The best LLMs for your use case:

1DeepSeek-V3-0324DeepSeek

Mixture-of-Experts 671B parameter model challenging top AI models at much lower cost.

Speed:

Intelligence:

Price: (1M Tokens)

$1.25

Inputs:

ImageText

JSON Mode:

Function Calling:

Benchmarks:

#1

LMArena

Chat

1372
#1

WebDevArena

Code

1207
#3

MMLU-Pro

General Knowledge

81.2
#3

EQBench

Creative Writing

1164.3
#3

Aider Polyglot

Code

55.1
#3

Multilingual MMLU

Multilingual

79.4
#4

GPQA-Diamond

General Knowledge

68.4
#4

LiveBench

General Knowledge

66.86
#4

MGSM

Multilingual

92
#4

BFCL

Agents and Function Calling

57.61
#5

LiveCodeBench

Code

49.6
#1

LMArena

Chat

1372
#1

WebDevArena

Code

1207
#3

MMLU-Pro

General Knowledge

81.2
#3

EQBench

Creative Writing

1164.3
#3

Aider Polyglot

Code

55.1
#3

Multilingual MMLU

Multilingual

79.4
#4

GPQA-Diamond

General Knowledge

68.4
#4

LiveBench

General Knowledge

66.86
#4

MGSM

Multilingual

92
#4

BFCL

Agents and Function Calling

57.61
#5

LiveCodeBench

Code

49.6
Try it out
2DeepSeek-R1DeepSeek

SOTA reasoning model trained with reinforcement learning, delivering strong performance on math, code, and logic tasks.

Speed:

Intelligence:

Price: (1M Tokens)

$3.00

Inputs:

ImageText

JSON Mode:

Function Calling:

Benchmarks:

#2

LMArena

Chat

1359
#1

GPQA-Diamond

General Knowledge

71.5
#1

MMLU-Pro

General Knowledge

84
#1

LongBenchv2

Summarization

59.3
#2

LiveBench

General Knowledge

72.49
#2

LiveCodeBench

Code

65.9
#2

WebDevArena

Code

1199
#2

Aider Polyglot

Code

56.9
#3

MGSM

Multilingual

92.4
#2

LMArena

Chat

1359
#1

GPQA-Diamond

General Knowledge

71.5
#1

MMLU-Pro

General Knowledge

84
#1

LongBenchv2

Summarization

59.3
#2

LiveBench

General Knowledge

72.49
#2

LiveCodeBench

Code

65.9
#2

WebDevArena

Code

1199
#2

Aider Polyglot

Code

56.9
#3

MGSM

Multilingual

92.4
Try it out

Use case:

Chat