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
    944.00
    47.2 / $0.05/M
  2. 2
    Gemini 2.0 Flash
    Google
    573.70
    57.4 / $0.10/M
  3. 3
    Gemini 1.5 Flash
    Google
    496.80
    37.3 / $0.08/M
  4. 4
    Qwen3 235B (Thinking)
    Alibaba (Qwen)
    376.00
    75.2 / $0.20/M
  5. 5
    Qwen3 235B
    Alibaba (Qwen)
    304.30
    60.9 / $0.20/M
  6. 6
    Gemini 3 Flash
    Google
    303.57
    91.1 / $0.30/M
  7. 7
    DeepSeek V3 (Thinking)
    DeepSeek
    289.56
    78.2 / $0.27/M
  8. 8
    DeepSeek V3
    DeepSeek
    289.33
    78.1 / $0.27/M
  9. 9
    Gemini 2.5 Flash
    Google
    254.97
    76.5 / $0.30/M
  10. 10
    GPT-5 mini
    OpenAI
    252.96
    63.2 / $0.25/M
  11. 11
    GPT-4o mini
    OpenAI
    247.93
    37.2 / $0.15/M
  12. 12
    Llama 4 Scout
    Meta
    197.00
    35.5 / $0.18/M
  13. 13
    GLM-4.6
    Zhipu AI (GLM)
    166.48
    83.2 / $0.50/M
  14. 14
    GLM-4.7
    Zhipu AI (GLM)
    163.84
    81.9 / $0.50/M
  15. 15
    DeepSeek R1
    DeepSeek
    144.44
    79.4 / $0.55/M
  16. 16
    Llama 4 Maverick
    Meta
    139.07
    37.5 / $0.27/M
  17. 17
    Kimi K2
    Moonshot (Kimi)
    125.72
    75.4 / $0.60/M
  18. 18
    Gemini 3 Pro
    Google
    77.84
    97.3 / $1.25/M
  19. 19
    Gemini 2.5 Pro
    Google
    71.27
    89.1 / $1.25/M
  20. 20
    Claude Haiku 4.5
    Anthropic
    67.57
    67.6 / $1.00/M
  21. 21
    GPT-5.1
    OpenAI
    66.81
    83.5 / $1.25/M
  22. 22
    GPT-5.5
    OpenAI
    61.95
    92.9 / $1.50/M
  23. 23
    GPT-5.2
    OpenAI
    61.20
    76.5 / $1.25/M
  24. 24
    GPT-5.4
    OpenAI
    61.15
    91.7 / $1.50/M
  25. 25
    GPT-5
    OpenAI
    58.14
    72.7 / $1.25/M
Open full leaderboard

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