Weekly model directory

Popular AI models

Start with the current BenchLM-derived top 100, then search the retained directory for models that have left the weekly list or active revision.

Week of August 24, 2026Snapshot needs refresh
Decision facts

Current weekly leaders

100 models shown · Evidence remains source-linked.

ModelDecision factsStatus
Claude Mythos 5Anthropic · Proprietary
Weekly rank
#1
Overall
83.40
Strongest category
Agentic · 75.79
Direct API
$10.00 in / $50.00 out per 1M
Evidence
Supported
Current
Claude Fable 5Anthropic · Proprietary
Weekly rank
#2
Overall
83.15
Strongest category
Coding · 81.41
Direct API
$10.00 in / $50.00 out per 1M
Evidence
Supported
Current
Claude Opus 5Anthropic · Proprietary
Weekly rank
#3
Overall
83.06
Strongest category
Knowledge · 97.00
Direct API
$5.00 in / $25.00 out per 1M
Evidence
Supported
Current
GPT-5.6 SolOpenAI · Proprietary
Weekly rank
#4
Overall
82.20
Strongest category
Coding · 79.01
Direct API
$5.00 in / $30.00 out per 1M
Evidence
Supported
Current
Kimi K3Moonshot AI · Unknown
Weekly rank
#5
Overall
80.21
Strongest category
Multimodal grounded · 87.90
Direct API
$3.00 in / $15.00 out per 1M
Evidence
Supported
Current
Qwen3.8 MaxAlibaba · Open Weight
Weekly rank
#6
Overall
79.22
Strongest category
Reasoning · 95.50
Direct API
Unavailable
Evidence
Supported
Current
Hy4 previewTencent · Open Weight
Weekly rank
#7
Overall
79.16
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Estimated
Current
Muse Spark 1.1Meta · Proprietary
Weekly rank
#8
Overall
77.14
Strongest category
Knowledge · 92.80
Direct API
Unavailable
Evidence
Supported
Current
Claude Opus 4.8Anthropic · Proprietary
Weekly rank
#9
Overall
76.60
Strongest category
Math · 66.80
Direct API
$5.00 in / $25.00 out per 1M
Evidence
Supported
Current
Gemini 3.6 FlashGoogle · Proprietary
Weekly rank
#10
Overall
75.66
Strongest category
Coding · 65.25
Direct API
$1.50 in / $7.50 out per 1M
Evidence
Supported
Current
Grok 4.5xAI · Proprietary
Weekly rank
#11
Overall
75.65
Strongest category
Agentic · 63.07
Direct API
$2.00 in / $6.00 out per 1M
Evidence
Supported
Current
GPT-5.4OpenAI · Proprietary
Weekly rank
#12
Overall
73.56
Strongest category
Multimodal grounded · 63.50
Direct API
$2.50 in / $15.00 out per 1M
Evidence
Supported
Current
GPT-5.6 TerraOpenAI · Proprietary
Weekly rank
#13
Overall
72.95
Strongest category
Unavailable
Direct API
$2.50 in / $15.00 out per 1M
Evidence
Estimated
Current
GPT-5.5OpenAI · Proprietary
Weekly rank
#14
Overall
72.92
Strongest category
Unavailable
Direct API
$5.00 in / $30.00 out per 1M
Evidence
Estimated
Current
Claude Opus 4.7 (Adaptive)Anthropic · Proprietary
Weekly rank
#15
Overall
72.58
Strongest category
Unavailable
Direct API
$5.00 in / $25.00 out per 1M
Evidence
Estimated
Current
Qwen3.8-27BAlibaba · Open Weight
Weekly rank
#16
Overall
72.51
Strongest category
Agentic · 70.34
Direct API
Unavailable
Evidence
Supported
Current
Claude Opus 4.7Anthropic · Proprietary
Weekly rank
#17
Overall
72.33
Strongest category
Coding · 68.72
Direct API
$5.00 in / $25.00 out per 1M
Evidence
Supported
Current
Qwen3.7 MaxAlibaba · Proprietary
Weekly rank
#18
Overall
71.79
Strongest category
Multilingual · 100.00
Direct API
Unavailable
Evidence
Supported
Current
Muse SparkMeta · Proprietary
Weekly rank
#19
Overall
71.02
Strongest category
Multimodal grounded · 71.40
Direct API
Unavailable
Evidence
Supported
Current
MiMo-V2.5-ProXiaomi · Proprietary
Weekly rank
#20
Overall
69.41
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Supported
Current
MiniMax M3MiniMax · Open Weight
Weekly rank
#21
Overall
68.73
Strongest category
Multimodal grounded · 42.20
Direct API
$0.30 in / $1.20 out per 1M
Evidence
Supported
Current
dots3-note PreviewDots Studio · Open Weight
Weekly rank
#22
Overall
68.66
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Estimated
Current
Ornith-1.5-397BOrnith AI · Open Weight
Weekly rank
#23
Overall
68.60
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Estimated
Current
Claude Opus 4.6Anthropic · Proprietary
Weekly rank
#24
Overall
68.26
Strongest category
Knowledge · 82.40
Direct API
$5.00 in / $25.00 out per 1M
Evidence
Supported
Current
Hy3Tencent · Open Weight
Weekly rank
#25
Overall
68.16
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Supported
Current
Gemini 3 ProGoogle · Proprietary
Weekly rank
#26
Overall
67.64
Strongest category
Multimodal grounded · 67.60
Direct API
$2.00 in / $12.00 out per 1M
Evidence
Supported
Current
GPT-5.6 LunaOpenAI · Proprietary
Weekly rank
#27
Overall
67.35
Strongest category
Unavailable
Direct API
$1.00 in / $6.00 out per 1M
Evidence
Estimated
Current
GPT-5.2 ProOpenAI · Proprietary
Weekly rank
#28
Overall
67.30
Strongest category
Unavailable
Direct API
$21.00 in / $168.00 out per 1M
Evidence
Supported
Current
MiMo-V2-ProXiaomi · Proprietary
Weekly rank
#29
Overall
67.15
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Supported
Current
GLM-5.1Z.AI · Open Weight
Weekly rank
#30
Overall
67.04
Strongest category
Math · 64.50
Direct API
$1.40 in / $4.40 out per 1M
Evidence
Supported
Current
InklingThinking Machines Lab · Open Weight
Weekly rank
#31
Overall
67.02
Strongest category
Instruction Following · 88.60
Direct API
$1.87 in / $4.68 out per 1M
Evidence
Supported
Current
GPT-5.4 nanoOpenAI · Proprietary
Weekly rank
#32
Overall
66.78
