Skip to content

Value ranking

Best value on Format Adherence

As of October 25, 2026, the best value on Format Adherence is GPT-6 Luna, at 2000.00 normalized points per dollar of input price ($0.05 per million tokens, score 100.0).

How reliably the model produces output in the requested format (JSON schemas, markdown structures, exact-string responses). Pairs well with IFEval but reflects how the deployed API is behaving day to day rather than how a frozen test set scores.

“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-6 Luna
    OpenAI
    2000.00
    100.0 / $0.05/M
  2. 2
    GPT-5.6 Luna
    OpenAI
    630.40
    63.0 / $0.10/M
  3. 3
    DeepSeek V4 Flash 0423
    DeepSeek
    592.97
    54.0 / $0.09/M
  4. 4
    DeepSeek V4 Pro 0423
    DeepSeek
    478.93
    100.0 / $0.21/M
  5. 5
    Gemini 3.5 Flash Lite
    Google
    455.00
    68.3 / $0.15/M
  6. 6
    Gemini 3.8 Flash
    Google
    266.67
    100.0 / $0.38/M
  7. 7
    GPT-6 Sol
    OpenAI
    100.00
    100.0 / $1.00/M
  8. 8
    GPT-5.6 Terra
    OpenAI
    59.79
    59.8 / $1.00/M
  9. 9
    GPT-5.6 Sol
    OpenAI
    50.00
    100.0 / $2.00/M
  10. 10
    Kimi K3
    Moonshot (Kimi)
    33.33
    100.0 / $3.00/M
  11. 11
    GPT-5.5
    OpenAI
    23.89
    59.7 / $2.50/M
  12. 12
    GLM 5.3
    Zhipu AI (GLM)
    19.84
    27.8 / $1.40/M
  13. 13
    Claude Opus 4.6
    Anthropic
    19.70
    98.5 / $5.00/M
  14. 14
    Claude Opus 5
    Anthropic
    19.04
    95.2 / $5.00/M
  15. 15
    Claude Opus 5.5
    Anthropic
    16.29
    65.2 / $4.00/M
  16. 16
    Kimi K2.7 Code
    Moonshot (Kimi)
    15.06
    14.3 / $0.95/M
  17. 17
    Claude Sonnet 5.5
    Anthropic
    14.56
    29.1 / $2.00/M
  18. 18
    Claude Opus 4.7
    Anthropic
    13.46
    67.3 / $5.00/M
  19. 19
    Claude Sonnet 4.6
    Anthropic
    13.20
    39.6 / $3.00/M
  20. 20
    Claude Sonnet 5
    Anthropic
    9.19
    18.4 / $2.00/M
  21. 21
    Claude Opus 4.8
    Anthropic
    8.61
    43.1 / $5.00/M
  22. 22
    GPT-6 Astra
    OpenAI
    8.37
    41.8 / $5.00/M
  23. 23
    Claude Fable 5.1
    Anthropic
    1.26
    12.6 / $10.00/M
  24. 24
    GPT-6.1 Sol
    OpenAI
    0.00
    0.0 / $1.00/M
Open full leaderboard

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