sourc.dev
Home LLMs Tools SaaS APIs
Claude 3.5 Sonnet input $3.00/1M ↓ -50%
GPT-4o input $2.50/1M
Gemini 1.5 Pro input $1.25/1M
Mistral Large input $2.00/1M ↓ -33%
DeepSeek V3 input $0.27/1M
synced 2026-04-05
Claude 3.5 Sonnet input $3.00/1M ↓ -50%
GPT-4o input $2.50/1M
Gemini 1.5 Pro input $1.25/1M
Mistral Large input $2.00/1M ↓ -33%
DeepSeek V3 input $0.27/1M
synced 2026-04-05

Best Value

Models ranked by benchmark performance per dollar of input cost. Higher scores mean more capability for less money.

Methodology: Computed as benchmark_mmlu / input_price_per_1m. Only models with both values included. Higher is better.

# Model Metric
1 Gemini 1.5 Flash 1052.0 score/$1
2 Gemini 2.0 Flash 879.0 score/$1
3 Llama 3.3 70B 860.0 score/$1
4 Qwen 2.5 72B 717.5 score/$1
5 GPT-4o mini 546.7 score/$1
6 DeepSeek V3.2 340.4 score/$1
7 DeepSeek V3 327.8 score/$1
8 Claude 3 Haiku 300.8 score/$1
9 Mistral 7B 250.0 score/$1
10 Kimi K2.5 212.7 score/$1
11 Llama 3 70B 160.8 score/$1
12 Gemini 1.0 Pro 158.2 score/$1
13 Mixtral 8x7B 130.7 score/$1
14 DeepSeek R1 129.7 score/$1
15 ERNIE 4.0 97.0 score/$1
16 Claude 3.5 Haiku 94.0 score/$1
17 Llama 2 70B 76.6 score/$1
18 Gemini 1.5 Pro 68.7 score/$1
19 GPT-3.5 Turbo 46.7 score/$1
20 Grok 2 43.8 score/$1
21 Mistral Large 2 42.0 score/$1
22 GPT-4o 35.5 score/$1
23 Command R+ 30.3 score/$1
24 Claude 3.5 Sonnet 29.6 score/$1
25 Claude Sonnet 4.6 29.4 score/$1
26 Claude 3 Sonnet 26.3 score/$1
27 Llama 3.1 405B 17.7 score/$1
28 GPT-4 Turbo 8.6 score/$1
29 o1 6.2 score/$1
30 Claude 3 Opus 5.8 score/$1
31 GPT-4 2.9 score/$1
32 GPT-3 (davinci-002) 0.7 score/$1
← All leaderboards