Skip to content

Scenario guide

Best AI models for Math / Reasoning Tutor

As of October 25, 2026, the highest-ranked model for Math / Reasoning Tutor is DeepSeek V4.1 Flash 1017, with a scenario score of 97.0 out of 100. The score blends this scenario's benchmark weights with its cost weight.

Tutors students through hard math. Reasoning-heavy; cost matters less because depth-of-thought is the value. Weighted toward contamination-resistant problem sets (FrontierMath, OTIS Mock AIME) since AIME 2024 and MATH-500 are now in most training corpora.

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 1017
    DeepSeek
    Score 97.0Q 99.4In $0.15/M
  2. 2
    GPT-6.1 Sol
    OpenAI
    Score 95.0Q 99.7In $1.00/M
  3. 3
    Gemini 4 Argon
    Google
    Score 93.9Q 98.5In $1.00/M
  4. 4
    Claude Opus 5.5
    Anthropic
    Score 93.7Q 100.0In $4.00/M
  5. 5
    GPT-6 Astra
    OpenAI
    Score 93.5Q 100.0In $5.00/M
  6. 6
    Claude Sonnet 5.5
    Anthropic
    Score 93.0Q 98.3In $2.00/M
  7. 7
    GPT-6 Sol
    OpenAI
    Score 92.4Q 96.8In $1.00/M
  8. 8
    Claude Haiku 5.5
    Anthropic
    Score 91.7Q 93.2In $0.10/M
  9. 9
    GPT-5.5
    OpenAI
    Score 91.5Q 97.1In $2.50/M
  10. 10
    Claude Fable 5.1
    Anthropic
    Score 91.4Q 98.5In $10.00/M
  11. 11
    GPT-5.6 Sol
    OpenAI
    Score 91.1Q 96.2In $2.00/M
  12. 12
    GPT-6 Luna
    OpenAI
    Score 91.0Q 91.6In $0.05/M
  13. 13
    Claude Opus 5
    Anthropic
    Score 90.0Q 96.2In $5.00/M
  14. 14
    GPT-5.6 Terra
    OpenAI
    Score 89.9Q 94.3In $1.00/M
  15. 15
    Claude Fable 5
    Anthropic
    Score 89.7Q 96.6In $10.00/M
Open interactive leaderboard Build custom weightsHome