Strongest category
Knowledge · 51.70
Direct API
$0.20 in / $1.25 out per 1M
Evidence
Supported
Current
GLM-5-TurboZ.AI · Proprietary
Weekly rank
#33
Overall
66.30
Strongest category
Unavailable
Direct API
$1.20 in / $4.00 out per 1M
Evidence
Supported
Current
GPT-5.3 CodexOpenAI · Proprietary
Weekly rank
#34
Overall
66.16
Strongest category
Agentic · 61.10
Direct API
$1.75 in / $14.00 out per 1M
Evidence
Supported
Current
Qwen3.7 PlusAlibaba · Proprietary
Weekly rank
#35
Overall
65.93
Strongest category
Multilingual · 78.90
Direct API
Unavailable
Evidence
Supported
Current
GLM-5Z.AI · Open Weight
Weekly rank
#36
Overall
65.89
Strongest category
Multilingual · 48.70
Direct API
$1.00 in / $3.20 out per 1M
Evidence
Supported
Current
Gemini 3.5 Flash-LiteGoogle · Proprietary
Weekly rank
#37
Overall
65.50
Strongest category
Multimodal grounded · 53.70
Direct API
$0.30 in / $2.50 out per 1M
Evidence
Supported
Current
Claude Opus 4.6 (Adaptive)Anthropic · Proprietary
Weekly rank
#38
Overall
65.06
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Estimated
Current
Claude Sonnet 5Anthropic · Proprietary
Weekly rank
#39
Overall
65.02
Strongest category
Unavailable
Direct API
$2.00 in / $10.00 out per 1M
Evidence
Estimated
Current
Qwen3.6 PlusAlibaba · Proprietary
Weekly rank
#40
Overall
64.99
Strongest category
Multilingual · 69.70
Direct API
Unavailable
Evidence
Supported
Current
Claude Sonnet 4.6Anthropic · Proprietary
Weekly rank
#41
Overall
64.77
Strongest category
Knowledge · 76.10
Direct API
$3.00 in / $15.00 out per 1M
Evidence
Supported
Current
Gemini 3.5 FlashGoogle · Proprietary
Weekly rank
#42
Overall
64.73
Strongest category
Unavailable
Direct API
$1.50 in / $9.00 out per 1M
Evidence
Estimated
Current
GPT-5.5 ProOpenAI · Proprietary
Weekly rank
#43
Overall
64.43
Strongest category
Unavailable
Direct API
$30.00 in / $180.00 out per 1M
Evidence
Estimated
Current
Grok 4.3xAI · Proprietary
Weekly rank
#44
Overall
64.25
Strongest category
Instruction Following · 91.20
Direct API
$1.25 in / $2.50 out per 1M
Evidence
Supported
Current
Inkling-SmallThinking Machines Lab · Open Weight
Weekly rank
#45
Overall
64.02
Strongest category
Instruction Following · 92.80
Direct API
$0.58 in / $1.44 out per 1M
Evidence
Supported
Current
Claude Opus 4.5Anthropic · Proprietary
Weekly rank
#46
Overall
63.91
Strongest category
Multilingual · 82.90
Direct API
$5.00 in / $25.00 out per 1M
Evidence
Supported
Current
Grok 4.6xAI · Proprietary
Weekly rank
#47
Overall
63.42
Strongest category
Unavailable
Direct API
$2.00 in / $6.00 out per 1M
Evidence
Estimated
Current
GLM-5.2Z.AI · Open Weight
Weekly rank
#48
Overall
63.40
Strongest category
Unavailable
Direct API
$1.40 in / $4.40 out per 1M
Evidence
Estimated
Current
MiniMax M2.7MiniMax · Open Weight
Weekly rank
#49
Overall
63.29
Strongest category
Unavailable
Direct API
$0.30 in / $1.20 out per 1M
Evidence
Supported
Current
GLM-5.3Z.AI · Open Weight
Weekly rank
#50
Overall
62.84
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Estimated
Current
MiMo-V2-OmniXiaomi · Proprietary
Weekly rank
#51
Overall
62.61
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Supported
Current
GLM-5V-TurboZ.AI · Proprietary
Weekly rank
#52
Overall
62.53
Strongest category
Unavailable
Direct API
$1.20 in / $4.00 out per 1M
Evidence
Supported
Current
Gemini 3 Pro Deep ThinkGoogle · Proprietary
Weekly rank
#53
Overall
62.13
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Estimated
Current
Muse Spark 1.2Meta · Proprietary
Weekly rank
#54
Overall
61.71
Strongest category
Unavailable
Direct API
$1.25 in / $4.25 out per 1M
Evidence
Estimated
Current
GPT-5.4 ProOpenAI · Proprietary
Weekly rank
#55
Overall
61.53
Strongest category
Unavailable
Direct API
$30.00 in / $180.00 out per 1M
Evidence
Estimated
Current
Gemini 3.7 FlashGoogle · Unknown
Weekly rank
#56
Overall
61.40
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Estimated
Current
Qwen3.8-Flash-NextAlibaba · Open Weight
Weekly rank
#57
Overall
61.32
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Estimated
Current
GLM-5.3-FlashZ.AI · Open Weight
Weekly rank
#58
Overall
61.27
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Estimated
Current
DeepSeek V4 Pro 0813DeepSeek · Proprietary
Weekly rank
#59
Overall
Unavailable
Strongest category
Unavailable
Direct API
$0.43 in / $0.87 out per 1M
Evidence
Source only
Current
Agents-A1InternScience · Open Weight
Weekly rank
#60
Overall
61.02
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Estimated
Current
Agents-A1-F16-GGUFInternScience · Open Weight
Weekly rank
#61
Overall
61.02
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Estimated
Current
Agents-A1-FP8InternScience · Open Weight
Weekly rank
#62
Overall
61.02
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Estimated
Current
Agents-A1-Q4_K_M-GGUFInternScience · Open Weight
Weekly rank
#63
Overall
61.02
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Estimated
Current
Agents-A1-Q8_0-GGUFInternScience · Open Weight
Weekly rank
#64
Overall
61.02
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Estimated
Current
GLM-4.7Z.AI · Open Weight
Weekly rank
#65
Overall
60.91
Strongest category
Agentic · 51.35
Direct API
Unavailable
Evidence
Supported
Current
Grok 4.1xAI · Proprietary
Weekly rank
#66
Overall
60.75
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Estimated
