Skip to content

Value ranking

Best value on Rolling Data Analysis

As of October 25, 2026, the best value on Rolling Data Analysis is DeepSeek V3 (Thinking), at 242.62 normalized points per dollar of input price ($0.29 per million tokens, score 70.4).

Rolling contamination-controlled data-analysis evaluation. Table comprehension, CSV / spreadsheet reasoning, SQL-style joins, and chart interpretation. Refreshed every six months with new tables and questions to minimise contamination.

“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
    242.62
    70.4 / $0.29/M
  2. 2
    Qwen3 235B (Thinking)
    Alibaba (Qwen)
    170.67
    76.8 / $0.45/M
  3. 3
    Gemini 2.5 Pro (Max Thinking)
    Google
    114.40
    71.5 / $0.63/M
  4. 4
    Qwen3 235B
    Alibaba (Qwen)
    68.44
    6.2 / $0.09/M
  5. 5
    Claude Sonnet 4 (Thinking)
    Anthropic
    33.33
    100.0 / $3.00/M
  6. 6
    DeepSeek V3
    DeepSeek
    31.34
    9.1 / $0.29/M
  7. 7
    Claude Opus 4 (Thinking)
    Anthropic
    3.10
    46.5 / $15.00/M
  8. 8
    Claude Opus 4
    Anthropic
    0.83
    12.4 / $15.00/M
  9. 9
    Claude Sonnet 4
    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.