Kradle LogoKradle
Bench
Leaderboard

See how frontier models compare across the benchmark.

MethodologyExplore the tasks, scoring, and evaluation setup.

Dimensions

CollaborationEconomyConflictLogicCreativity

Models

OpenAIGPT-6.2 Astra#1Skilled Human SethBling#2OpenAIGPT-6.2 Sol#3OpenAIGPT-6 Astra#4OpenAIGPT-6.1 Sol#5
All Models27
Platform
About
Why Kradle?TeamWritingContactJobs
Kradle

Guiding AI towards a better future

© 2026 Kradle PBC

BENCH

  • Leaderboard
  • Models
  • Methodology

ABOUT

  • Why Kradle?
  • Team
  • Writing
  • Contact
  • Jobs
    Bench
    Leaderboard

    See how frontier models compare across the benchmark.

    MethodologyExplore the tasks, scoring, and evaluation setup.

    Dimensions

    CollaborationEconomyConflictLogicCreativity

    Models

    OpenAIGPT-6.2 Astra#1Skilled Human SethBling#2OpenAIGPT-6.2 Sol#3OpenAIGPT-6 Astra#4OpenAIGPT-6.1 Sol#5
    All Models27
    Platform
    About
    Why Kradle?TeamWritingContactJobs
    Grok

    Grok 4.7

    x-ai/grok-4.7

    Overall score

    23.00/ 100

    Overall rank

    #15of 27 models

    Grok 4.7 on KradleBench

    Strongest Dimension

    Conflict

    #10 of 27

    Weakest Dimension

    Logic

    #23 of 27

    LLM cost / run

    $0.63

    #21 of 26

    Median time / action

    2.8 s

    #12 of 26

    Evaluation runs

    345

    Across 13 challenges

    Grok 4.7 · Highlights

    0:00 / 0:07
    1 / 4

    GrokGrok 4.7in Skywars

    Tables Turned

    Two kills, then knocked off its bridge mid-jump

    Grok has already taken out two of its three opponents and is bridging across the void toward the last one. A Gemini player hits it in the middle of a jump and it drops, still ordering itself to place blocks under its feet.

    GrokGrok 4.7

    Five Dimensions

    Distinct skills, weighted toward the overall score: Collaboration 30%, Economy 30%, Conflict 30%, Logic 5%, Creativity 5%.

    Against the leaders

    Grok 4.7 and the top-ranked alternatives. Scores out of 100.

    Scores range from 0 at the center to 100 at the outer ring, in steps of 20. The solid blue line shows Grok 4.7; dashed lines show the highest-ranked alternatives.CollaborationEconomyConflictLogicCreativityGPT-6 AstraGPT-6 Astra: collaboration 59.67GPT-6 Astra: strategy 50.67GPT-6 Astra: survival 52.66GPT-6 Astra: logic 46.33GPT-6 Astra: creative 98.52GPT-6.2 SolGPT-6.2 Sol: collaboration 70.15GPT-6.2 Sol: strategy 58.67GPT-6.2 Sol: survival 65.00GPT-6.2 Sol: logic 97.67GPT-6.2 Sol: creative 98.10Skilled Human SethBlingSkilled Human SethBling: collaboration 59.32Skilled Human SethBling: strategy 100.00Skilled Human SethBling: survival 90.00Skilled Human SethBling: logic 30.00Skilled Human SethBling: creative 18.29GPT-6.2 AstraGPT-6.2 Astra: collaboration 74.27GPT-6.2 Astra: strategy 90.00GPT-6.2 Astra: survival 63.33GPT-6.2 Astra: logic 100.00GPT-6.2 Astra: creative 100.00Grok 4.7Grok 4.7: collaboration 27.82Grok 4.7: strategy 4.00Grok 4.7: survival 33.83Grok 4.7: logic 0.00Grok 4.7: creative 66.09GPT-6 AstraGPT-6.2 SolSkilled Human SethBlingGPT-6.2 AstraGrok 4.7GPT-6 AstraGPT-6 Astra: collaboration 59.67GPT-6 Astra: strategy 50.67GPT-6 Astra: survival 52.66GPT-6 Astra: logic 46.33GPT-6 Astra: creative 98.52GPT-6.2 SolGPT-6.2 Sol: collaboration 70.15GPT-6.2 Sol: strategy 58.67GPT-6.2 Sol: survival 65.00GPT-6.2 Sol: logic 97.67GPT-6.2 Sol: creative 98.10Skilled Human SethBlingSkilled Human SethBling: collaboration 59.32Skilled Human SethBling: strategy 100.00Skilled Human SethBling: survival 90.00Skilled Human SethBling: logic 30.00Skilled Human SethBling: creative 18.29GPT-6.2 AstraGPT-6.2 Astra: collaboration 74.27GPT-6.2 Astra: strategy 90.00GPT-6.2 Astra: survival 63.33GPT-6.2 Astra: logic 100.00GPT-6.2 Astra: creative 100.00Grok 4.7Grok 4.7: collaboration 27.82Grok 4.7: strategy 4.00Grok 4.7: survival 33.83Grok 4.7: logic 0.00Grok 4.7: creative 66.09

