Skip to content

Value ranking

Best value on Humanity's Last Exam

As of October 25, 2026, the best value on Humanity's Last Exam is Claude Haiku 5.5, at 526.10 normalized points per dollar of input price ($0.10 per million tokens, score 52.6).

A challenging multi-disciplinary exam aggregating expert-written questions from across academic fields. Designed to discriminate at the very top of the capability range when MMLU-style tests saturate.

“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
    Claude Haiku 5.5
    Anthropic
    526.10
    52.6 / $0.10/M
  2. 2
    GPT-5 mini
    OpenAI
    256.80
    32.1 / $0.13/M
  3. 3
    Gemini 3.8 Flash
    Google
    214.03
    80.3 / $0.38/M
  4. 4
    Gemini 2.5 Flash
    Google
    119.80
    18.0 / $0.15/M
  5. 5
    Gemini 3.1 Flash Lite
    Google
    90.96
    11.4 / $0.13/M
  6. 6
    Gemini 3.1 Pro
    Google
    83.95
    84.0 / $1.00/M
  7. 7
    Gemini 2.0 Flash
    Google
    73.70
    7.4 / $0.10/M
  8. 8
    Kimi K2
    Moonshot (Kimi)
    72.93
    41.6 / $0.57/M
  9. 9
    GPT-5.1
    OpenAI
    64.40
    40.3 / $0.63/M
  10. 10
    Gemini 2.5 Pro
    Google
    58.13
    36.3 / $0.63/M
  11. 11
    GPT-5.2
    OpenAI
    55.04
    48.2 / $0.88/M
  12. 12
    GLM 4.5 Air
    Zhipu AI (GLM)
    51.85
    10.4 / $0.20/M
  13. 13
    GPT-5.4
    OpenAI
    51.49
    64.4 / $1.25/M
  14. 14
    Claude Sonnet 5.5
    Anthropic
    41.66
    83.3 / $2.00/M
  15. 15
    GPT-5
    OpenAI
    34.71
    43.4 / $1.25/M
  16. 16
    Llama 4 Maverick
    Meta
    30.29
    5.7 / $0.19/M
  17. 17
    o4-mini
    OpenAI
    26.81
    29.5 / $1.10/M
  18. 18
    GPT-6 Astra
    OpenAI
    20.00
    100.0 / $5.00/M
  19. 19
    GLM 4.5
    Zhipu AI (GLM)
    17.92
    10.8 / $0.60/M
  20. 20
    o3
    OpenAI
    16.89
    33.8 / $2.00/M
  21. 21
    Claude Opus 4.7
    Anthropic
    12.86
    64.3 / $5.00/M
  22. 22
    Claude Opus 4.6
    Anthropic
    12.18
    60.9 / $5.00/M
  23. 23
    Mistral Medium 3
    Mistral
    8.65
    3.5 / $0.40/M
  24. 24
    Claude Opus 4.5
    Anthropic
    8.63
    43.2 / $5.00/M
  25. 25
    Claude Fable 5.1
    Anthropic
    8.41
    84.1 / $10.00/M
Open full leaderboard

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