unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS

Observed from session logs: unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS

run Qwen3.8-Flash-Next-UD-IQ3_XXS · requested model default · generated 2026-11-13T07:42:09+00:00 · 78 challenges

51passed
27failed
0error
88.8%avg tests
378.85 / 744.00final score
50.9%of max
3.6Mcontext tokens
46.0kavg tokens/task
11compactions
passed
AD100-ALG-02
Dijkstra shortest paths
2/2 drivers
100.0%
100.0%
3
3.00
5897
41.6s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillaralgorithmic
  • Languagecpp
  • Difficultyeasy
  • Weight3
  • Tagsgraphs, dijkstra, priority-queue
  • Exit code0
  • Timed outFalse
  • Context tokens5,897
  • LLM calls10
  • Tool calls9
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

failed
AD100-ALG-03
JSON parser from scratch
1/43
2.3%
0.0%
3
0.00
11.8k
90.7s
PI_EXIT

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillaralgorithmic
  • Languagepython
  • Difficultyeasy
  • Weight3
  • Tagsparsing, recursive-descent, unicode
  • Exit code0
  • Timed outFalse
  • Context tokens11,763
  • LLM calls3
  • Tool calls2
  • Compactions0

Failed tests

  • test_number_forms
  • test_string_escapes
  • test_raw_utf8_passthrough
  • test_nested_and_mixed
  • test_duplicate_keys_last_wins
  • test_deep_nesting
  • test_top_level_edge_documents
  • test_invalid_documents_raise_value_error[]
  • test_invalid_documents_raise_value_error[ ]
  • test_invalid_documents_raise_value_error[tru]
  • test_invalid_documents_raise_value_error[nul]
  • test_invalid_documents_raise_value_error[fals]
  • test_invalid_documents_raise_value_error[TRUE]
  • test_invalid_documents_raise_value_error[1 2]
  • test_invalid_documents_raise_value_error[{} {}]
  • test_invalid_documents_raise_value_error[[1,]]
  • test_invalid_documents_raise_value_error[{"a": 1,}]
  • test_invalid_documents_raise_value_error[['a']]
  • test_invalid_documents_raise_value_error[{a: 1}]
  • test_invalid_documents_raise_value_error[{"a" 1}]
  • test_invalid_documents_raise_value_error[{"a": }]
  • test_invalid_documents_raise_value_error[[1 2]]
  • test_invalid_documents_raise_value_error[[1,]
  • test_invalid_documents_raise_value_error[{"a":]
  • test_invalid_documents_raise_value_error["unterminated]
  • test_invalid_documents_raise_value_error["\\q"]
  • test_invalid_documents_raise_value_error["\\u12"]
  • test_invalid_documents_raise_value_error["\\uZZZZ"]
  • test_invalid_documents_raise_value_error[NaN]
  • test_invalid_documents_raise_value_error[Infinity]
  • test_invalid_documents_raise_value_error[-Infinity]
  • test_invalid_documents_raise_value_error[+1]
  • test_invalid_documents_raise_value_error[01]
  • test_invalid_documents_raise_value_error[00]
  • test_invalid_documents_raise_value_error[.5]
  • test_invalid_documents_raise_value_error[1.]
  • test_invalid_documents_raise_value_error[1e]
  • test_invalid_documents_raise_value_error[-]
  • test_invalid_documents_raise_value_error[{,}]
  • test_invalid_documents_raise_value_error[{"a": 1}x]
  • test_error_does_not_silently_succeed_on_partial_parse
  • test_source_is_a_real_parser
passed
AD100-ALG-16
RFC-4180 CSV parser from scratch
6/6
100.0%
100.0%
3.5
3.50
18.4k
147.7s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillaralgorithmic
  • Languagepython
  • Difficultyeasy
  • Weight3.5
  • Tagsparsing, csv, purity
  • Exit code0
  • Timed outFalse
  • Context tokens18,381
  • LLM calls17
  • Tool calls18
  • Compactions0
passed
AD100-ALG-19
S-expression reader/writer
4/4
100.0%
100.0%
3.5
3.50
11.3k
99.7s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillaralgorithmic
  • Languagepython
  • Difficultyeasy
  • Weight3.5
  • Tagsparsing, s-expression, recursion-limit
  • Exit code0
  • Timed outFalse
  • Context tokens11,311
  • LLM calls10
  • Tool calls9
  • Compactions0
passed
AD100-ALG-20
word ladder shortest chain
4/4
100.0%
100.0%
3
3.00
6619
53.8s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillaralgorithmic
  • Languagepython
  • Difficultyeasy
  • Weight3
  • Tagsgraph, bfs, lexicographic
  • Exit code0
  • Timed outFalse
  • Context tokens6,619
  • LLM calls8
  • Tool calls7
  • Compactions0
passed
AD100-ALG-22
strongly connected components (Tarjan)
3/3 drivers
100.0%
100.0%
3
3.00
20.1k
311.1s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillaralgorithmic
  • Languagecpp
  • Difficultyeasy
  • Weight3
  • Tagsgraph, scc, tarjan
  • Exit code0
  • Timed outFalse
  • Context tokens20,068
  • LLM calls27
  • Tool calls27
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