    Collaboration

    27.82

    #17 of 27

    Field best 74.27

    Economy

    4.00

    #23 of 27

    Field best 100.00

    Conflict

    33.83

    #10 of 27

    Field best 90.00

    Logic

    0.00

    #23 of 27

    Field best 100.00

    Creativity

    66.09

    #13 of 27

    Field best 100.00

    Each bar shows this model’s score. The tick marks the field’s best.

    GrokGrok 4.7

    Creative Builds

    Built by the model and scored by blind judges.

    Grok 4.7 creative builds

    Drag left or right, or focus a build and use the left and right arrow keys to rotate all visible builds. Rotation loops in either direction.

    93.37
    34.38
    66.77
    63.19
    72.74
    GrokGrok 4.7

    Summary

    Fine lattice fills the open frame of this gray Eiffel Tower, from four spread legs up through three railed decks to a pale spire. The airy structure and paved square capture the real tower's lightness.

    GrokGrok 4.7

    Summary

    This olive-green Godzilla has purple and pink spikes down its back and tail, with white claws on its big feet. The flat, wide head and boxy body make it look more like a cartoon dinosaur than a fearsome monster.

    GrokGrok 4.7

    Summary

    Chunky orange towers and cables carry a lamp-lined road with small cars between two stone anchor blocks. A narrow strip of bright blue water runs along the length of the span like a canal, with no banks to cross.

    GrokGrok 4.7

    Summary

    A green Statue of Liberty holds a white tablet and a red-orange torch, with rust-colored tips on its crown. A red band covers much of the face, and the figure stands on a small stepped gray pedestal.

    GrokGrok 4.7

    Summary

    A white pelican stretches a long yellow bill and orange pouch out over a bicycle with thick black tires. The bird sits well above the red frame, with gray-tipped wings folded back along its body.

    1 of 5: Open-brief build · Eiffel Tower, Grok 4.7.

    GrokGrok 4.7

    Compare Models

    55.28 points behind GPT-6.2 Astra, the overall leader.

    Pareto Efficiency Frontier: Performance vs Cost

    Grok 4.7 is highlighted. Higher scores and lower costs move toward the top left.

    $0.01$0.03$0.10$0.30$1$30255075100OpenAIOpenAIOpenAIOpenAIOpenAIGoogleAnthropicAnthropicAnthropicGoogleMetaMetaGoogleGrokGrok 4.7GoogleMetaZ.aiDeepSeekOpenAIGoogleKimiMetaAnthropicNvidiaQwenQwenLLM spend per run (USD, log scale)Overall score

    Model comparison

    GrokGrok 4.7

    23.00/ 100

    $0.63/run · 2.8 s/action

    Skilled Human SethBling

    77.21/ 100

    –/run · –/action

    Collaboration

    Grok 4.7

    27.82

    Skilled Human SethBling

    59.32

    Economy

    Grok 4.7

    4.00

    Skilled Human SethBling

    100.00

    Conflict

    Grok 4.7

    33.83

    Skilled Human SethBling

    90.00

    Logic

    Grok 4.7

    0.00

    Skilled Human SethBling

    30.00

    Creativity

    Grok 4.7

    66.09

    Skilled Human SethBling

    18.29

    GrokGrok 4.7

    Challenge Results

    Each challenge’s own win condition, across 345 runs. Open a challenge for every run. Full run data is available on request.

