AMA

Value ranking

Best value on Safety Handling

How well the model handles safety-sensitive prompts without false-refusing benign requests or producing unsafe output. The upstream signal does not separate refusal counts from substantive content-safety behaviour, so this single axis covers both.

“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
    DeepSeek V3
    DeepSeek
    370.37
    100.0 / $0.27/M
  2. 2
    Gemini 2.5 Flash
    Google
    333.33
    100.0 / $0.30/M
  3. 3
    GLM-4.6
    Zhipu AI (GLM)
    200.00
    100.0 / $0.50/M
  4. 4
    GLM-4.7
    Zhipu AI (GLM)
    200.00
    100.0 / $0.50/M
  5. 5
    DeepSeek R1
    DeepSeek
    181.82
    100.0 / $0.55/M
  6. 6
    Kimi K2
    Moonshot (Kimi)
    166.67
    100.0 / $0.60/M
  7. 7
    GPT-5.2
    OpenAI
    80.00
    100.0 / $1.25/M
  8. 8
    Gemini 3 Pro
    Google
    80.00
    100.0 / $1.25/M
  9. 9
    GPT-5.4
    OpenAI
    66.67
    100.0 / $1.50/M
  10. 10
    GPT-5.5
    OpenAI
    66.67
    100.0 / $1.50/M
  11. 11
    Claude Sonnet 4
    Anthropic
    33.33
    100.0 / $3.00/M
  12. 12
    Claude Sonnet 4.5
    Anthropic
    33.33
    100.0 / $3.00/M
  13. 13
    Claude Sonnet 4.6
    Anthropic
    22.49
    67.5 / $3.00/M
  14. 14
    Grok 4
    xAI
    20.00
    100.0 / $5.00/M
  15. 15
    Claude Opus 4.6
    Anthropic
    6.67
    100.0 / $15.00/M
  16. 16
    Claude Opus 4.7
    Anthropic
    6.67
    100.0 / $15.00/M
  17. 17
    Claude Opus 4
    Anthropic
    2.55
    38.3 / $15.00/M
  18. 18
    Claude Opus 4.5
    Anthropic
    0.00
    0.0 / $15.00/M
Open full leaderboard

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