Best value on HumanEval

“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

   Gemini 2.0 Flash

   Google
   680.20

   68.0 / $0.10/M
2. 2

   Qwen3 235B

   Alibaba (Qwen)
   414.40

   82.9 / $0.20/M
3. 3

   GPT-4o mini

   OpenAI
   387.40

   58.1 / $0.15/M
4. 4

   Llama 4 Scout

   Meta
   292.78

   52.7 / $0.18/M
5. 5

   Llama 4 Maverick

   Meta
   271.93

   73.4 / $0.27/M
6. 6

   DeepSeek V3

   DeepSeek
   230.22

   62.2 / $0.27/M
7. 7

   DeepSeek R1

   DeepSeek
   180.18

   99.1 / $0.55/M
8. 8

   o3-mini

   OpenAI
   78.63

   86.5 / $1.10/M
9. 9

   Claude 3.5 Haiku

   Anthropic
   77.70

   62.2 / $0.80/M
10. 10

    Gemini 2.5 Pro

    Google
    76.40

    95.5 / $1.25/M
11. 11

    Llama 3.3 70B Instruct

    Meta
    72.17

    63.5 / $0.88/M
12. 12

    Qwen2.5 72B Instruct

    Alibaba (Qwen)
    61.57

    55.4 / $0.90/M
13. 13

    Gemini 1.5 Pro

    Google
    35.31

    44.1 / $1.25/M
14. 14

    Grok 2

    xAI
    31.75

    63.5 / $2.00/M
15. 15

    Llama 3.1 70B Instruct

    Meta
    31.74

    27.9 / $0.88/M
16. 16

    Claude Sonnet 4

    Anthropic
    31.08

    93.2 / $3.00/M
17. 17

    Claude 3.5 Sonnet

    Anthropic
    29.13

    87.4 / $3.00/M
18. 18

    Mistral Large 2

    Mistral
    29.05

    58.1 / $2.00/M
19. 19

    GPT-4o

    OpenAI
    28.65

    71.6 / $2.50/M
20. 20

    o1-mini

    OpenAI
    27.18

    81.5 / $3.00/M
21. 21

    Grok 3

    xAI
    25.83

    77.5 / $3.00/M
22. 22

    Llama 3.1 405B Instruct

    Meta
    18.92

    66.2 / $3.50/M
23. 23

    o3

    OpenAI
    9.37

    93.7 / $10.00/M
24. 24

    Claude Opus 4

    Anthropic
    6.67

    100.0 / $15.00/M
25. 25

    o1

    OpenAI
    5.44

    81.5 / $15.00/M

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