Skip to content

Value ranking

Best value on Rolling Contamination-Controlled Average

As of October 25, 2026, the best value on Rolling Contamination-Controlled Average is DeepSeek V3 (Thinking), at 344.83 normalized points per dollar of input price ($0.29 per million tokens, score 100.0).

Contamination-controlled average across every task category in the latest rolling release (e.g. reasoning, coding, data analysis, research, browsing, long-horizon tasks). Questions are rotated with each release and graded against objective ground truth, removing the need for LLM-as-judge scoring. Only models with a score in every category get an average.

“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 (Thinking)
    DeepSeek
    344.83
    100.0 / $0.29/M
  2. 2
    Gemini 2.5 Pro (Max Thinking)
    Google
    113.65
    71.0 / $0.63/M
  3. 3
    DeepSeek V3
    DeepSeek
    77.45
    22.5 / $0.29/M
  4. 4
    Qwen3 235B (Thinking)
    Alibaba (Qwen)
    68.69
    30.9 / $0.45/M
  5. 5
    Claude Sonnet 4 (Thinking)
    Anthropic
    31.01
    93.0 / $3.00/M
  6. 6
    Claude Opus 4 (Thinking)
    Anthropic
    6.47
    97.1 / $15.00/M
  7. 7
    Claude Sonnet 4
    Anthropic
    5.34
    16.0 / $3.00/M
  8. 8
    Claude Opus 4
    Anthropic
    2.80
    42.0 / $15.00/M
  9. 9
    Qwen3 235B
    Alibaba (Qwen)
    0.00
    0.0 / $0.09/M
Open full leaderboard

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