Best AI models for Bulk Classification

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

   GPT-5 nano

   OpenAI
   Score 82.9Q 51.2In $0.05/M
2. 2

   Gemini 2.0 Flash

   Google
   Score 81.6Q 62.2In $0.10/M
3. 3

   Qwen3 235B (Thinking)

   Alibaba (Qwen)
   Score 81.0Q 81.4In $0.20/M
4. 4

   DeepSeek V3 (Thinking)

   DeepSeek
   Score 77.7Q 84.8In $0.27/M
5. 5

   DeepSeek V3

   DeepSeek
   Score 77.6Q 84.4In $0.27/M
6. 6

   Gemini 1.5 Flash

   Google
   Score 77.3Q 40.4In $0.08/M
7. 7

   Gemini 3 Flash

   Google
   Score 76.0Q 92.3In $0.30/M
8. 8

   Qwen3 235B

   Alibaba (Qwen)
   Score 75.6Q 65.9In $0.20/M
9. 9

   GLM-4.6

   Zhipu AI (GLM)
   Score 72.8Q 90.1In $0.50/M
10. 10

    Gemini 2.5 Flash

    Google
    Score 72.6Q 82.6In $0.30/M
11. 11

    GLM-4.7

    Zhipu AI (GLM)
    Score 72.0Q 87.8In $0.50/M
12. 12

    GPT-5 mini

    OpenAI
    Score 70.1Q 68.5In $0.25/M
13. 13

    DeepSeek R1

    DeepSeek
    Score 69.8Q 86.1In $0.55/M
14. 14

    GPT-4o mini

    OpenAI
    Score 69.2Q 40.3In $0.15/M
15. 15

    Kimi K2

    Moonshot (Kimi)
    Score 67.9Q 84.0In $0.60/M