Current
GLM-5 (Reasoning)Z.AI · Open Weight
Weekly rank
#67
Overall
60.58
Strongest category
Unavailable
Direct API
$1.00 in / $3.20 out per 1M
Evidence
Estimated
Current
Qwen 3.6 Max (preview)Alibaba · Proprietary
Weekly rank
#68
Overall
60.41
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Supported
Current
Gemma 4 31BGoogle · Open Weight
Weekly rank
#69
Overall
60.39
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Supported
Current
Qwen3.5 397B (Reasoning)Alibaba · Open Weight
Weekly rank
#70
Overall
60.30
Strongest category
Unavailable
Direct API
$0.60 in / $3.60 out per 1M
Evidence
Estimated
Current
Kimi K2.5 (Reasoning)Moonshot AI · Proprietary
Weekly rank
#71
Overall
60.14
Strongest category
Unavailable
Direct API
$0.60 in / $3.00 out per 1M
Evidence
Estimated
Current
Kimi K2.6Moonshot AI · Open Weight
Weekly rank
#72
Overall
60.11
Strongest category
Unavailable
Direct API
$0.95 in / $4.00 out per 1M
Evidence
Estimated
Current
Gemini 3 FlashGoogle · Proprietary
Weekly rank
#73
Overall
60.09
Strongest category
Unavailable
Direct API
$0.50 in / $3.00 out per 1M
Evidence
Supported
Current
Qwen3.5-27BAlibaba · Open Weight
Weekly rank
#74
Overall
60.04
Strongest category
Instruction Following · 93.90
Direct API
Unavailable
Evidence
Supported
Current
Grok 4.1 Fast (Reasoning)xAI · Proprietary
Weekly rank
#75
Overall
59.94
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Supported
Current
Qwen3.5-122B-A10BAlibaba · Open Weight
Weekly rank
#76
Overall
59.89
Strongest category
Multilingual · 36.80
Direct API
Unavailable
Evidence
Supported
Current
Grok 4xAI · Proprietary
Weekly rank
#77
Overall
59.84
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Supported
Current
GPT-5.2 InstantOpenAI · Proprietary
Weekly rank
#78
Overall
59.80
Strongest category
Unavailable
Direct API
$1.50 in / $6.00 out per 1M
Evidence
Estimated
Current
GPT-5.3 InstantOpenAI · Proprietary
Weekly rank
#79
Overall
59.69
Strongest category
Unavailable
Direct API
$1.75 in / $14.00 out per 1M
Evidence
Estimated
Current
MiMo-V2.5Xiaomi · Proprietary
Weekly rank
#80
Overall
59.48
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Estimated
Current
GPT-5 (high)OpenAI · Proprietary
Weekly rank
#81
Overall
59.42
Strongest category
Unavailable
Direct API
$1.25 in / $10.00 out per 1M
Evidence
Estimated
Current
Kimi K2.5Moonshot AI · Open Weight
Weekly rank
#82
Overall
59.14
Strongest category
Math · 62.50
Direct API
$0.60 in / $3.00 out per 1M
Evidence
Supported
Current
MiniMax M2.5MiniMax · Proprietary
Weekly rank
#83
Overall
58.92
Strongest category
Unavailable
Direct API
$0.30 in / $1.20 out per 1M
Evidence
Supported
Current
DeepSeek V3.2 (Thinking)DeepSeek · Open Weight
Weekly rank
#84
Overall
58.91
Strongest category
Unavailable
Direct API
$0.55 in / $2.19 out per 1M
Evidence
Estimated
Current
Qwen3 235B 2507 (Reasoning)Alibaba · Open Weight
Weekly rank
#85
Overall
58.80
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Estimated
Current
GPT-5.2OpenAI · Proprietary
Weekly rank
#86
Overall
58.39
Strongest category
Unavailable
Direct API
$1.75 in / $14.00 out per 1M
Evidence
Estimated
Current
GPT-5.2-CodexOpenAI · Proprietary
Weekly rank
#87
Overall
58.36
Strongest category
Coding · 57.42
Direct API
$1.75 in / $14.00 out per 1M
Evidence
Supported
Current
GLM-4.5Z.AI · Proprietary
Weekly rank
#88
Overall
58.35
Strongest category
Unavailable
Direct API
$0.60 in / $2.20 out per 1M
Evidence
Estimated
Current
Qwen3.5 397BAlibaba · Open Weight
Weekly rank
#89
Overall
57.78
Strongest category
Unavailable
Direct API
$0.60 in / $3.60 out per 1M
Evidence
Estimated
Current
GPT-5.3-Codex-SparkOpenAI · Proprietary
Weekly rank
#90
Overall
57.68
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Estimated
Current
Claude Opus 4.5 ThinkingAnthropic · Proprietary
Weekly rank
#91
Overall
57.56
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Estimated
Current
Gemma 4 26B A4BGoogle · Open Weight
Weekly rank
#92
Overall
57.45
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Supported
Current
Claude Haiku 4.5Anthropic · Proprietary
Weekly rank
#93
Overall
57.38
Strongest category
Unavailable
Direct API
$1.00 in / $5.00 out per 1M
Evidence
Estimated
Current
GPT-5.4 miniOpenAI · Proprietary
Weekly rank
#94
Overall
56.96
Strongest category
Unavailable
Direct API
$0.75 in / $4.50 out per 1M
Evidence
Estimated
Current
Gemini 2.5 ProGoogle · Proprietary
Weekly rank
#95
Overall
56.87
Strongest category
Unavailable
Direct API
$1.25 in / $10.00 out per 1M
Evidence
Supported
Current
Qwen3 235B 2507Alibaba · Open Weight
Weekly rank
#96
Overall
56.77
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Estimated
Current
Trinity-Large-PreviewArcee AI · Open Weight
Weekly rank
#97
Overall
56.69
Strongest category
Unavailable
Direct API
$0.25 in / $1.00 out per 1M
Evidence
Estimated
Current
Qwen3.5-35B-A3BAlibaba · Open Weight
Weekly rank
#98
Overall
56.38
Strongest category
Multilingual · 21.10
Direct API
Unavailable
Evidence
Supported
Current
Gemini 3.1 ProGoogle · Proprietary
Weekly rank
#99
Overall
56.25
Strongest category
Unavailable
Direct API
$2.00 in / $12.00 out per 1M
Evidence
Estimated
Current
Grok 4 Fast (Reasoning)xAI · Proprietary
Weekly rank
#100
Overall
56.11
Strongest category
Unavailable
Direct API
Unavailable
Evidence
Supported
Current
  • Current#1

