Skip to content

Scenario guide

Best AI models for Autonomous Agent / Tool Use

As of November 16, 2026, the highest-ranked model for Autonomous Agent / Tool Use is Gemini 4 Carbon, with a scenario score of 86.3 out of 100. The score blends this scenario's benchmark weights with its cost weight.

An agent that runs multi-step jobs on its own: shell commands, code changes, tool calls. Weighted toward agentic benchmarks that grade finished tasks (Terminal-Bench, SWE-bench) plus novel-problem reasoning, with a slice for self-correction because a long run fails if the model cannot recover from its own mistakes. Cost matters because agent loops resend large contexts on every step.

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 4 Carbon
    Google
    Score 86.3Q 95.2In $1.00/M
  2. 2
    GPT-6.1 Terra
    OpenAI
    Score 84.1Q 90.0In $0.50/M
  3. 3
    GPT-6.1 Sol
    OpenAI
    Score 83.0Q 91.1In $1.00/M
  4. 4
    GPT-5.3-Codex
    OpenAI
    Score 81.5Q 92.3In $1.75/M
  5. 5
    Gemini 3.1 Pro
    Google
    Score 80.4Q 88.2In $1.00/M
  6. 6
    GPT-6 Astra
    OpenAI
    Score 79.9Q 93.1In $5.00/M
  7. 7
    GPT-5.5
    OpenAI
    Score 79.1Q 89.9In $2.50/M
  8. 8
    GPT-6 Sol
    OpenAI
    Score 78.2Q 85.1In $1.00/M
  9. 9
    Claude Opus 5.5
    Anthropic
    Score 78.0Q 89.8In $4.00/M
  10. 10
    Gemini 4 Argon
    Google
    Score 77.6Q 84.3In $1.00/M
  11. 11
    DeepSeek V4.1 Flash 1017
    DeepSeek
    Score 77.5Q 77.0In $0.15/M
  12. 12
    GPT-5.4
    OpenAI
    Score 77.2Q 85.0In $1.25/M
  13. 13
    Claude Sonnet 5.5
    Anthropic
    Score 77.2Q 86.3In $2.00/M
  14. 14
    Gemini 3.8 Flash
    Google
    Score 76.7Q 79.7In $0.38/M
  15. 15
    GPT-5.6 Terra
    OpenAI
    Score 76.7Q 83.6In $1.00/M