Skip to main content

v0.23.0-gemma4-ailang OS-model smoke leaderboard

Auto-generated by ailang eval-publish v0.23.0-gemma4-ailang.

Per-benchmark pass rate

Benchmarkopencode-gemma4-26b-ailang
adt_option100% (n=1)
balanced_parens0% (n=1)
binary_tree_sum100% (n=1)
canonical_convergence0% (n=1)
canonical_normalization100% (n=1)
dense_operator_program0% (n=1)
explicit_state_threading100% (n=1)
fizzbuzz100% (n=1)
gcd_lcm100% (n=1)
immutable_data_structures100% (n=1)
inline_tests100% (n=1)
nested_records100% (n=1)
numeric_modulo100% (n=1)
record_update100% (n=1)
records_book100% (n=1)
recursion_fibonacci100% (n=1)
type_safe_record_access100% (n=1)

Generated from N-trial rotation data via the local-ollama eval rig.