    Claude Mythos 5

    Anthropic · Proprietary

    Weekly rank
    #1
    Overall
    83.40
    Strongest category
    Agentic · 75.79
    Direct API
    $10.00 in / $50.00 out per 1M
    Evidence
    Supported
  • Current#2

    Claude Fable 5

    Anthropic · Proprietary

    Weekly rank
    #2
    Overall
    83.15
    Strongest category
    Coding · 81.41
    Direct API
    $10.00 in / $50.00 out per 1M
    Evidence
    Supported
  • Current#3

    Claude Opus 5

    Anthropic · Proprietary

    Weekly rank
    #3
    Overall
    83.06
    Strongest category
    Knowledge · 97.00
    Direct API
    $5.00 in / $25.00 out per 1M
    Evidence
    Supported
  • Current#4

    GPT-5.6 Sol

    OpenAI · Proprietary

    Weekly rank
    #4
    Overall
    82.20
    Strongest category
    Coding · 79.01
    Direct API
    $5.00 in / $30.00 out per 1M
    Evidence
    Supported
  • Current#5

    Kimi K3

    Moonshot AI · Unknown

    Weekly rank
    #5
    Overall
    80.21
    Strongest category
    Multimodal grounded · 87.90
    Direct API
    $3.00 in / $15.00 out per 1M
    Evidence
    Supported
  • Current#6

    Qwen3.8 Max

    Alibaba · Open Weight

    Weekly rank
    #6
    Overall
    79.22
    Strongest category
    Reasoning · 95.50
    Direct API
    Unavailable
    Evidence
    Supported
  • Current#7

    Hy4 preview

    Tencent · Open Weight

    Weekly rank
    #7
    Overall
    79.16
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Estimated
  • Current#8

    Muse Spark 1.1

    Meta · Proprietary

    Weekly rank
    #8
    Overall
    77.14
    Strongest category
    Knowledge · 92.80
    Direct API
    Unavailable
    Evidence
    Supported
  • Current#9

