The best LLMs for your use case:

1DeepSeek-R1-0528DeepSeek

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

LiveBench

General Knowledge

70.1
#1

MMLU-Pro

General Knowledge

85
#1

GPQA-Diamond

General Knowledge

81
#1

LMArena

Chat

1411
#1

WebDevArena

Code

1409
#1

Aider Polyglot

Code

71.4
#1

LongBenchv2

Summarization

59.3
#2

LiveCodeBench

Code

73.3
#3

MGSM

Multilingual

92.4
#2

LiveBench

General Knowledge

70.1
#1

MMLU-Pro

General Knowledge

85
#1

GPQA-Diamond

General Knowledge

81
#1

LMArena

Chat

1411
#1

WebDevArena

Code

1409
#1

Aider Polyglot

Code

71.4
#1

LongBenchv2

Summarization

59.3
#2

LiveCodeBench

Code

73.3
#3

MGSM

Multilingual

92.4
Try it out
2Qwen3 235B A22BQwen

Hybrid instruct + reasoning model (232Bx22B MoE) optimized for high-throughput, cost-efficient inference and distillation.

Speed:

Intelligence:

Price: (1M Tokens)

$0.20

Inputs:

ImageText

JSON Mode:

Function Calling:

Benchmarks:

#2

MMLU-Pro

General Knowledge

83.66
#2

GPQA-Diamond

General Knowledge

70
#1

LiveBench

General Knowledge

73.23
#1

EQBench

Creative Writing

1271.6
#1

LiveCodeBench

Code

80.4
#1

MGSM

Multilingual

92.7
#1

BFCL

Agents and Function Calling

70.8
#2

Aider Polyglot

Code

59.6
#2

LongBenchv2

Summarization

50.1
#2

Multilingual MMLU

Multilingual

82.8
#3

WebDevArena

Code

1186
#11

LMArena

Chat

45.92
#2

MMLU-Pro

General Knowledge

83.66
#2

GPQA-Diamond

General Knowledge

70
#1

LiveBench

General Knowledge

73.23
#1

EQBench

Creative Writing

1271.6
#1

LiveCodeBench

Code

80.4
#1

MGSM

Multilingual

92.7
#1

BFCL

Agents and Function Calling

70.8
#2

Aider Polyglot

Code

59.6
#2

LongBenchv2

Summarization

50.1
#2

Multilingual MMLU

Multilingual

82.8
#3

WebDevArena

Code

1186
#11

LMArena

Chat

45.92
Try it out

Use case:

General Knowledge