
    Llama 4 Maverick
    Meta
    150.63
    40.7 / $0.27/M
  17. 17
    Kimi K2
    Moonshot (Kimi)
    139.97
    84.0 / $0.60/M
  18. 18
    Gemini 2.5 Pro
    Google
    77.26
    96.6 / $1.25/M
  19. 19
    Claude Haiku 4.5
    Anthropic
    74.50
    74.5 / $1.00/M
  20. 20
    Gemini 3 Pro
    Google
    73.52
    91.9 / $1.25/M
  21. 21
    GPT-5.1
    OpenAI
    72.30
    90.4 / $1.25/M
  22. 22
    GPT-5.4
    OpenAI
    66.67
    100.0 / $1.50/M
  23. 23
    GPT-5.5
    OpenAI
    65.95
    98.9 / $1.50/M
  24. 24
    GPT-5.2
    OpenAI
    65.83
    82.3 / $1.25/M
  25. 25
    GPT-5
    OpenAI
    63.01
    78.8 / $1.25/M
Open full leaderboard

AI Model Analyzer does not recommend specific vendors; rankings are derived from public data only.