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
    Gemini 3 Pro
    Google
    80.00
    100.0 / $1.25/M
  2. 2
    GPT-5.5
    OpenAI
    66.67
    100.0 / $1.50/M
  3. 3
    GPT-5.4
    OpenAI
    48.20
    72.3 / $1.50/M
  4. 4
    Claude Sonnet 4.5
    Anthropic
    33.33
    100.0 / $3.00/M
  5. 5
    Claude Opus 4.6
    Anthropic
    6.67
    100.0 / $15.00/M
  6. 6
    Claude Opus 4.7
    Anthropic
    6.67
    100.0 / $15.00/M
  7. 7
    Claude Opus 4.5
    Anthropic
    3.90
    58.5 / $15.00/M
  8. 8
    Claude Sonnet 4.6
    Anthropic
    0.00
    0.0 / $3.00/M
Open full leaderboard

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