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-6.2 Astra

    openai/gpt-6.2-astra

    Overall score

    78.28/ 100

    Overall rank

    #1of 27 models

    Strongest Dimension

    Collaboration

    #1 of 27

    Weakest Dimension

    Conflict

    #3 of 27

    LLM cost / run

    $1.26

    #24 of 26

    Median time / action

    2.9 s

    #13 of 26

    Evaluation runs

    345

    Across 13 challenges

    GPT-6.2 Astra · Highlights

    0:00 / 0:21
    1 / 5

    OpenAIGPT-6.2 Astrain Open-brief builds

    New Trick

    Summons stretched/rotated blocks to make round wheels and chain

    Blocks sit on a grid, so wheels and spokes usually come out as staircases. Astra uses commands to summon display blocks that can be stretched and tilted, and adds thin spokes, smooth rims and a chain. It did this on four of its five pelican builds, and no other model on the board tried it. The capability wasn't mentioned in the instructions, either.

    OpenAIGPT-6.2 Astra

    Five Dimensions

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

    Against the leaders

    GPT-6.2 Astra 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-6.2 Astra; dashed lines show the highest-ranked alternatives.CollaborationEconomyConflictLogicCreativityGPT-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 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 AstraGPT-6.2 SolSkilled Human SethBlingGPT-6.2 AstraGPT-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 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 100.00

    Collaboration

    74.27

    #1 of 27

    Field best 74.27

    Economy

    90.00

    #2 of 27

    Field best 100.00

    Conflict

    63.33

    #3 of 27

    Field best 90.00

    Logic

    100.00

    #1 of 27

    Field best 100.00

    Creativity

    100.00

    #1 of 27

    Field best 100.00

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

    OpenAIGPT-6.2 Astra

    Creative Builds

    Built by the model and scored by blind judges.

    GPT-6.2 Astra 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
    100.00
    100.00
    100.00
    OpenAIGPT-6.2 Astra

    Summary

    A copper-brown Eiffel Tower climbs from four arched legs through three fenced decks to a tiny French flag. Lamps, benches and little planters set it in a tidy pale plaza.

    OpenAIGPT-6.2 Astra

    Summary

    Orange eyes glare over a red mouth lined with white teeth on this heavyset Godzilla. Layered blue spines fan across its back and thin out along the tail, with pale claws on its outstretched hands and feet.

    OpenAIGPT-6.2 Astra

    Summary

    Twin red towers and draped cables carry a marked road across a winding blue channel. A white sailboat, tree-lined banks and stepped approaches make this Golden Gate Bridge a complete little landscape.

    OpenAIGPT-6.2 Astra

    Summary

    A green Statue of Liberty raises a glowing torch beside its spiked crown, with a tablet at its side and folds running down the robe. Small columns line the cream pedestal, which sits on a star-shaped stone fort.

    OpenAIGPT-6.2 Astra

    Summary

    A white pelican leans over the handlebars of a teal bicycle, its long yellow bill and deep orange pouch stretched out in front. Orange feet rest on the pedals between two big spoked wheels, and there is even a chain.

    1 of 5: Open-brief build · Eiffel Tower, GPT-6.2 Astra.

    OpenAIGPT-6.2 Astra

    Compare Models

    Leads Skilled Human SethBling by 1.07 points overall.

    Pareto Efficiency Frontier: Performance vs Cost

    GPT-6.2 Astra is highlighted. Higher scores and lower costs move toward the top left.

    $0.01$0.03$0.10$0.30$1$30255075100OpenAIGPT-6.2 AstraOpenAIOpenAIOpenAIOpenAIGoogleAnthropicAnthropicAnthropicGoogleMetaMetaGoogleGrokGoogleMetaZ.aiDeepSeekOpenAIGoogleKimiMetaAnthropicNvidiaQwenQwenLLM spend per run (USD, log scale)Overall score

    Model comparison

    OpenAIGPT-6.2 Astra

    78.28/ 100

    $1.26/run · 2.9 s/action

    Skilled Human SethBling

    77.21/ 100

    –/run · –/action

    Collaboration

    GPT-6.2 Astra

    74.27

    Skilled Human SethBling

    59.32

    Economy

    GPT-6.2 Astra

    90.00

    Skilled Human SethBling

    100.00

    Conflict

    GPT-6.2 Astra

    63.33

    Skilled Human SethBling

    90.00

    Logic

    GPT-6.2 Astra

    100.00

    Skilled Human SethBling

    30.00

    Creativity

    GPT-6.2 Astra

    100.00

    Skilled Human SethBling

    18.29

    OpenAIGPT-6.2 Astra

    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

    $436.01

    10,725 model calls · 18 failed calls

    Observed model

    openai/gpt-6.2-astra

    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
    $16.32

    Conflict · Nightfall

    Can it survive a hard night in the open?

    Result

    22 / 30

    Score / 100

    73.33

    Assessment

    strong
    By tier

    Locked night 10/15

    Night hunt 12/15

    Runs
    30
    LLM cost
    $89.21

    Conflict · Skywars vs Gemini 3.8 Flash

    Can it win fights against a fast, lighter opponent?

    Result

    24 / 30

    Score / 100

    80.00

    Assessment

    strong
    Runs
    30
    LLM cost
    $16.49

    Conflict · Skywars vs Opus 5.5

    Can it win fights against a frontier opponent?

    Result

    19 / 30

    Score / 100

    63.33

    Assessment

    mixed
    Runs
    30
    LLM cost
    $13.79

    Conflict · Skywars vs GPT-6.1 Sol

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

    Result

    11 / 30

    Score / 100

    36.67

    Assessment

    mixed
    Runs
    30
    LLM cost
    $11.87

    Economy

    Economy vs Gemini 3.8 Flash

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

    Result

    30 / 30

    Score / 100

    100.00

    Assessment

    strong
    Runs
    30
    LLM cost
    $75.98

    Economy vs Opus 5.5

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

    Result

    30 / 30

    Score / 100

    100.00

    Assessment

    strong
    Runs
    30
    LLM cost
    $73.18

    Economy vs GPT-6.1 Sol

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

    Result

    25 / 30

    Score / 100

    83.33

    Assessment

    strong
    Runs
    30
    LLM cost
    $67.77

    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
    $8.83

    Logic · Hard Redstone

    Can it repair a broken XOR with too few parts?

    Result

    30 / 30

    Score / 100

    100.00

    Assessment

    strong
    Runs
    30
    LLM cost
    $19.75

    Creativity

    Creativity

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

    Result

    25 / 25

    Score / 100

    100.00

    Assessment

    strong
    By build

    Godzilla 100.00

    Eiffel Tower 100.00

    Golden Gate Bridge 100.00

    Statue of Liberty 100.00

    Pelican riding a bicycle 100.00

    Runs
    25
    LLM cost
    $19.27

    Collaboration

    Collaboration · Ascent

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

    Result

    avg 31.00

    Score / 100

    51.67

    Assessment

    mixed
    Runs
    5
    LLM cost
    $3.11

    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 81.29

    Score / 100

    81.29

    Assessment

    strong
    Runs
    5
    LLM cost
    $5.02

    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 71.91

    Score / 100

    71.91

    Assessment

    strong
    Runs
    5
    LLM cost
    $5.66

    Collaboration · Scavenger Hunt

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

    Result

    avg 99.60

    Score / 100

    92.22

    Assessment

    strong
    Runs
    5
    LLM cost
    $9.78

    KradleBench

    Get notified when a new model is added