    Claude Opus 4.8

    Anthropic · Proprietary

    Weekly rank
    #9
    Overall
    76.60
    Strongest category
    Math · 66.80
    Direct API
    $5.00 in / $25.00 out per 1M
    Evidence
    Supported
  • Current#10

    Gemini 3.6 Flash

    Google · Proprietary

    Weekly rank
    #10
    Overall
    75.66
    Strongest category
    Coding · 65.25
    Direct API
    $1.50 in / $7.50 out per 1M
    Evidence
    Supported
  • Current#11

    Grok 4.5

    xAI · Proprietary

    Weekly rank
    #11
    Overall
    75.65
    Strongest category
    Agentic · 63.07
    Direct API
    $2.00 in / $6.00 out per 1M
    Evidence
    Supported
  • Current#12

    GPT-5.4

    OpenAI · Proprietary

    Weekly rank
    #12
    Overall
    73.56
    Strongest category
    Multimodal grounded · 63.50
    Direct API
    $2.50 in / $15.00 out per 1M
    Evidence
    Supported
  • Current#13

    GPT-5.6 Terra

    OpenAI · Proprietary

    Weekly rank
    #13
    Overall
    72.95
    Strongest category
    Unavailable
    Direct API
    $2.50 in / $15.00 out per 1M
    Evidence
    Estimated
  • Current#14

    GPT-5.5

    OpenAI · Proprietary

    Weekly rank
    #14
    Overall
    72.92
    Strongest category
    Unavailable
    Direct API
    $5.00 in / $30.00 out per 1M
    Evidence
    Estimated
  • Current#15

    Claude Opus 4.7 (Adaptive)

    Anthropic · Proprietary

    Weekly rank
    #15
    Overall
    72.58
    Strongest category
    Unavailable
    Direct API
    $5.00 in / $25.00 out per 1M
    Evidence
    Estimated
  • Current#16

    Qwen3.8-27B

    Alibaba · Open Weight

    Weekly rank
    #16
    Overall
    72.51
    Strongest category
    Agentic · 70.34
    Direct API
    Unavailable
    Evidence
    Supported
  • Current#17

    Claude Opus 4.7

    Anthropic · Proprietary

    Weekly rank
    #17
    Overall
    72.33
    Strongest category
    Coding · 68.72
    Direct API
    $5.00 in / $25.00 out per 1M
    Evidence
    Supported
  • Current#18

    Qwen3.7 Max

    Alibaba · Proprietary

    Weekly rank
    #18
    Overall
    71.79
    Strongest category
    Multilingual · 100.00
    Direct API
    Unavailable
    Evidence
    Supported
  • Current#19

    Muse Spark

    Meta · Proprietary

    Weekly rank
    #19
    Overall
    71.02
    Strongest category
    Multimodal grounded · 71.40
    Direct API
    Unavailable
    Evidence
    Supported
  • Current#20

    MiMo-V2.5-Pro

    Xiaomi · Proprietary

    Weekly rank
    #20
    Overall
    69.41
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Supported
  • Current#21

    MiniMax M3

    MiniMax · Open Weight

    Weekly rank
    #21
    Overall
    68.73
    Strongest category
    Multimodal grounded · 42.20
    Direct API
    $0.30 in / $1.20 out per 1M
    Evidence
    Supported
  • Current#22

    dots3-note Preview

    Dots Studio · Open Weight

    Weekly rank
    #22
    Overall
    68.66
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Estimated
  • Current#23

    Ornith-1.5-397B

    Ornith AI · Open Weight

    Weekly rank
    #23
    Overall
    68.60
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Estimated
  • Current#24

    Claude Opus 4.6

    Anthropic · Proprietary

    Weekly rank
    #24
    Overall
    68.26
    Strongest category
    Knowledge · 82.40
    Direct API
    $5.00 in / $25.00 out per 1M
    Evidence
    Supported
  • Current#25

    Hy3

    Tencent · Open Weight

    Weekly rank
    #25
    Overall
    68.16
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Supported
  • Current#26

    Gemini 3 Pro

    Google · Proprietary

    Weekly rank
    #26
    Overall
    67.64
    Strongest category
    Multimodal grounded · 67.60
    Direct API
    $2.00 in / $12.00 out per 1M
    Evidence
    Supported
  • Current#27

    GPT-5.6 Luna

    OpenAI · Proprietary

    Weekly rank
    #27
    Overall
    67.35
    Strongest category
    Unavailable
    Direct API
    $1.00 in / $6.00 out per 1M
    Evidence
    Estimated
  • Current#28

    GPT-5.2 Pro

    OpenAI · Proprietary

    Weekly rank
    #28
    Overall
    67.30
    Strongest category
    Unavailable
    Direct API
    $21.00 in / $168.00 out per 1M
    Evidence
    Supported
  • Current#29

    MiMo-V2-Pro

    Xiaomi · Proprietary

    Weekly rank
    #29
    Overall
    67.15
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Supported
  • Current#30

    GLM-5.1

    Z.AI · Open Weight

    Weekly rank
    #30
    Overall
    67.04
    Strongest category
    Math · 64.50
    Direct API
    $1.40 in / $4.40 out per 1M
    Evidence
    Supported
  • Current#31

