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 Sol

    openai/gpt-6.2-sol

    Overall score

    67.93/ 100

    Overall rank

    #3of 27 models

    Strongest Dimension

    Collaboration

    #2 of 27

    Weakest Dimension

    Creativity

    #3 of 27

    LLM cost / run

    $0.35

    #14 of 26

    Median time / action

    2.0 s

    #6 of 26

    Evaluation runs

    345

    Across 13 challenges

    GPT-6.2 Sol · Highlights

    0:00 / 0:19
    1 / 6

    OpenAIGPT-6.2 Solin Ascent

    Teamwork

    A shared staircase carries the team to 42

    Sol's team builds a staircase so the two donors can walk up beside the climber and hand over dirt at height. They reclaim dirt from under the stairs for more hand-offs, and the climber finishes at 42, the highest tower on the board.

    OpenAIGPT-6.2 Sol

    Five Dimensions

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

    Against the leaders

    GPT-6.2 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-6.2 Sol; 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 98.52Skilled 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-6.2 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 98.10GPT-6.1 SolGPT-6 AstraSkilled Human SethBlingGPT-6.2 AstraGPT-6.2 SolGPT-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 98.52Skilled 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-6.2 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 98.10

    Collaboration

    70.15

    #2 of 27

    Field best 74.27

    Economy

    58.67

    #3 of 27

    Field best 100.00

    Conflict

    65.00

    #2 of 27

    Field best 90.00

    Logic

    97.67

    #2 of 27

    Field best 100.00

    Creativity

    98.10

    #3 of 27

    Field best 100.00

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

    OpenAIGPT-6.2 Sol

    Creative Builds

    Built by the model and scored by blind judges.

    GPT-6.2 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.

    92.20
    100.00
    100.00
    100.00
    98.29
    OpenAIGPT-6.2 Sol

    Summary

    Patches of green weather the copper frame of this Eiffel Tower, which rises from four arched legs past fenced decks to a thin antenna. Garden beds and lamps turn the paved base into a small park.

    OpenAIGPT-6.2 Sol

    Summary

    A hulking black Godzilla opens a red mouth full of white teeth beneath small orange eyes. Turquoise and purple spines run from its neck to the tip of the tail, with white claws on every hand and foot.

    OpenAIGPT-6.2 Sol

    Summary

    Red cables swoop between two capped towers above a road dotted with yellow lines. Rocky banks with little trees anchor each end, and a small sailboat drifts on the water below.

    OpenAIGPT-6.2 Sol

    Summary

    This green Statue of Liberty lifts a glowing torch high above its spiked crown, with deep folds in the robe and a tablet held at its side. A gray stone pedestal with small windows steps down to a broad base.

    OpenAIGPT-6.2 Sol

    Summary

    A plump white pelican with a big yellow bill and orange pouch perches on a teal bicycle. Orange legs reach down to the pedals between two chunky black wheels with pale rims.

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

    OpenAIGPT-6.2 Sol

    Compare Models

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

    Pareto Efficiency Frontier: Performance vs Cost

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

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

    Model comparison

    OpenAIGPT-6.2 Sol

    67.93/ 100

    $0.35/run · 2.0 s/action

    Skilled Human SethBling

    77.21/ 100

    –/run · –/action

    Collaboration

    GPT-6.2 Sol

    70.15

    Skilled Human SethBling

    59.32

    Economy

    GPT-6.2 Sol

    58.67

    Skilled Human SethBling

    100.00

    Conflict

    GPT-6.2 Sol

    65.00

    Skilled Human SethBling

    90.00

    Logic

    GPT-6.2 Sol

    97.67

    Skilled Human SethBling

    30.00

    Creativity

    GPT-6.2 Sol

    98.10

    Skilled Human SethBling

    18.29

    OpenAIGPT-6.2 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

    $119.72

    12,253 model calls · 8 failed calls

    Observed model

    openai/gpt-6.2-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
    $4.99

    Conflict · Nightfall

    Can it survive a hard night in the open?

    Result

    20 / 30

    Score / 100

    66.67

    Assessment

    mixed
    By tier

    Locked night 9/15

    Night hunt 11/15

    Runs
    30
    LLM cost
    $21.87

    Conflict · Skywars vs Gemini 3.8 Flash

    Can it win fights against a fast, lighter opponent?

    Result

    21 / 30

    Score / 100

    70.00

    Assessment

    strong
    Runs
    30
    LLM cost
    $5.41

    Conflict · Skywars vs Opus 5.5

    Can it win fights against a frontier opponent?

    Result

    24 / 30

    Score / 100

    80.00

    Assessment

    strong
    Runs
    30
    LLM cost
    $5.07

    Conflict · Skywars vs GPT-6.1 Sol

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

    Result

    15 / 30

    Score / 100

    50.00

    Assessment

    mixed
    Runs
    30
    LLM cost
    $4.83

    Economy

    Economy vs Gemini 3.8 Flash

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

    Result

    29 / 30

    Score / 100

    96.67

    Assessment

    strong
    Runs
    30
    LLM cost
    $17.23

    Economy vs Opus 5.5

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

    Result

    29 / 30

    Score / 100

    96.67

    Assessment

    strong
    Runs
    30
    LLM cost
    $17.46

    Economy vs GPT-6.1 Sol

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

    Result

    10 / 30

    Score / 100

    33.33

    Assessment

    mixed
    Runs
    30
    LLM cost
    $17.86

    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
    $3.88

    Logic · Hard Redstone

    Can it repair a broken XOR with too few parts?

    Result

    29 / 30

    Score / 100

    96.67

    Assessment

    strong
    Runs
    30
    LLM cost
    $9.61

    Creativity

    Creativity

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

    Result

    25 / 25

    Score / 100

    98.10

    Assessment

    strong
    By build

    Godzilla 100.00

    Eiffel Tower 92.20

    Golden Gate Bridge 100.00

    Statue of Liberty 100.00

    Pelican riding a bicycle 98.29

    Runs
    25
    LLM cost
    $5.09

    Collaboration

    Collaboration · Ascent

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

    Result

    avg 34.40

    Score / 100

    57.33

    Assessment

    mixed
    Runs
    5
    LLM cost
    $0.79

    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 76.97

    Score / 100

    76.97

    Assessment

    strong
    Runs
    5
    LLM cost
    $1.16

    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 73.14

    Score / 100

    73.14

    Assessment

    strong
    Runs
    5
    LLM cost
    $1.58

    Collaboration · Scavenger Hunt

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

    Result

    avg 79.00

    Score / 100

    73.15

    Assessment

    strong
    Runs
    5
    LLM cost
    $2.87

    KradleBench

    Get notified when a new model is added