Skip to content

Value ranking

Best value on IFEval

As of October 25, 2026, the best value on IFEval is Llama 3.3 70B Instruct, at 1000.00 normalized points per dollar of input price ($0.10 per million tokens, score 100.0).

Verifiable instruction-following benchmark; 25 categories of strict formatting / structural directives.

“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
    1000.00
    100.0 / $0.10/M
  2. 2
    Qwen2.5 72B Instruct
    Alibaba (Qwen)
    257.67
    92.8 / $0.36/M
  3. 3
    Llama 3.1 70B Instruct
    Meta
    233.45
    93.4 / $0.40/M
  4. 4
    Mistral Large 2
    Mistral
    43.98
    88.0 / $2.00/M
  5. 5
    Mixtral 8x22B
    Mistral
    31.72
    63.4 / $2.00/M
Open full leaderboard

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