AMA

Scenario guide

Best AI models for Realtime Chat / Voice

A streaming consumer chat or voice assistant. Speed and time-to-first-token matter as much as raw quality — a slightly less smart model that responds instantly often beats a frontier model that pauses to think.

Rankings use the same scenario weights and cost blending as the interactive leaderboard on AI Model Analyzer. Data is min-max normalised per benchmark; missing scores are skipped without penalty.

  1. 1
    Gemini 2.0 Flash
    Google
    Score 91.3Q 89.9In $0.10/M
  2. 2
    DeepSeek V3
    DeepSeek
    Score 89.9Q 95.8In $0.27/M
  3. 3
    Gemini 1.5 Flash
    Google
    Score 88.9Q 84.1In $0.08/M
  4. 4
    DeepSeek R1
    DeepSeek
    Score 86.4Q 96.3In $0.55/M
  5. 5
    Gemini 3 Flash
    Google
    Score 84.5Q 92.3In $0.30/M
  6. 6
    Gemini 2.5 Flash
    Google
    Score 83.0Q 90.1In $0.30/M
  7. 7
    GLM-4.6
    Zhipu AI (GLM)
    Score 83.0Q 90.1In $0.50/M
  8. 8
    Qwen3 235B (Thinking)
    Alibaba (Qwen)
    Score 82.3Q 81.4In $0.20/M
  9. 9
    DeepSeek V3 (Thinking)
    DeepSeek
    Score 82.2Q 84.8In $0.27/M
  10. 10
    GLM-4.7
    Zhipu AI (GLM)
    Score 81.3Q 87.8In $0.50/M
  11. 11
    GPT-5.4
    OpenAI
    Score 81.2Q 100.0In $1.50/M
  12. 12
    GPT-5.5
    OpenAI
    Score 80.4Q 98.9In $1.50/M
  13. 13
    Kimi K2
    Moonshot (Kimi)
    Score 77.1Q 84.0In $0.60/M
  14. 14
    Gemini 3 Pro
    Google
    Score 76.5Q 91.9In $1.25/M
  15. 15
    GPT-5.1
    OpenAI
    Score 75.4Q 90.4In $1.25/M
Open interactive leaderboard Build custom weightsHome