How many tracked prints does the HLE family have?

HLE leaderboard — the family board.

6 TRACKED VARIANTS · 2 FIRST-CLASS BOARDS

One family, 6 tracked prints: HLE-Verified is cited standalone and keeps live board of its own. Scoring configs and splits of the base board render as sections of this page, each under its own honest label.

● LIVE DATA425 MODELS ON THIS BOARDLEADER CLAUDE OPUS 5.5 AT 67.7

First-class boards in this familyCITED STANDALONE · EACH KEEPS ITS OWN LIVE BOARD

#BoardModels scored

01HLETHIS PAGE425

02HLE-Verified8

The board — HLETOP 100 OF 425 MEASURED · BEST SCORE PER MODEL, DEFAULT VARIANT

#ModelVendorScoreVLast seen

01Claude Opus 5.5Anthropic67.72026-10-04

02Claude Fable 5.1Anthropic65.62026-10-04

03Claude Opus 5Anthropic64.72026-10-04

04Claude Mythos PreviewAnthropic64.72026-08-24

05Sonnet 5.5Anthropic64.52026-10-07

06Claude Fable 5Anthropic64.52026-10-04

07GLM-5.3Z.ai62.52026-09-25

08Muse Spark 1.1Meta62.12026-08-24

09Claude Mythos 5.1Anthropic60.92026-09-01

10Claude Mythos 5Anthropic592026-09-01

11Muse SparkMeta58.42026-08-24

12Claude Opus 4.8Anthropic57.92026-10-04

13Claude Sonnet 5Anthropic57.42026-10-04

14Haiku 5.5Anthropic57.42026-10-08

15GPT-5.5 ProOpenAI57.22026-08-24

16GPT-6 AstraOpenAI57.22026-09-22

17Gemini 4 ArgonGoogle57.12026-10-01

18Kimi K3Moonshot562026-08-24

19Seed 2.1 Pro PreviewByteDance55.72026-09-26

20GLM 5.3 FlashZ.ai55.32026-08-27

21Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)Anthropic55.02026-10-04

22Claude Opus 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback)Anthropic54.72026-10-04

