Skip to content

Value ranking

Best value on FrontierMath Tiers 1-3

As of October 25, 2026, the best value on FrontierMath Tiers 1-3 is GPT-5 nano, at 640.40 normalized points per dollar of input price ($0.03 per million tokens, score 16.0).

Mathematical research problems spanning analysis, algebra, combinatorics and number theory. Tiers 1-3 are progressively harder; even frontier reasoning models only solve a small fraction. The hardest publicly reported benchmark for general mathematical reasoning.

“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-5 nano
    OpenAI
    640.40
    16.0 / $0.03/M
  2. 2
    GPT-5.4 Nano
    OpenAI
    500.20
    50.0 / $0.10/M
  3. 3
    GPT-5 mini
    OpenAI
    421.52
    52.7 / $0.13/M
  4. 4
    Gemini 3 Flash
    Google
    275.76
    68.9 / $0.25/M
  5. 5
    Qwen3.5-Flash
    Alibaba (Qwen)
    184.77
    12.0 / $0.07/M
  6. 6
    Qwen3.6 Plus
    Alibaba (Qwen)
    155.97
    50.7 / $0.33/M
  7. 7
    GPT-5.4 Mini
    OpenAI
    145.87
    54.7 / $0.38/M
  8. 8
    Qwen3.6 Flash
    Alibaba (Qwen)
    106.72
    20.0 / $0.19/M
  9. 9
    Gemini 3.5 Flash
    Google
    100.49
    75.4 / $0.75/M
  10. 10
    GPT-5.1
    OpenAI
    96.05
    60.0 / $0.63/M
  11. 11
    Kimi K2
    Moonshot (Kimi)
    94.68
    54.0 / $0.57/M
  12. 12
    GPT-5.2
    OpenAI
    89.97
    78.7 / $0.88/M
  13. 13
    Kimi K2.6
    Moonshot (Kimi)
    79.34
    75.4 / $0.95/M
  14. 14
    GPT-5.4
    OpenAI
    73.66
    92.1 / $1.25/M
  15. 15
    Gemini 3.1 Pro
    Google
    72.73
    72.7 / $1.00/M
  16. 16
    Gemini 2.5 Flash
    Google
    62.47
    9.4 / $0.15/M
  17. 17
    GPT-5
    OpenAI
    50.16
    62.7 / $1.25/M
  18. 18
    GLM 5.1
    Zhipu AI (GLM)
    46.21
    64.7 / $1.40/M
  19. 19
    Gemini 2.5 Pro
    Google
    43.76
    27.4 / $0.63/M
  20. 20
    o4-mini
    OpenAI
    43.65
    48.0 / $1.10/M
  21. 21
    GPT-5.5
    OpenAI
    40.00
    100.0 / $2.50/M
  22. 22
    Qwen3 235B (Thinking)
    Alibaba (Qwen)
    36.44
    16.4 / $0.45/M
  23. 23
    Gemini 2.0 Flash
    Google
    33.30
    3.3 / $0.10/M
  24. 24
    GLM 5
    Zhipu AI (GLM)
    31.79
    31.8 / $1.00/M
  25. 25
    o3-mini
    OpenAI
    21.83
    24.0 / $1.10/M
Open full leaderboard

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