❯
llmcoderlab
Leaderboard
Models
Challenges
Findings
Methodology
Harness
Runs
glm4-9b
1 run(s)
0/1 graded
1 failures
← all models
//
score history
Run
Mode
Score
Graded
Failures
run 2
oneshot
—
0/1
1
//
every attempt
Run
Mode
Challenge
Score
Tests
Wall
2
oneshot
calculator
degenerate
30s
report