    Inkling

    Thinking Machines Lab · Open Weight

    Weekly rank
    #31
    Overall
    67.02
    Strongest category
    Instruction Following · 88.60
    Direct API
    $1.87 in / $4.68 out per 1M
    Evidence
    Supported
  • Current#32

    GPT-5.4 nano

    OpenAI · Proprietary

    Weekly rank
    #32
    Overall
    66.78
    Strongest category
    Knowledge · 51.70
    Direct API
    $0.20 in / $1.25 out per 1M
    Evidence
    Supported
  • Current#33

    GLM-5-Turbo

    Z.AI · Proprietary

    Weekly rank
    #33
    Overall
    66.30
    Strongest category
    Unavailable
    Direct API
    $1.20 in / $4.00 out per 1M
    Evidence
    Supported
  • Current#34

    GPT-5.3 Codex

    OpenAI · Proprietary

    Weekly rank
    #34
    Overall
    66.16
    Strongest category
    Agentic · 61.10
    Direct API
    $1.75 in / $14.00 out per 1M
    Evidence
    Supported
  • Current#35

    Qwen3.7 Plus

    Alibaba · Proprietary

    Weekly rank
    #35
    Overall
    65.93
    Strongest category
    Multilingual · 78.90
    Direct API
    Unavailable
    Evidence
    Supported
  • Current#36

    GLM-5

    Z.AI · Open Weight

    Weekly rank
    #36
    Overall
    65.89
    Strongest category
    Multilingual · 48.70
    Direct API
    $1.00 in / $3.20 out per 1M
    Evidence
    Supported
  • Current#37

    Gemini 3.5 Flash-Lite

    Google · Proprietary

    Weekly rank
    #37
    Overall
    65.50
    Strongest category
    Multimodal grounded · 53.70
    Direct API
    $0.30 in / $2.50 out per 1M
    Evidence
    Supported
  • Current#38

    Claude Opus 4.6 (Adaptive)

    Anthropic · Proprietary

    Weekly rank
    #38
    Overall
    65.06
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Estimated
  • Current#39

    Claude Sonnet 5

    Anthropic · Proprietary

    Weekly rank
    #39
    Overall
    65.02
    Strongest category
    Unavailable
    Direct API
    $2.00 in / $10.00 out per 1M
    Evidence
    Estimated
  • Current#40

    Qwen3.6 Plus

    Alibaba · Proprietary

    Weekly rank
    #40
    Overall
    64.99
    Strongest category
    Multilingual · 69.70
    Direct API
    Unavailable
    Evidence
    Supported
  • Current#41

    Claude Sonnet 4.6

    Anthropic · Proprietary

    Weekly rank
    #41
    Overall
    64.77
    Strongest category
    Knowledge · 76.10
    Direct API
    $3.00 in / $15.00 out per 1M
    Evidence
    Supported
  • Current#42

    Gemini 3.5 Flash

    Google · Proprietary

    Weekly rank
    #42
    Overall
    64.73
    Strongest category
    Unavailable
    Direct API
    $1.50 in / $9.00 out per 1M
    Evidence
    Estimated
  • Current#43

    GPT-5.5 Pro

    OpenAI · Proprietary

    Weekly rank
    #43
    Overall
    64.43
    Strongest category
    Unavailable
    Direct API
    $30.00 in / $180.00 out per 1M
    Evidence
    Estimated
  • Current#44

    Grok 4.3

    xAI · Proprietary

    Weekly rank
    #44
    Overall
    64.25
    Strongest category
    Instruction Following · 91.20
    Direct API
    $1.25 in / $2.50 out per 1M
    Evidence
    Supported
  • Current#45

    Inkling-Small

    Thinking Machines Lab · Open Weight

    Weekly rank
    #45
    Overall
    64.02
    Strongest category
    Instruction Following · 92.80
    Direct API
    $0.58 in / $1.44 out per 1M
    Evidence
    Supported
  • Current#46

    Claude Opus 4.5

    Anthropic · Proprietary

    Weekly rank
    #46
    Overall
    63.91
    Strongest category
    Multilingual · 82.90
    Direct API
    $5.00 in / $25.00 out per 1M
    Evidence
    Supported
  • Current#47

    Grok 4.6

    xAI · Proprietary

    Weekly rank
    #47
    Overall
    63.42
    Strongest category
    Unavailable
    Direct API
    $2.00 in / $6.00 out per 1M
    Evidence
    Estimated
  • Current#48

    GLM-5.2

    Z.AI · Open Weight

    Weekly rank
    #48
    Overall
    63.40
    Strongest category
    Unavailable
    Direct API
    $1.40 in / $4.40 out per 1M
    Evidence
    Estimated
  • Current#49

    MiniMax M2.7

    MiniMax · Open Weight

    Weekly rank
    #49
    Overall
    63.29
    Strongest category
    Unavailable
    Direct API
    $0.30 in / $1.20 out per 1M
    Evidence
    Supported
  • Current#50

    GLM-5.3

    Z.AI · Open Weight

    Weekly rank
    #50
    Overall
    62.84
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Estimated
  • Current#51

    MiMo-V2-Omni

    Xiaomi · Proprietary

    Weekly rank
    #51
    Overall
    62.61
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Supported
  • Current#52

    GLM-5V-Turbo

    Z.AI · Proprietary

    Weekly rank
    #52
    Overall
    62.53
    Strongest category
    Unavailable
    Direct API
    $1.20 in / $4.00 out per 1M
    Evidence
    Supported
  • Current#53

