Skip to content

Value ranking

Best value on Time to First Token

As of October 25, 2026, the best value on Time to First Token is gpt-oss-20b, at 5435.00 normalized points per dollar of input price ($0.02 per million tokens, score 97.8).

Median time from request to first streamed token in milliseconds over the last 14 days on the model maker's own API, using the same nightly probe prompt. Lower is snappier; reasoning models are penalised here because they think before talking.

“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-oss-20b
    OpenAI
    5435.00
    97.8 / $0.02/M
  2. 2
    DeepSeek V4.1 Flash
    DeepSeek
    4955.00
    99.1 / $0.02/M
  3. 3
    GPT-5 nano
    OpenAI
    3879.20
    97.0 / $0.03/M
  4. 4
    Qwen3.7 Flash
    Alibaba (Qwen)
    3308.33
    99.3 / $0.03/M
  5. 5
    Gemma 3 4B
    Google
    2496.75
    99.9 / $0.04/M
  6. 6
    DeepSeek V4 Flash 0731
    DeepSeek
    2361.37
    99.7 / $0.04/M
  7. 7
    Mistral Small 3
    Mistral
    2000.00
    100.0 / $0.05/M
  8. 8
    Gemma 3 12B
    Google
    1999.00
    100.0 / $0.05/M
  9. 9
    Gemini 2.5 Flash Lite
    Google
    1978.20
    98.9 / $0.05/M
  10. 10
    GPT-6 Luna
    OpenAI
    1868.20
    93.4 / $0.05/M
  11. 11
    Nemotron 3 Nano 30B A3B
    NVIDIA
    1661.50
    99.7 / $0.06/M
  12. 12
    GLM 4.7 Flash
    Zhipu AI (GLM)
    1647.44
    99.7 / $0.06/M
  13. 13
    GPT-6 Luna Pro
    OpenAI
    1540.20
    77.0 / $0.05/M
  14. 14
    Qwen3.5-Flash
    Alibaba (Qwen)
    1533.54
    99.7 / $0.07/M
  15. 15
    Nemotron 3.5 Lightning
    NVIDIA
    1425.43
    99.8 / $0.07/M
  16. 16
    Qwen3 Coder 30B A3B Instruct
    Alibaba (Qwen)
    1415.00
    99.0 / $0.07/M
  17. 17
    Gemini 1.5 Flash
    Google
    1329.60
    99.7 / $0.08/M
  18. 18
    Seed 1.6 Flash
    ByteDance Seed
    1328.53
    99.6 / $0.08/M
  19. 19
    Qwen3 32B
    Alibaba (Qwen)
    1243.50
    99.5 / $0.08/M
  20. 20
    Gemma 3 27B
    Google
    1242.63
    99.4 / $0.08/M
  21. 21
    Qwen3 Next 80B A3B Instruct
    Alibaba (Qwen)
    1108.22
    99.7 / $0.09/M
  22. 22
    Qwen3 235B
    Alibaba (Qwen)
    1097.56
    98.8 / $0.09/M
  23. 23
    Qwen3 30B A3B Instruct 2507
    Alibaba (Qwen)
    1097.11
    98.7 / $0.09/M
  24. 24
    DeepSeek V4 Flash 0423
    DeepSeek
    1086.59
    98.9 / $0.09/M
  25. 25
    Ministral 3 3B 2512
    Mistral
    997.90
    99.8 / $0.10/M
Open full leaderboard

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