Value ranking

Best value on Output Speed

Median sustained output speed in tokens per second on the model's first-party API for medium-length prompts. Higher is faster.

“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
Gemini 1.5 Flash
Google
1333.33
100.0 / $0.08/M
2
Gemini 2.0 Flash
Google
1000.00
100.0 / $0.10/M
3
DeepSeek V3
DeepSeek
370.37
100.0 / $0.27/M
4
Gemini 2.5 Flash
Google
289.47
86.8 / $0.30/M
5
Llama 4 Scout
Meta
248.56
44.7 / $0.18/M
6
DeepSeek R1
DeepSeek
181.82
100.0 / $0.55/M
7
Llama 4 Maverick
Meta
175.44
47.4 / $0.27/M
8
Claude 3.5 Haiku
Anthropic
125.00
100.0 / $0.80/M
9
GPT-4o mini
OpenAI
122.80
18.4 / $0.15/M
10
Qwen3 235B
Alibaba (Qwen)
92.10
18.4 / $0.20/M
11
Gemini 1.5 Pro
Google
80.00
100.0 / $1.25/M
12
o4-mini
OpenAI
52.63
57.9 / $1.10/M
13
o3-mini
OpenAI
52.63
57.9 / $1.10/M
14
Grok 2
xAI
50.00
100.0 / $2.00/M
15
Llama 3.3 70B Instruct
Meta
35.89
31.6 / $0.88/M
16
Gemini 2.5 Pro
Google
35.79
44.7 / $1.25/M
17
o1-mini
OpenAI
33.33
100.0 / $3.00/M
18
Claude 3.5 Sonnet
Anthropic
33.33
100.0 / $3.00/M
19
Claude 3.7 Sonnet
Anthropic
33.33
100.0 / $3.00/M
20
GPT-5
OpenAI
25.26
31.6 / $1.25/M
21
GPT-4o
OpenAI
22.10
55.3 / $2.50/M
22
Qwen2.5 72B Instruct
Alibaba (Qwen)
14.62
13.2 / $0.90/M
23
Claude 3 Opus
Anthropic
6.67
100.0 / $15.00/M
24
Grok 3
xAI
4.39
13.2 / $3.00/M
25
Claude Sonnet 4 (Thinking)
Anthropic
3.51
10.5 / $3.00/M

Open full leaderboard

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