Skip to content

Scenario guide

Best AI models for Bulk Classification

As of October 25, 2026, the highest-ranked model for Bulk Classification is DeepSeek V4.1 Flash, with a scenario score of 83.3 out of 100. The score blends this scenario's benchmark weights with its cost weight.

Classifying / extracting fields from millions of documents. Quality barely matters past a threshold; cost dominates.

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
    DeepSeek V4.1 Flash
    DeepSeek
    Score 83.3Q 83.1In $0.02/M
  2. 2
    DeepSeek V4 Flash 0423
    DeepSeek
    Score 80.8Q 74.2In $0.09/M
  3. 3
    GLM 5.3 Flash
    Zhipu AI (GLM)
    Score 80.3Q 85.3In $0.15/M
  4. 4
    Llama 3.3 70B Instruct
    Meta
    Score 80.1Q 76.0In $0.10/M
  5. 5
    MiMo-V2.6-Flash
    Xiaomi (MiMo)
    Score 79.6Q 79.7In $0.14/M
  6. 6
    GPT-6 Luna
    OpenAI
    Score 79.6Q 62.8In $0.05/M
  7. 7
    Qwen3.5-Flash
    Alibaba (Qwen)
    Score 78.8Q 64.6In $0.07/M
  8. 8
    MiMo-V2.5
    Xiaomi (MiMo)
    Score 78.5Q 73.1In $0.12/M
  9. 9
    Gemini 2.5 Flash Lite
    Google
    Score 78.1Q 57.0In $0.05/M
  10. 10
    GPT-5.6 Luna
    OpenAI
    Score 78.0Q 74.0In $0.10/M
  11. 11
    Hy3
    Tencent (Hunyuan)
    Score 77.6Q 76.0In $0.13/M
  12. 12
    Qwen3 235B
    Alibaba (Qwen)
    Score 77.5Q 70.7In $0.09/M
  13. 13
    gpt-oss-20b
    OpenAI
    Score 77.1Q 34.5In $0.02/M
  14. 14
    Step 3.5 Flash
    StepFun
    Score 76.8Q 66.2In $0.10/M
  15. 15
    DeepSeek V4 Pro 0423
    DeepSeek
    Score 76.7Q 79.5In $0.21/M
Open interactive leaderboard Build custom weightsHome