Skip to content

Scenario guide

Best AI models for Research / Analyst

As of October 25, 2026, the highest-ranked model for Research / Analyst is GPT-6.1 Sol, with a scenario score of 94.1 out of 100. The score blends this scenario's benchmark weights with its cost weight.

A research assistant that reads long PDFs and answers nuanced questions. Weighted toward reasoning, knowledge, long-context, and a saturation-resistant frontier capability score so the ranking stays meaningful as MMLU-style evals saturate.

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-6.1 Sol
    OpenAI
    Score 94.1Q 98.4In $1.00/M
  2. 2
    GPT-6 Astra
    OpenAI
    Score 93.6Q 99.9In $5.00/M
  3. 3
    Gemini 4 Argon
    Google
    Score 92.8Q 97.0In $1.00/M
  4. 4
    Claude Opus 5.5
    Anthropic
    Score 92.4Q 98.2In $4.00/M
  5. 5
    GPT-5.6 Sol
    OpenAI
    Score 85.2Q 89.4In $2.00/M
  6. 6
    Claude Fable 5.1
    Anthropic
    Score 84.9Q 91.1In $10.00/M
  7. 7
    Claude Fable 5
    Anthropic
    Score 84.6Q 90.7In $10.00/M
  8. 8
    GPT-6 Sol
    OpenAI
    Score 83.2Q 86.3In $1.00/M
  9. 9
    GPT-5.5 Pro
    OpenAI
    Score 82.4Q 88.8In $15.00/M
  10. 10
    Muse Wonder
    Meta
    Score 82.1Q 86.8In $4.00/M
  11. 11
    Gemini 3.7 Flash
    Google
    Score 81.4Q 83.1In $0.38/M
  12. 12
    Claude Opus 5
    Anthropic
    Score 81.3Q 86.2In $5.00/M
  13. 13
    Gemini 3.8 Flash
    Google
    Score 80.3Q 81.9In $0.38/M
  14. 14
    Gemini 3.1 Pro
    Google
    Score 79.8Q 82.5In $1.00/M
  15. 15
    Claude Sonnet 5.5
    Anthropic
    Score 79.3Q 82.9In $2.00/M
Open interactive leaderboard Build custom weightsHome