How many tracked prints does the SciCode family have?

SciCode leaderboard — the family board.

2 TRACKED VARIANTS · 1 FIRST-CLASS BOARD

One family, 2 tracked prints. Scoring configs and splits of the base board render as sections of this page, each under its own honest label.

● LIVE DATA409 MODELS ON THIS BOARDLEADER MISTRAL LARGE 4 AT 91.8

The board — SciCodeTOP 100 OF 409 MEASURED · BEST SCORE PER MODEL, DEFAULT VARIANT

#ModelVendorScoreVLast seen

01Mistral Large 4Mistral91.82026-10-08

02Claude Opus 5.5Anthropic66.92026-10-04

03Claude Fable 5.1Anthropic63.12026-10-04

04Gemini 4 ArgonGoogle61.82026-10-01

05Claude Fable 5Anthropic61.02026-10-04

06Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)Anthropic61.02026-10-04

07MiMo V2.6 ProXiaomi60.92026-09-22

08Gemini 3.7 FlashGoogle59.82026-08-14

09Seed 2.1 Pro PreviewByteDance59.82026-09-28

10Muse Spark 1.3Meta59.72026-09-03

11Kimi K3Moonshot59.52026-07-31

12Claude Opus 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback)Anthropic59.32026-10-04

13GLM-5.3Z.ai59.02026-09-25

14Gemini 3.1 ProGoogle592026-08-24

15Step 5 PreviewStepFun58.92026-09-19

16Muse Spark 1.1Meta58.82026-07-11

17GPT-5.5OpenAI58.42026-09-28

18Seed2.1ByteDance57.82026-09-28

19Grok 4.7SpaceXAI57.82026-10-02

20GPT-5.6 SolOpenAI57.82026-07-27

21GPT-6 SolOpenAI57.62026-09-23

22Muse Spark 1.2Meta57.42026-08-06

23GPT-5.4OpenAI56.62026-05-03

24Gemini 3.8 FlashGoogle56.62026-09-03

25Grok 4.6SpaceXAI56.52026-08-22

26GPT-6 AstraOpenAI56.52026-09-04

27Claude Opus 5Anthropic56.42026-10-04

28Gemini 3 ProGoogle56.12026-08-24

29GPT-6.1 SolOpenAI55.82026-09-30

30GPT-5.6 TerraOpenAI55.02026-07-10

31Grok4.5SpaceXAI55.02026-07-09

32Haiku 5.5Anthropic55.02026-10-08

33GPT-5.2 CodexOpenAI54.62026-05-02

34GPT-6 LunaOpenAI54.62026-09-23

35Claude Opus 4.7Anthropic54.52026-06-01

36Claude Opus 4.8Anthropic54.42026-10-04

37Claude Sonnet 5Anthropic54.32026-10-04

38Ling-3.1-flashInclusionAI54.12026-10-04

39Qwen3.8 2.4T A95BAlibaba54.12026-08-14

40Gemini 3.5 FlashGoogle53.92026-09-10

41GPT-5.6 LunaOpenAI53.62026-07-30

42Qwen3.7 MaxAlibaba53.52026-08-23

43Gemini 3.6 FlashGoogle53.42026-09-10

44GPT-5.3 CodexOpenAI53.22026-05-02

45Qwen3.8 Max PreviewAlibaba53.22026-09-16

46Claude 5.5Anthropic52.92026-10-04

47GPT-5.5 InstantOpenAI52.52026-07-01

48Kimi K2.6Moonshot52.22026-08-23

49GPT-5.2OpenAI52.12026-08-24

50GPT-5.4 miniOpenAI52.12026-06-01

51Claude Opus 4.6Anthropic522026-08-24

52JT-4.1 Flash 236B A21BChina Mobile52.02026-09-30

53DeepSeek-V4.1-FlashDeepSeek51.92026-10-01

54Agnes 3.0 FlashSapiens AI51.62026-09-12

55GLM 5.3 FlashZ.ai51.62026-08-27

56Muse SparkMeta51.52026-05-02

57Qwen3.7 Plus PreviewAlibaba51.32026-08-23

58MiMo V2.6 Flash RLXiaomi51.32026-09-28

59GLM-5.2Z.ai51.22026-07-27

60DeepSeek-V4-ProDeepSeek50.82026-10-01

61MiMo V2.5 ProXiaomi50.62026-09-22

62Qwen3.8 Flash NextAlibaba50.62026-08-28

63Gemini 3 Flash PreviewGoogle50.62026-05-02

64DeepSeek-V4-FlashDeepSeek50.32026-10-01

65MiniMax M2.7MiniMax50.12026-07-30

66Claude Sonnet 4.6Anthropic50.12026-10-04

67Claude Opus 4.5Anthropic502026-08-24

68Inkling-SmallThinking Machines49.72026-08-23

69Claude Sonnet 5.5 (Adaptive Reasoning, Low Effort, Default Fallback)Anthropic49.12026-10-04

70Kimi K2.5Moonshot49.02026-08-23

71Agnes 2.5 Pro BetaSapiens AI48.82026-08-27

72Hy3-previewTencent48.62026-05-02

73Grok 4.3SpaceXAI48.32026-05-23

74Solar Open2 250BUpstage48.02026-08-13

75Kimi K2.7 CodeMoonshot47.82026-06-17

76Solar Mini4Upstage47.62026-10-08

77GPT-5.4 nanoOpenAI47.22026-06-01

78MiniMax M3MiniMax47.12026-06-04

79InklingThinking Machines47.02026-09-10

80Qwen3.6 Max PreviewAlibaba46.92026-05-02

81Qwen3.8 27BAlibaba46.62026-08-25

82o4-miniOpenAI46.52026-05-02

83Gemini 2.5 ProGoogle46.32026-06-06

84GLM-5Z.ai46.22026-05-02

85Claude Sonnet 4.5Anthropic45.72026-08-24

86Grok 4SpaceXAI45.72026-05-02

87Gemma 4 31BGoogle45.52026-06-01

88Apodex 1.1Apodex45.52026-08-31

89GLM-4.7Z.ai45.12026-06-01

90Muse GlimmerMeta44.92026-08-23

91Kimi K2 ThinkingMoonshot44.82026-05-15

92Qwen3.5 397B A17BAlibaba44.82026-07-30

93GLM-5.1Z.ai44.82026-05-02

94Grok 4.20SpaceXAI44.72026-05-02

95Nemotron 3 Ultra 550B A55BNVIDIA44.62026-09-01

96Solar Pro4Upstage44.62026-08-13

97MiniMax M2.5MiniMax44.42026-08-24

98Motif-3-BetaMotif Technologies44.32026-07-21

99Grok 4.1 FastSpaceXAI44.22026-06-23

100Grok 4 FastSpaceXAI44.22026-05-02

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

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

SciCode (subtask)

VARIANT9 models · best score per model

#ModelVendorScoreVLast seen

01Kimi K2.6Moonshot522026-06-06

02DeepSeek-V4-ProDeepSeek50.52026-06-06

03DeepSeek-V4-FlashDeepSeek48.22026-06-06

04Qwen3.5 397B A17BAlibaba482026-06-06

05GLM-5.1Z.ai47.72026-06-06

06Nemotron 3 Ultra 550B A55BNVIDIA44.62026-09-01

07Nemotron 3 Super 120B A12BNVIDIA42.32026-07-07

08NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-BF16NVIDIA40.62026-07-07

09MiniMax M2.7MiniMax38.32026-06-06

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