Skip to content

Value ranking

Best value on Frontier Composite

As of October 25, 2026, the best value on Frontier Composite is DeepSeek V4.1 Flash, at 3782.00 normalized points per dollar of input price ($0.02 per million tokens, score 75.6).

Saturation-resistant composite capability score stitched together from ~40 underlying benchmarks using Item Response Theory. Each benchmark is weighted by its fitted difficulty and discriminative slope, so doing well on hard, contamination-resistant evals (FrontierMath, ARC-AGI 2, Humanity's Last Exam) moves the score and saturated benchmarks contribute almost nothing. Imported per-model from Epoch AI's published index; we anchor it to the same min-max scale we use for every other benchmark so it's directly weightable in scenarios.

“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 V4.1 Flash
    DeepSeek
    3782.00
    75.6 / $0.02/M
  2. 2
    gpt-oss-20b
    OpenAI
    2289.44
    41.2 / $0.02/M
  3. 3
    Qwen3.7 Flash
    Alibaba (Qwen)
    1773.33
    53.2 / $0.03/M
  4. 4
    GPT-5 nano
    OpenAI
    1762.40
    44.1 / $0.03/M
  5. 5
    DeepSeek V4 Flash 0731
    DeepSeek
    1740.05
    73.4 / $0.04/M
  6. 6
    GPT-6 Luna
    OpenAI
    1543.80
    77.2 / $0.05/M
  7. 7
    Claude Haiku 5.5
    Anthropic
    820.40
    82.0 / $0.10/M
  8. 8
    GPT-5.6 Luna
    OpenAI
    767.10
    76.7 / $0.10/M
  9. 9
    Gemini 2.5 Flash Lite
    Google
    677.60
    33.9 / $0.05/M
  10. 10
    DeepSeek V4 Flash 0423
    DeepSeek
    627.36
    57.1 / $0.09/M
  11. 11
    GPT-5.4 Nano
    OpenAI
    569.40
    56.9 / $0.10/M
  12. 12
    Qwen3 32B
    Alibaba (Qwen)
    532.13
    42.6 / $0.08/M
  13. 13
    Qwen3 235B
    Alibaba (Qwen)
    488.33
    44.0 / $0.09/M
  14. 14
    GLM 5.3 Flash
    Zhipu AI (GLM)
    468.33
    70.3 / $0.15/M
  15. 15
    GPT-5 mini
    OpenAI
    445.12
    55.6 / $0.13/M
  16. 16
    Gemini 3.1 Flash Lite
    Google
    428.80
    53.6 / $0.13/M
  17. 17
    Qwen3 30B A3B
    Alibaba (Qwen)
    372.50
    44.7 / $0.12/M
  18. 18
    Gemini 2.0 Flash
    Google
    365.60
    36.6 / $0.10/M
  19. 19
    Gemini 3.5 Flash Lite
    Google
    365.53
    54.8 / $0.15/M
  20. 20
    Qwen3 14B
    Alibaba (Qwen)
    350.50
    42.1 / $0.12/M
  21. 21
    Gemini 2.5 Flash
    Google
    340.20
    51.0 / $0.15/M
  22. 22
    Gemini 1.5 Flash
    Google
    338.67
    25.4 / $0.08/M
  23. 23
    Gemma 3 27B
    Google
    332.63
    26.6 / $0.08/M
  24. 24
    Gemma 4 26B A4B
    Google
    327.33
    49.1 / $0.15/M
  25. 25
    Qwen3.5-35B-A3B
    Alibaba (Qwen)
    309.23
    50.3 / $0.16/M

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