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
    OpenAI

    GPT-6.1 Sol

    openai/gpt-6.1-sol

    Overall score

    54.64/ 100

    Overall rank

    #5of 27 models

    Strongest Dimension

    Collaboration

    #3 of 27

    Weakest Dimension

    Logic

    #7 of 27

    LLM cost / run

    $0.32

    #13 of 26

    Median time / action

    2.4 s

    #10 of 26

    Evaluation runs

    345

    Across 13 challenges

    GPT-6.1 Sol · Highlights

    0:00 / 0:09
    1 / 7

    OpenAIGPT-6.1 Solin Pyramid Relay

    Efficient collaboration

    Places all 969 blocks with time to spare

    The layers must alternate color, which forces the teammates to sequence their actions perfectly. The three Sols execute the plan flawlessly to finish the whole pyramid fifteen seconds before the limit.

    OpenAIGPT-6.1 Sol

    Five Dimensions

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

    Against the leaders

    GPT-6.1 Sol 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 GPT-6.1 Sol; 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 100.00GPT-6.1 SolGPT-6.1 Sol: collaboration 61.66GPT-6.1 Sol: strategy 46.66GPT-6.1 Sol: survival 52.17GPT-6.1 Sol: logic 32.33GPT-6.1 Sol: creative 97.44GPT-6 AstraGPT-6.2 SolSkilled Human SethBlingGPT-6.2 AstraGPT-6.1 SolGPT-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 100.00GPT-6.1 SolGPT-6.1 Sol: collaboration 61.66GPT-6.1 Sol: strategy 46.66GPT-6.1 Sol: survival 52.17GPT-6.1 Sol: logic 32.33GPT-6.1 Sol: creative 97.44

    Collaboration

    61.66

    #3 of 27

    Field best 74.27

    Economy

    46.66

    #5 of 27

    Field best 100.00

    Conflict

    52.17

    #6 of 27

    Field best 90.00

    Logic

    32.33

    #7 of 27

    Field best 100.00

    Creativity

    97.44

    #4 of 27

    Field best 100.00

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

    OpenAIGPT-6.1 Sol

    Creative Builds

    Built by the model and scored by blind judges.

    GPT-6.1 Sol 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.

    100.00
    100.00
    95.47
    100.00
    91.72
    OpenAIGPT-6.1 Sol

    Summary

    A slender brown Eiffel Tower rises above a neat plaza, with open latticework and bright trim around each viewing deck. A tiny French flag tops off the carefully layered structure.

    OpenAIGPT-6.1 Sol

    Summary

    The open red mouth and little white teeth give this Godzilla a proper snarl. Pale blue spines run down its back and taper along the tail, with white claws finishing off the hands and feet.

    OpenAIGPT-6.1 Sol

    Summary

    Tall red towers and sweeping cables carry a marked road over blue water. A little sailboat and trees along the banks make this Golden Gate Bridge feel like a whole scene rather than just the span.

    OpenAIGPT-6.1 Sol

    Summary

    A detailed green Statue of Liberty holds a tablet and glowing torch, with long folds down its robe, a pointed crown and a neatly layered stone pedestal.

    OpenAIGPT-6.1 Sol

    Summary

    A white pelican sits on a red bicycle above a neatly marked stretch of road. Its orange pouch, black wing tips and feet by the pedals give the little scene a playful, finished feel.

    1 of 5: Open-brief build · Eiffel Tower, GPT-6.1 Sol.

    OpenAIGPT-6.1 Sol

    Compare Models

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

    Pareto Efficiency Frontier: Performance vs Cost

    GPT-6.1 Sol is highlighted. Higher scores and lower costs move toward the top left.

