Skip to content

Value ranking

Best value on Terminal-Bench 2

As of October 25, 2026, the best value on Terminal-Bench 2 is GPT-5 nano, at 904.80 normalized points per dollar of input price ($0.03 per million tokens, score 22.6).

Long-horizon shell-and-filesystem tasks executed in a sandboxed terminal, scored by whether the agent's final state matches a target state. Tests practical tool-using ability for everyday devops and data-wrangling work; one of the hardest agentic benchmarks today.

“Value” is normalized benchmark score (0–100 for this leaderboard cohort) divided by input price per million tokens. Higher means more capability per dollar on this axis only — always sanity-check latency, context length, and your real workload.

  1. 1
    GPT-5 nano
    OpenAI
    904.80
    22.6 / $0.03/M
  2. 2
    GPT-5 mini
    OpenAI
    309.20
    38.6 / $0.13/M
  3. 3
    Gemini 3 Flash
    Google
    299.40
    74.8 / $0.25/M
  4. 4
    GPT-5.1-Codex-Mini
    OpenAI
    286.16
    71.5 / $0.25/M
  5. 5
    Qwen3.6 35B A3B
    Alibaba (Qwen)
    261.00
    26.1 / $0.10/M
  6. 6
    MiniMax M2.7
    MiniMax
    170.77
    51.2 / $0.30/M
  7. 7
    MiniMax M2.5
    MiniMax
    161.07
    48.3 / $0.30/M
  8. 8
    DeepSeek V3
    DeepSeek
    153.31
    44.5 / $0.29/M
  9. 9
    Grok Code Fast 1
    xAI
    138.00
    27.6 / $0.20/M
  10. 10
    MiniMax M2.1
    MiniMax
    136.20
    40.9 / $0.30/M
  11. 11
    MiniMax M2
    MiniMax
    128.47
    32.8 / $0.26/M
  12. 12
    gpt-oss-120b
    OpenAI
    125.40
    18.8 / $0.15/M
  13. 13
    Gemini 2.5 Flash
    Google
    112.33
    16.9 / $0.15/M
  14. 14
    Qwen3 Coder 480B A35B
    Alibaba (Qwen)
    97.53
    29.3 / $0.30/M
  15. 15
    Gemini 3.1 Pro
    Google
    94.47
    94.5 / $1.00/M
  16. 16
    GPT-5.1
    OpenAI
    86.96
    54.4 / $0.63/M
  17. 17
    GPT-5.2
    OpenAI
    86.49
    75.7 / $0.88/M
  18. 18
    Kimi K2
    Moonshot (Kimi)
    85.88
    49.0 / $0.57/M
  19. 19
    GPT-5.4
    OpenAI
    77.13
    96.4 / $1.25/M
  20. 20
    GLM-4.7
    Zhipu AI (GLM)
    61.47
    36.9 / $0.60/M
  21. 21
    GLM 5
    Zhipu AI (GLM)
    60.28
    60.3 / $1.00/M
  22. 22
    Gemini 2.5 Pro
    Google
    57.54
    36.0 / $0.63/M
  23. 23
    GPT-5.1-Codex-Max
    OpenAI
    56.13
    70.2 / $1.25/M
  24. 24
    GPT-5.1-Codex
    OpenAI
    53.52
    66.9 / $1.25/M
  25. 25
    Grok 4.20
    xAI
    53.03
    66.3 / $1.25/M
Open full leaderboard

AI Model Analyzer does not recommend specific vendors; rankings are derived from public data only.