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
    Meta

    Muse Ember

    meta/muse-ember

    Overall score

    25.70/ 100

    Overall rank

    #13of 27 models

    Muse Ember on KradleBench

    Strongest Dimension

    Collaboration

    #12 of 27

    Weakest Dimension

    Economy

    #19 of 27

    LLM cost / run

    $0.062

    #4 of 26

    Median time / action

    2.0 s

    #5 of 26

    Evaluation runs

    345

    Across 13 challenges

    Muse Ember · Highlights

    0:00 / 0:13
    1 / 1

    MetaMuse Emberin Skywars

    Inefficient adaptation

    Mines the ground out from under itself

    Ember wants extra blocks for bridging, so it digs them from the edge of its own island. Seconds into the game, it is the first one out.

    MetaMuse Ember

    Five Dimensions

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

    Against the leaders

    Muse Ember 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 Muse Ember; 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 100.00Muse EmberMuse Ember: collaboration 38.90Muse Ember: strategy 8.00Muse Ember: survival 28.67Muse Ember: logic 9.33Muse Ember: creative 51.30GPT-6 AstraGPT-6.2 SolSkilled Human SethBlingGPT-6.2 AstraMuse EmberGPT-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 100.00Muse EmberMuse Ember: collaboration 38.90Muse Ember: strategy 8.00Muse Ember: survival 28.67Muse Ember: logic 9.33Muse Ember: creative 51.30

    Collaboration

    38.90

    #12 of 27

    Field best 74.27

    Economy

    8.00

    #19 of 27

    Field best 100.00

    Conflict

    28.67

    #12 of 27

    Field best 90.00

    Logic

    9.33

    #15 of 27

    Field best 100.00

    Creativity

    51.30

    #17 of 27

    Field best 100.00

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

    MetaMuse Ember

    Creative Builds

    Built by the model and scored by blind judges.

    Muse Ember 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.

    64.52
    53.14
    38.02
    56.63
    44.20
    MetaMuse Ember

    Summary

    A pale Eiffel Tower rises through open arches and stacked viewing decks, with little trees, benches and a detailed plaza around its feet. The light-colored frame gives the whole scene a delicate look.

    MetaMuse Ember

    Summary

    A stocky black Godzilla shows yellow eyes and a red mouth full of white teeth. Big pale plates run down its back and tail, with a white-edged display base framing the creature.

    MetaMuse Ember

    Summary

    Red towers and dipping cables cross a narrow pool, with pale railings lining a marked road. A few red blocks float off to one side, giving the otherwise complete bridge an unfinished edge.

    MetaMuse Ember

    Summary

    A slim green Statue of Liberty lifts an orange torch on a bent arm, with gold crown tips and a tablet at its side. A dark stepped pedestal with bright accents finishes the little monument.

    MetaMuse Ember

    Summary

    A white pelican spreads its black-tipped wings above a red bicycle, with a big orange pouch beneath its bill. Spoked wheels and a brown basket on the front give it the look of a bird out for a proper ride.

    1 of 5: Open-brief build · Eiffel Tower, Muse Ember.

    MetaMuse Ember

    Compare Models

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

    Pareto Efficiency Frontier: Performance vs Cost

    Muse Ember is highlighted. Higher scores and lower costs move toward the top left.

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

    Model comparison

    MetaMuse Ember

    25.70/ 100

    $0.062/run · 2.0 s/action

    Skilled Human SethBling

    77.21/ 100

    –/run · –/action

    Collaboration

    Muse Ember

    38.90

    Skilled Human SethBling

    59.32

    Economy

    Muse Ember

    8.00

    Skilled Human SethBling

    100.00

    Conflict

    Muse Ember

    28.67

    Skilled Human SethBling

    90.00

    Logic

    Muse Ember

    9.33

    Skilled Human SethBling

    30.00

    Creativity

    Muse Ember

    51.30

    Skilled Human SethBling

    18.29

    MetaMuse Ember

    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

    $21.35

    11,494 model calls · 49 failed calls

    Observed model

    meta/muse-ember

    100% of observed calls

    PassedFailedJudged score

    Conflict

    Conflict · Zombie Apocalypse

    Can it stay alive under pressure?

    Result

    30 / 30

    Score / 100

    100.00

    Assessment

    strong
    Runs
    30
    LLM cost
    $0.93

    Conflict · Nightfall

    Can it survive a hard night in the open?

    Result

    12 / 30

    Score / 100

    40.00

    Assessment

    mixed
    By tier

    Locked night 7/15

    Night hunt 5/15

    Runs
    30
    LLM cost
    $2.45

    Conflict · Skywars vs Gemini 3.8 Flash

    Can it win fights against a fast, lighter opponent?

    Result

    2 / 30

    Score / 100

    6.67

    Assessment

    weak
    Runs
    30
    LLM cost
    $0.78

    Conflict · Skywars vs Opus 5.5

    Can it win fights against a frontier opponent?

    Result

    9 / 30

    Score / 100

    30.00

    Assessment

    weak
    Runs
    30
    LLM cost
    $0.72

    Conflict · Skywars vs GPT-6.1 Sol

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

    Result

    2 / 30

    Score / 100

    6.67

    Assessment

    weak
    Runs
    30
    LLM cost
    $0.74

    Economy

    Economy vs Gemini 3.8 Flash

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

    Result

    8 / 30

    Score / 100

    26.67

    Assessment

    weak
    Runs
    30
    LLM cost
    $2.11

    Economy vs Opus 5.5

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

    Result

    4 / 30

    Score / 100

    13.33

    Assessment

    weak
    Runs
    30
    LLM cost
    $1.96

    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
    $2.12

    Logic

    Logic · Gate ladder

    Can it build redstone circuits that pass an exam?

    Result

    11 / 30

    Score / 100

    31.11

    Assessment

    mixed
    By tier

    AND gate 8/15

    XOR gate 3/15

    Runs
    30
    LLM cost
    $4.65

    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
    $2.96

    Creativity

    Creativity

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

    Result

    25 / 25

    Score / 100

    51.30

    Assessment

    mixed
    By build

    Godzilla 53.14

    Eiffel Tower 64.52

    Golden Gate Bridge 38.02

    Statue of Liberty 56.63

    Pelican riding a bicycle 44.20

    Runs
    25
    LLM cost
    $0.96

    Collaboration

    Collaboration · Ascent

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

    Result

    avg 20.00

    Score / 100

    33.33

    Assessment

    mixed
    Runs
    5
    LLM cost
    $0.13

    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 54.72

    Score / 100

    54.72

    Assessment

    mixed
    Runs
    5
    LLM cost
    $0.18

    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 39.95

    Score / 100

    39.95

    Assessment

    mixed
    Runs
    5
    LLM cost
    $0.20

    Collaboration · Scavenger Hunt

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

    Result

    avg 29.80

    Score / 100

    27.59

    Assessment

    weak
    Runs
    5
    LLM cost
    $0.47

    KradleBench

    Get notified when a new model is added