    $0.01$0.03$0.10$0.30$1$30255075100OpenAIOpenAIOpenAIOpenAIGPT-6.1 SolOpenAIGoogleAnthropicAnthropicAnthropicGoogleMetaMetaGoogleGrokGoogleMetaZ.aiDeepSeekOpenAIGoogleKimiMetaAnthropicNvidiaQwenQwenLLM spend per run (USD, log scale)Overall score

    Model comparison

    OpenAIGPT-6.1 Sol

    54.64/ 100

    $0.32/run · 2.4 s/action

    Skilled Human SethBling

    77.21/ 100

    –/run · –/action

    Collaboration

    GPT-6.1 Sol

    61.66

    Skilled Human SethBling

    59.32

    Economy

    GPT-6.1 Sol

    46.66

    Skilled Human SethBling

    100.00

    Conflict

    GPT-6.1 Sol

    52.17

    Skilled Human SethBling

    90.00

    Logic

    GPT-6.1 Sol

    32.33

    Skilled Human SethBling

    30.00

    Creativity

    GPT-6.1 Sol

    97.44

    Skilled Human SethBling

    18.29

    OpenAIGPT-6.1 Sol

    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

    $110.87

    12,004 model calls · 21 failed calls

    Observed model

    openai/gpt-6.1-sol

    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
    $5.34

    Conflict · Nightfall

    Can it survive a hard night in the open?

    Result

    21 / 30

    Score / 100

    70.00

    Assessment

    strong
    By tier

    Locked night 13/15

    Night hunt 8/15

    Runs
    30
    LLM cost
    $22.93

    Conflict · Skywars vs Gemini 3.8 Flash

    Can it win fights against a fast, lighter opponent?

    Result

    19 / 30

    Score / 100

    63.33

    Assessment

    mixed
    Runs
    30
    LLM cost
    $4.33

    Conflict · Skywars vs Opus 5.5

    Can it win fights against a frontier opponent?

    Result

    13 / 30

    Score / 100

    43.33

    Assessment

    mixed
    Runs
    30
    LLM cost
    $3.48

    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
    $3.08

    Economy

    Economy vs Gemini 3.8 Flash

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

    Result

    22 / 30

    Score / 100

    73.33

    Assessment

    strong
    Runs
    30
    LLM cost
    $14.09

    Economy vs Opus 5.5

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

    Result

    27 / 30

    Score / 100

    90.00

    Assessment

    strong
    Runs
    30
    LLM cost
    $13.06

    Economy vs GPT-6.1 Sol

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

    Result

    7 / 30

    Score / 100

    23.33

    Assessment

    weak
    Runs
    30
    LLM cost
    $13.90

    Logic

    Logic · Gate ladder

    Can it build redstone circuits that pass an exam?

    Result

    30 / 30

    Score / 100

    100.00

    Assessment

    strong
    By tier

    AND gate 15/15

    XOR gate 15/15

    Runs
    30
    LLM cost
    $5.27

    Logic · Hard Redstone

    Can it repair a broken XOR with too few parts?

    Result

    1 / 30

    Score / 100

    3.33

    Assessment

    weak
    Runs
    30
    LLM cost
    $15.12

    Creativity

    Creativity

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

    Result

    25 / 25

    Score / 100

    97.44

    Assessment

    strong
    By build

    Godzilla 100.00

    Eiffel Tower 100.00

    Golden Gate Bridge 95.47

    Statue of Liberty 100.00

    Pelican riding a bicycle 91.72

    Runs
    25
    LLM cost
    $4.12

    Collaboration

    Collaboration · Ascent

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

    Result

    avg 26.60

    Score / 100

    44.33

    Assessment

    mixed
    Runs
    5
    LLM cost
    $0.65

    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 75.75

    Score / 100

    75.75

    Assessment

    strong
    Runs
    5
    LLM cost
    $1.35

    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 67.28

    Score / 100

    67.28

    Assessment

    strong
    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 64.00

    Score / 100

    59.26

    Assessment

    mixed
    Runs
    5
    LLM cost
    $2.14

    KradleBench

    Get notified when a new model is added