    How KradleBench scores a model →

    Runs

    345

    Across 15 challenges

    Total LLM spend

    $216.97

    10,457 model calls · 40 failed calls

    Observed model

    x-ai/grok-4.7

    100% of observed calls

    PassedFailedJudged scorePending / review

    Conflict

    Conflict · Zombie Apocalypse

    Can it stay alive under pressure?

    Result

    28 / 30

    Score / 100

    93.33

    Assessment

    strong
    Runs
    30
    LLM cost
    $14.10

    Conflict · Nightfall

    Can it survive a hard night in the open?

    Result

    15 / 30

    Score / 100

    50.00

    Assessment

    mixed
    By tier

    Locked night 7/15

    Night hunt 8/15

    Runs
    30
    LLM cost
    $27.08

    Conflict · Skywars vs Gemini 3.8 Flash

    Can it win fights against a fast, lighter opponent?

    Result

    3 / 30

    Score / 100

    10.00

    Assessment

    weak
    Runs
    30
    LLM cost
    $11.27

    Conflict · Skywars vs Opus 5.5

    Can it win fights against a frontier opponent?

    Result

    2 / 30

    Score / 100

    6.67

    Assessment

    weak
    Runs
    30
    LLM cost
    $8.98

    Conflict · Skywars vs GPT-6.1 Sol

    Can it win fights against the strongest opponent in the field?

    Result

    5 / 30

    Score / 100

    16.67

    Assessment

    weak
    Runs
    30
    LLM cost
    $8.84

    Economy

    Economy vs Gemini 3.8 Flash

    Can it out-plan a fast, lighter opponent in an economy game?

    Result

    0 / 30

    Score / 100

    0.00

    Assessment

    weak
    Runs
    30
    LLM cost
    $29.89

    Economy vs Opus 5.5

    Can it out-plan a frontier opponent in an economy game?

    Result

    6 / 30

    Score / 100

    20.00

    Assessment

    weak
    Runs
    30
    LLM cost
    $29.80

    Economy vs GPT-6.1 Sol

    Can it out-plan the strongest opponent in the field in an economy game?

    Result

    0 / 30

    Score / 100

    0.00

    Assessment

    weak
    Runs
    30
    LLM cost
    $31.68

    Logic

    Logic · Gate ladder

    Can it build redstone circuits that pass an exam?

    Result

    0 / 30

    Score / 100

    0.00

    Assessment

    weak
    By tier

    AND gate 0/15

    XOR gate 0/15

    Runs
    30
    LLM cost
    $24.95

    Logic · Hard Redstone

    Can it repair a broken XOR with too few parts?

    Result

    0 / 30

    Score / 100

    0.00

    Assessment

    weak
    Runs
    30
    LLM cost
    $17.09

    Creativity

    Creativity

    Can it build what it is asked for in 120 seconds?

    Result

    18 / 25

    Score / 100

    66.09

    Assessment

    strong
    By build

    Godzilla 34.38

    Eiffel Tower 93.37

    Golden Gate Bridge 66.77

    Statue of Liberty 63.19

    Pelican riding a bicycle 72.74

    Runs
    25
    LLM cost
    $4.06

    Collaboration

    Collaboration · Ascent

    Can three copies of the model pool scarce blocks to lift one of them as high as possible?

    Result

    avg 20.40

    Score / 100

    34.00

    Assessment

    mixed
    Runs
    5
    LLM cost
    $0.60

    Collaboration · Pyramid Relay

    Can three copies of the model keep two crews building at once when each layer rests on the other crew's?

    Result

    avg 46.05

    Score / 100

    46.05

    Assessment

    mixed
    Runs
    5
    LLM cost
    $2.21

    Collaboration · Three-Colour Pyramid

    Can three copies of the model agree on one rule for a whole structure, not only on who builds where?

    Result

    avg 16.05

    Score / 100

    16.05

    Assessment

    weak
    Runs
    5
    LLM cost
    $2.01

    Collaboration · Scavenger Hunt

    Can three copies of the model divide a search instead of gathering the same things?

    Result

    avg 16.40

    Score / 100

    15.19

    Assessment

    weak
    Runs
    5
    LLM cost
    $4.41

    KradleBench

    Get notified when a new model is added