    Gemini 3 Pro Deep Think

    Google · Proprietary

    Weekly rank
    #53
    Overall
    62.13
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Estimated
  • Current#54

    Muse Spark 1.2

    Meta · Proprietary

    Weekly rank
    #54
    Overall
    61.71
    Strongest category
    Unavailable
    Direct API
    $1.25 in / $4.25 out per 1M
    Evidence
    Estimated
  • Current#55

    GPT-5.4 Pro

    OpenAI · Proprietary

    Weekly rank
    #55
    Overall
    61.53
    Strongest category
    Unavailable
    Direct API
    $30.00 in / $180.00 out per 1M
    Evidence
    Estimated
  • Current#56

    Gemini 3.7 Flash

    Google · Unknown

    Weekly rank
    #56
    Overall
    61.40
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Estimated
  • Current#57

    Qwen3.8-Flash-Next

    Alibaba · Open Weight

    Weekly rank
    #57
    Overall
    61.32
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Estimated
  • Current#58

    GLM-5.3-Flash

    Z.AI · Open Weight

    Weekly rank
    #58
    Overall
    61.27
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Estimated
  • Current#59

    DeepSeek V4 Pro 0813

    DeepSeek · Proprietary

    Weekly rank
    #59
    Overall
    Unavailable
    Strongest category
    Unavailable
    Direct API
    $0.43 in / $0.87 out per 1M
    Evidence
    Source only
  • Current#60

    Agents-A1

    InternScience · Open Weight

    Weekly rank
    #60
    Overall
    61.02
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Estimated
  • Current#61

    Agents-A1-F16-GGUF

    InternScience · Open Weight

    Weekly rank
    #61
    Overall
    61.02
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Estimated
  • Current#62

    Agents-A1-FP8

    InternScience · Open Weight

    Weekly rank
    #62
    Overall
    61.02
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Estimated
  • Current#63

    Agents-A1-Q4_K_M-GGUF

    InternScience · Open Weight

    Weekly rank
    #63
    Overall
    61.02
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Estimated
  • Current#64

    Agents-A1-Q8_0-GGUF

    InternScience · Open Weight

    Weekly rank
    #64
    Overall
    61.02
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Estimated
  • Current#65

    GLM-4.7

    Z.AI · Open Weight

    Weekly rank
    #65
    Overall
    60.91
    Strongest category
    Agentic · 51.35
    Direct API
    Unavailable
    Evidence
    Supported
  • Current#66

    Grok 4.1

    xAI · Proprietary

    Weekly rank
    #66
    Overall
    60.75
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Estimated
  • Current#67

    GLM-5 (Reasoning)

    Z.AI · Open Weight

    Weekly rank
    #67
    Overall
    60.58
    Strongest category
    Unavailable
    Direct API
    $1.00 in / $3.20 out per 1M
    Evidence
    Estimated
  • Current#68

    Qwen 3.6 Max (preview)

    Alibaba · Proprietary

    Weekly rank
    #68
    Overall
    60.41
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Supported
  • Current#69

    Gemma 4 31B

    Google · Open Weight

    Weekly rank
    #69
    Overall
    60.39
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Supported
  • Current#70

    Qwen3.5 397B (Reasoning)

    Alibaba · Open Weight

    Weekly rank
    #70
    Overall
    60.30
    Strongest category
    Unavailable
    Direct API
    $0.60 in / $3.60 out per 1M
    Evidence
    Estimated
  • Current#71

    Kimi K2.5 (Reasoning)

    Moonshot AI · Proprietary

    Weekly rank
    #71
    Overall
    60.14
    Strongest category
    Unavailable
    Direct API
    $0.60 in / $3.00 out per 1M
    Evidence
    Estimated
  • Current#72

    Kimi K2.6

    Moonshot AI · Open Weight

    Weekly rank
    #72
    Overall
    60.11
    Strongest category
    Unavailable
    Direct API
    $0.95 in / $4.00 out per 1M
    Evidence
    Estimated
  • Current#73

    Gemini 3 Flash

    Google · Proprietary

    Weekly rank
    #73
    Overall
    60.09
    Strongest category
    Unavailable
    Direct API
    $0.50 in / $3.00 out per 1M
    Evidence
    Supported
  • Current#74

    Qwen3.5-27B

    Alibaba · Open Weight

    Weekly rank
    #74
    Overall
    60.04
    Strongest category
    Instruction Following · 93.90
    Direct API
    Unavailable
    Evidence
    Supported
  • Current#75

    Grok 4.1 Fast (Reasoning)

    xAI · Proprietary

    Weekly rank
    #75
    Overall
    59.94
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Supported
  • Current#76

    Qwen3.5-122B-A10B

    Alibaba · Open Weight

    Weekly rank
    #76
    Overall
    59.89
    Strongest category
    Multilingual · 36.80
    Direct API
    Unavailable
    Evidence
    Supported
  • Current#77

    Grok 4

    xAI · Proprietary

    Weekly rank
    #77
    Overall
    59.84
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Supported
  • Current#78

    GPT-5.2 Instant

    OpenAI · Proprietary

    Weekly rank
    #78
    Overall
    59.80
    Strongest category
    Unavailable
    Direct API
    $1.50 in / $6.00 out per 1M
    Evidence
    Estimated
  • Current#79

