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 90.4Q 88.6In $0.10/M
  2. 2
    DeepSeek V3
    DeepSeek
    Score 88.8Q 94.1In $0.27/M
  3. 3
    Gemini 1.5 Flash
    Google
    Score 88.3Q 83.3In $0.08/M
  4. 4
    DeepSeek R1
    DeepSeek
    Score 85.1Q 94.5In $0.55/M
  5. 5
    Gemini 3 Flash
    Google
    Score 83.7Q 91.1In $0.30/M
  6. 6
    Gemini 2.5 Flash
    Google
    Score 81.8Q 88.4In $0.30/M
  7. 7
    Gemini 3 Pro
    Google
    Score 80.3Q 97.3In $1.25/M
  8. 8
    GLM-4.6
    Zhipu AI (GLM)
    Score 78.1Q 83.2In $0.50/M
  9. 9
    Qwen3 235B (Thinking)
    Alibaba (Qwen)
    Score 78.0Q 75.2In $0.20/M
  10. 10
    DeepSeek V3 (Thinking)
    DeepSeek
    Score 77.6Q 78.2In $0.27/M
  11. 11
    GLM-4.7
    Zhipu AI (GLM)
    Score 77.2Q 81.9In $0.50/M
  12. 12
    GPT-5.5
    OpenAI
    Score 76.2Q 92.9In $1.50/M
  13. 13
    GPT-5.4
    OpenAI
    Score 75.4Q 91.7In $1.50/M
  14. 14
    Gemini 1.5 Pro
    Google
    Score 74.5Q 85.8In $1.25/M
  15. 15
    Claude 3.5 Haiku
    Anthropic
    Score 72.8Q 80.8In $0.80/M
Open interactive leaderboard Build custom weightsHome