23Claude Opus 4.7Anthropic54.72026-10-04

24GLM-5.2Z.ai54.72026-08-24

25Claude Opus 4.6Anthropic53.12026-10-08

26GPT-6.1 SolOpenAI52.92026-09-30

27GLM-5.1Z.ai52.32026-08-24

28GPT-5.5OpenAI52.22026-08-24

29Gemini 3.1 ProGoogle51.42026-10-08

30Kimi K2.5Moonshot50.22026-10-08

31GPT-5.6 SolOpenAI49.52026-09-10

32MiMo V2.6 ProXiaomi49.42026-09-22

33Claude Sonnet 4.6Anthropic492026-10-04

34Muse Spark 1.3Meta48.72026-09-03

35Qwen3.5 27BAlibaba48.52026-08-24

36DeepSeek-V4-ProDeepSeek48.22026-10-01

37MiMo V2.5 ProXiaomi482026-09-22

38GPT-6 SolOpenAI47.92026-09-23

39Gemini 3.7 FlashGoogle47.92026-08-14

40Gemini 3.8 FlashGoogle47.82026-09-03

41Qwen3.5 122B A10BAlibaba47.52026-08-24

42Qwen3.5 35B A3BAlibaba47.42026-08-24

43Step 5 PreviewStepFun46.52026-09-19

44Gemini 3 ProGoogle45.82026-08-24

45GPT-5.2OpenAI45.52026-08-24

46Muse Spark 1.2Meta45.52026-08-06

47Grok 4.6SpaceXAI44.12026-08-22

48GPT-5.4OpenAI43.72026-10-08

49Qwen3.8 Max PreviewAlibaba43.62026-09-16

50JT-4.1 Flash 236B A21BChina Mobile43.62026-09-30

51Gemini 3 Flash PreviewGoogle43.52026-08-24

52Grok 4.7SpaceXAI43.12026-10-02

53GPT-5.6 TerraOpenAI42.92026-07-10

54GLM-4.7Z.ai42.82026-08-24

55GPT-5.4 ProOpenAI42.72026-05-03

56Grok4.5SpaceXAI42.72026-07-09

57Gemini 3.5 FlashGoogle42.72026-09-10

58GPT-5.3 CodexOpenAI42.52026-05-02

59Qwen3.8 2.4T A95BAlibaba42.42026-08-14

60Qwen3.7 MaxAlibaba41.42026-08-24

61Gemini 3.6 FlashGoogle40.82026-09-10

62DeepSeek-V3.2DeepSeek40.82026-10-08

63Motif-3-BetaMotif Technologies40.42026-07-21

64Grok 4SpaceXAI402026-08-24

65Claude 5.5Anthropic39.82026-10-04

66GPT-5.6 LunaOpenAI39.52026-07-30

67Ling-3.1-flashInclusionAI39.42026-10-04

68DeepSeek-V4.1-FlashDeepSeek39.22026-10-01

69ERNIE 5.0 Thinking PreviewBaidu392026-08-24

70MiniMax M3MiniMax39.02026-07-13

71DeepSeek-V4-FlashDeepSeek38.62026-10-01

72GPT-6 LunaOpenAI38.52026-09-23

73Agnes 3.0 FlashSapiens AI38.52026-09-12

74Qwen3.8 Flash NextAlibaba38.02026-08-28

75Agnes 2.5 Pro BetaSapiens AI37.52026-08-27

76Kimi K2.6Moonshot37.52026-08-24

77Nemotron 3 Ultra 550B A55BNVIDIA37.42026-09-01

78Grok 4.3SpaceXAI37.22026-05-23

79Motif-3Motif Technologies37.02026-08-13

80GPT-5.2 ProOpenAI36.62026-08-24

81Claude Sonnet 5.5 (Adaptive Reasoning, Low Effort, Default Fallback)Anthropic36.22026-10-04

82GPT-5.2 CodexOpenAI35.72026-05-02

83Qwen3.7 Plus PreviewAlibaba35.62026-08-26

84MiMo V2.6 Flash RLXiaomi35.12026-09-28

85Mistral Large 4Mistral35.02026-10-07

86Kimi K2.7 CodeMoonshot35.02026-06-17

87Apodex 1.1Apodex34.12026-08-31

88Qwen3.8 27BAlibaba33.92026-08-26

89Nex-N2-ProNex AGI33.72026-06-26

90LongCat-2.0Meituan33.72026-07-20

91Agnes 2.5 Pro AlphaSapiens AI33.62026-07-25

92Hy3-previewTencent33.52026-05-02

93Inkling-SmallThinking Machines33.32026-08-24

94MiMo V2.5 Pro FP4 DFlashXiaomi332026-08-29

95Grok 4.20SpaceXAI32.42026-09-10

96K2 Horizon 375B A23BMBZUAI32.02026-09-04

97InklingThinking Machines31.92026-09-10

98Qwen3.6 Max PreviewAlibaba30.82026-05-02

99Claude Opus 4.5Anthropic30.82026-08-24

100DeepSeek-V3.2-SpecialeDeepSeek30.62026-08-24

◆ IV — INDEPENDENTLY VERIFIED · ◆ AA — AGGREGATOR · ◆ VA — VENDOR · ◇ SA — SOURCE-ATTRIBUTED

Variants of this boardSCORING CONFIGS & SPLITS — NOT CITED STANDALONE, SO THEY LIVE HERE

HLE (with tools)

VARIANT56 models · best score per model

#ModelVendorScoreVLast seen

01Claude Mythos 5.1Anthropic652026-09-01

02Claude Fable 5.1Anthropic652026-09-17

03Claude Opus 5Anthropic64.72026-09-17

04Claude Mythos PreviewAnthropic64.72026-06-12

05GPT-5.6 SolOpenAI64.52026-08-28

06Sonnet 5.5Anthropic64.52026-09-29

07Claude Fable 5Anthropic64.52026-09-17

08Claude Mythos 5Anthropic64.52026-09-01

09DeepSeek-V4.1-FlashDeepSeek63.92026-09-11

10GLM-5.3Z.ai62.52026-09-10

11DeepSeek-V4-ProDeepSeek602026-09-10

12Kimi K3Moonshot59.82026-08-28

13GPT-5.4 ProOpenAI58.72026-06-21

14Claude Opus 4.8Anthropic57.92026-08-28

15Claude Sonnet 5Anthropic57.42026-07-07

HLE (text-only, no tools)

VARIANT6 models · best score per model

#ModelVendorScoreVLast seen

01Nemotron 3 SuperNVIDIA20.32026-08-11

02Qwen3.6 35B A3BAlibaba19.62026-08-11

03Gemma 4 26B A4BGoogle17.42026-08-11

04gpt-oss-20bOpenAI13.82026-08-11

05Nemotron 3.5 LightningNVIDIA11.72026-08-11

06Nemotron 3 NanoNVIDIA10.92026-08-11

HLE Calibration

VARIANT5 models · best score per model

#ModelVendorScoreVLast seen

01Gemini 3.1 ProGoogle50.42026-07-13

02Muse SparkMeta50.32026-07-16

03GPT-5.5OpenAI44.22026-07-13

04Claude Opus 4.8Anthropic26.52026-07-13

05Muse Spark 1.1Meta23.42026-07-13

HLE (wo / w tools)

VARIANT5 models · best score per model

#ModelVendorScoreVLast seen

01Claude Opus 4.8Anthropic57.92026-08-13

02Kimi K3Moonshot562026-08-13

03GLM-5.2Z.ai54.72026-08-13

04DeepSeek-V4-FlashDeepSeek51.52026-08-13

05DeepSeek-V4-ProDeepSeek48.22026-08-13

THE FAMILY BOARD · EVERY PRINT LABELED · EVERY SCORE SOURCE-ATTRIBUTED ON ITS OWN LIVE BOARDAll leaderboards The frontier board Models by vendor