    GPT-5.3 Instant

    OpenAI · Proprietary

    Weekly rank
    #79
    Overall
    59.69
    Strongest category
    Unavailable
    Direct API
    $1.75 in / $14.00 out per 1M
    Evidence
    Estimated
  • Current#80

    MiMo-V2.5

    Xiaomi · Proprietary

    Weekly rank
    #80
    Overall
    59.48
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Estimated
  • Current#81

    GPT-5 (high)

    OpenAI · Proprietary

    Weekly rank
    #81
    Overall
    59.42
    Strongest category
    Unavailable
    Direct API
    $1.25 in / $10.00 out per 1M
    Evidence
    Estimated
  • Current#82

    Kimi K2.5

    Moonshot AI · Open Weight

    Weekly rank
    #82
    Overall
    59.14
    Strongest category
    Math · 62.50
    Direct API
    $0.60 in / $3.00 out per 1M
    Evidence
    Supported
  • Current#83

    MiniMax M2.5

    MiniMax · Proprietary

    Weekly rank
    #83
    Overall
    58.92
    Strongest category
    Unavailable
    Direct API
    $0.30 in / $1.20 out per 1M
    Evidence
    Supported
  • Current#84

    DeepSeek V3.2 (Thinking)

    DeepSeek · Open Weight

    Weekly rank
    #84
    Overall
    58.91
    Strongest category
    Unavailable
    Direct API
    $0.55 in / $2.19 out per 1M
    Evidence
    Estimated
  • Current#85

    Qwen3 235B 2507 (Reasoning)

    Alibaba · Open Weight

    Weekly rank
    #85
    Overall
    58.80
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Estimated
  • Current#86

    GPT-5.2

    OpenAI · Proprietary

    Weekly rank
    #86
    Overall
    58.39
    Strongest category
    Unavailable
    Direct API
    $1.75 in / $14.00 out per 1M
    Evidence
    Estimated
  • Current#87

    GPT-5.2-Codex

    OpenAI · Proprietary

    Weekly rank
    #87
    Overall
    58.36
    Strongest category
    Coding · 57.42
    Direct API
    $1.75 in / $14.00 out per 1M
    Evidence
    Supported
  • Current#88

    GLM-4.5

    Z.AI · Proprietary

    Weekly rank
    #88
    Overall
    58.35
    Strongest category
    Unavailable
    Direct API
    $0.60 in / $2.20 out per 1M
    Evidence
    Estimated
  • Current#89

    Qwen3.5 397B

    Alibaba · Open Weight

    Weekly rank
    #89
    Overall
    57.78
    Strongest category
    Unavailable
    Direct API
    $0.60 in / $3.60 out per 1M
    Evidence
    Estimated
  • Current#90

    GPT-5.3-Codex-Spark

    OpenAI · Proprietary

    Weekly rank
    #90
    Overall
    57.68
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Estimated
  • Current#91

    Claude Opus 4.5 Thinking

    Anthropic · Proprietary

    Weekly rank
    #91
    Overall
    57.56
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Estimated
  • Current#92

    Gemma 4 26B A4B

    Google · Open Weight

    Weekly rank
    #92
    Overall
    57.45
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Supported
  • Current#93

    Claude Haiku 4.5

    Anthropic · Proprietary

    Weekly rank
    #93
    Overall
    57.38
    Strongest category
    Unavailable
    Direct API
    $1.00 in / $5.00 out per 1M
    Evidence
    Estimated
  • Current#94

    GPT-5.4 mini

    OpenAI · Proprietary

    Weekly rank
    #94
    Overall
    56.96
    Strongest category
    Unavailable
    Direct API
    $0.75 in / $4.50 out per 1M
    Evidence
    Estimated
  • Current#95

    Gemini 2.5 Pro

    Google · Proprietary

    Weekly rank
    #95
    Overall
    56.87
    Strongest category
    Unavailable
    Direct API
    $1.25 in / $10.00 out per 1M
    Evidence
    Supported
  • Current#96

    Qwen3 235B 2507

    Alibaba · Open Weight

    Weekly rank
    #96
    Overall
    56.77
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Estimated
  • Current#97

    Trinity-Large-Preview

    Arcee AI · Open Weight

    Weekly rank
    #97
    Overall
    56.69
    Strongest category
    Unavailable
    Direct API
    $0.25 in / $1.00 out per 1M
    Evidence
    Estimated
  • Current#98

    Qwen3.5-35B-A3B

    Alibaba · Open Weight

    Weekly rank
    #98
    Overall
    56.38
    Strongest category
    Multilingual · 21.10
    Direct API
    Unavailable
    Evidence
    Supported
  • Current#99

    Gemini 3.1 Pro

    Google · Proprietary

    Weekly rank
    #99
    Overall
    56.25
    Strongest category
    Unavailable
    Direct API
    $2.00 in / $12.00 out per 1M
    Evidence
    Estimated
  • Current#100

    Grok 4 Fast (Reasoning)

    xAI · Proprietary

    Weekly rank
    #100
    Overall
    56.11
    Strongest category
    Unavailable
    Direct API
    Unavailable
    Evidence
    Supported
Read the evidence

A popular model is a starting point, not a verdict.

Weekly order follows the corrected BenchLM public bench-align-v5 overall order. Scores, category evidence, pricing, and freshness stay visible so you can validate the route that fits your workload.

Sources: Data from BenchLM.aiData from BenchLM.ai

How BenchAlign rankings work