Skip to content

Value ranking

Best value on MMLU Pro

As of October 25, 2026, the best value on MMLU Pro is Llama 3.3 70B Instruct, at 710.00 normalized points per dollar of input price ($0.10 per million tokens, score 71.0).

Harder version of MMLU testing knowledge across 57 academic subjects; reduces guessing-friendly answers.

“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
    Llama 3.3 70B Instruct
    Meta
    710.00
    71.0 / $0.10/M
  2. 2
    Qwen2.5 72B Instruct
    Alibaba (Qwen)
    265.61
    95.6 / $0.36/M
  3. 3
    Llama 3.1 70B Instruct
    Meta
    172.80
    69.1 / $0.40/M
  4. 4
    Mistral Large 2
    Mistral
    45.13
    90.3 / $2.00/M
  5. 5
    Mixtral 8x22B
    Mistral
    0.00
    0.0 / $2.00/M
Open full leaderboard

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