benchlm.ai

AI Models Directory

Browse 88 AI language models with benchmark scores across knowledge, coding, math, and reasoning.

GPT-5.4

88
OpenAI|Proprietary|1M

Gemini 3.1 Pro

87
Google|Proprietary|1M

Claude Opus 4.6

86
Anthropic|Proprietary|1M

GPT-5.3 Codex

85
OpenAI|Proprietary|400K

Grok 4.1

84
xAI|Proprietary|128K

GPT-5.2

83
OpenAI|Proprietary|400K

GPT-5.2-Codex

82
OpenAI|Proprietary|400K

Gemini 3 Pro Deep Think

81
Google|Proprietary|2M

Claude Sonnet 4.6

80
Anthropic|Proprietary|1M

Claude Opus 4.5

79
Anthropic|Proprietary|200K

Gemini 3 Pro

78
Google|Proprietary|2M

GPT-5.1-Codex-Max

77
OpenAI|Proprietary|400K

GPT-5.1

76
OpenAI|Proprietary|400K

GLM-5 (Reasoning)

75
Zhipu AI|Open Weight|200K

Claude Sonnet 4.5

74
Anthropic|Proprietary|1M

Grok 4.1 Fast

73
xAI|Proprietary|2M

GPT-5 (high)

72
OpenAI|Proprietary|128K

o1-preview

71
OpenAI|Proprietary|200K

Kimi K2.5 (Reasoning)

71
Moonshot AI|Open Weight|128K

GPT-5 (medium)

70
OpenAI|Proprietary|128K

Qwen3.5 397B (Reasoning)

70
Alibaba|Open Weight|128K

Grok 4

69
xAI|Proprietary|128K

DeepSeek V3.2 (Thinking)

69
DeepSeek|Open Weight|128K

GPT-5 mini

68
OpenAI|Proprietary|128K

o3-pro

68
OpenAI|Proprietary|200K

GLM-5

68
Zhipu AI|Open Weight|200K

o3

67
OpenAI|Proprietary|200K

GLM-4.7

67
Zhipu AI|Open Weight|200K

Qwen2.5-1M

66
Alibaba|Open Weight|1M

DeepSeek V3.2

66
DeepSeek|Open Weight|128K

Qwen2.5-72B

65
Alibaba|Open Weight|128K

o4-mini (high)

65
OpenAI|Proprietary|200K

Gemini 2.5 Pro

65
Google|Proprietary|2M

Qwen3.5 397B

65
Alibaba|Open Weight|128K

DeepSeek Coder 2.0

64
DeepSeek|Open Weight|128K

DeepSeekMath V2

64
DeepSeek|Open Weight|128K

DeepSeek LLM 2.0

63
DeepSeek|Open Weight|128K

MiMo-V2-Flash

63
Xiaomi|Open Weight|128K

Kimi K2.5

62
Moonshot AI|Open Weight|128K

Claude 4.1 Opus

61
Anthropic|Proprietary|200K

Mistral Large 3

61
Mistral|Open Weight|128K

Nemotron 3 Ultra 500B

60
NVIDIA|Open Weight|32K

Claude 4 Sonnet

59
Anthropic|Proprietary|200K

MiniMax M2.5

59
MiniMax|Proprietary|128K

Llama 3.1 405B

58
Meta|Open Weight|128K

Gemini 3 Flash

58
Google|Proprietary|1M

Mistral Large 2

57
Mistral|Proprietary|128K

Claude Haiku 4.5

57
Anthropic|Proprietary|200K

GPT-4o

56
OpenAI|Proprietary|128K

GLM-4.7-Flash

56
Zhipu AI|Open Weight|200K

Claude 3.5 Sonnet

55
Anthropic|Proprietary|200K

Nemotron 3 Super 100B

55
NVIDIA|Open Weight|32K

Gemini 1.5 Pro

54
Google|Proprietary|2M

Grok Code Fast 1

54
xAI|Proprietary|256K

Gemini 3.1 Flash-Lite

53
Google|Proprietary|1M

Mistral 8x7B

52
Mistral|Open Weight|32K

Gemini 1.0 Pro

52
Google|Proprietary|32K

Claude 3 Opus

51
Anthropic|Proprietary|200K

GPT-4 Turbo

50
OpenAI|Proprietary|128K

Llama 3 70B

48
Meta|Open Weight|128K

Nemotron 3 Nano 30B

47
NVIDIA|Open Weight|32K

Claude 3 Haiku

46
Anthropic|Proprietary|200K

Nemotron-4 15B

45
NVIDIA|Open Weight|32K

Moonshot v1

44
Moonshot AI|Proprietary|128K

Z-1

43
Z|Proprietary|128K

GPT-OSS 120B

42
OpenAI|Open Weight|128K

Gemini 2.5 Flash

41
Google|Proprietary|1M

Nemotron Ultra 253B

40
NVIDIA|Open Weight|32K

Llama 4 Behemoth

39
Meta|Open Weight|32K

Llama 4 Scout

38
Meta|Open Weight|32K

Llama 4 Maverick

37
Meta|Open Weight|32K

Gemma 3 27B

36
Google|Open Weight|32K

DeepSeek-R1

35
DeepSeek|Open Weight|128K

Qwen2.5-VL-32B

34
Alibaba|Open Weight|32K

Grok 3 [Beta]

33
xAI|Proprietary|128K

Nova Pro

32
Nova AI|Proprietary|128K

Qwen3 235B 2507 (Reasoning)

31
Alibaba|Open Weight|128K

Qwen3 235B 2507

30
Alibaba|Open Weight|128K

Claude 4.1 Opus Thinking

29
Anthropic|Proprietary|200K

GLM-4.5

28
Tsinghua|Proprietary|128K

MiniMax M1 80k

27
MiniMax|Proprietary|80K

GLM-4.5-Air

26
Tsinghua|Proprietary|128K

DeepSeek V3.1 (Reasoning)

25
DeepSeek|Open Weight|128K

DeepSeek V3.1

24
DeepSeek|Open Weight|128K

Kimi K2

23
Moonshot AI|Proprietary|128K

GPT-OSS 20B

22
OpenAI|Open Weight|128K

Mistral 7B v0.3

21
Mistral|Open Weight|32K

Mistral 8x7B v0.2

20
Mistral|Open Weight|32K