passed
AD100-ALG-23
segment tree: point update + range sum
3/3 drivers
100.0%
100.0%
3
3.00
5068
28.7s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillaralgorithmic
  • Languagecpp
  • Difficultyeasy
  • Weight3
  • Tagsdata-structure, segment-tree
  • Exit code0
  • Timed outFalse
  • Context tokens5,068
  • LLM calls7
  • Tool calls8
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

passed
AD100-ALG-26
sparse table RMQ
4/4 drivers
100.0%
100.0%
3
3.00
5657
41.7s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillaralgorithmic
  • Languagecpp
  • Difficultyeasy
  • Weight3
  • Tagsdata-structure, rmq, sparse-table
  • Exit code0
  • Timed outFalse
  • Context tokens5,657
  • LLM calls8
  • Tool calls9
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

passed
AD100-ALG-27
convex hull (monotone chain)
4/4 drivers
100.0%
100.0%
3
3.00
32.6k
290.0s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillaralgorithmic
  • Languagecpp
  • Difficultyeasy
  • Weight3
  • Tagsgeometry, convex-hull
  • Exit code0
  • Timed outFalse
  • Context tokens32,599
  • LLM calls36
  • Tool calls35
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

passed
AD100-ALG-28
min-cost max-flow
3/3 drivers
100.0%
100.0%
3
3.00
25.5k
481.3s
DEADLINE

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillaralgorithmic
  • Languagecpp
  • Difficultyeasy
  • Weight3
  • Tagsflow, min-cost-flow, optimization
  • Exit code0
  • Timed outFalse
  • Context tokens25,549
  • LLM calls14
  • Tool calls15
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

passed
AD100-ALG-29
glob matcher (*, ?, classes)
5/5
100.0%
100.0%
6
6.00
17.3k
163.8s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillaralgorithmic
  • Languagepython
  • Difficultyeasy
  • Weight6
  • Tagspattern-matching, backtracking
  • Exit code0
  • Timed outFalse
  • Context tokens17,269
  • LLM calls9
  • Tool calls10
  • Compactions0
passed
AD100-ALG-30
matrix-chain multiplication
5/5
100.0%
100.0%
3
3.00
18.6k
157.8s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillaralgorithmic
  • Languagepython
  • Difficultyeasy
  • Weight3
  • Tagsdp, parenthesization
  • Exit code0
  • Timed outFalse
  • Context tokens18,572
  • LLM calls21
  • Tool calls20
  • Compactions0
passed
AD100-ALG-31
Huffman coding round-trip
6/6
100.0%
100.0%
3
3.00
13.0k
105.7s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillaralgorithmic
  • Languagepython
  • Difficultyeasy
  • Weight3
  • Tagshuffman, compression, round-trip
  • Exit code0
  • Timed outFalse
  • Context tokens13,040
  • LLM calls11
  • Tool calls11
  • Compactions0
passed
AD100-ALG-33
big-decimal arithmetic (strings)
4/4 drivers
100.0%
100.0%
3.5
3.50
31.6k
155.8s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillaralgorithmic
  • Languagecpp
  • Difficultyeasy
  • Weight3.5
  • Tagsbignum, arithmetic, strings
  • Exit code0
  • Timed outFalse
  • Context tokens31,595
  • LLM calls18
  • Tool calls18
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

passed
AD100-ALG-34
treap: k-th order statistics
4/4 drivers
100.0%
100.0%
4.5
4.50
13.4k
481.4s
DEADLINE

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillaralgorithmic
  • Languagecpp
  • Difficultyeasy
  • Weight4.5
  • Tagstreap, order-statistics, balanced-bst
  • Exit code0
  • Timed outFalse
  • Context tokens13,438
  • LLM calls9
  • Tool calls9
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

passed
AD100-ALG-35
persistent segment tree (versions + k-th)
4/4 drivers
100.0%
100.0%
3
3.00
14.1k
99.7s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillaralgorithmic
  • Languagecpp
  • Difficultyeasy
  • Weight3
  • Tagspersistent-segment-tree, functional-data-structure, versions
  • Exit code0
  • Timed outFalse
  • Context tokens14,072
  • LLM calls17
  • Tool calls16
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

passed
AD100-DBG-11
API contract: exception + aliasing
16/16
100.0%
100.0%
3
3.00
6142
38.6s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillardebugging
  • Languagepython
  • Difficultyeasy
  • Weight3
  • Tagsapi-contract, exception-type, aliasing, defensive-copy
  • Exit code0
  • Timed outFalse
  • Context tokens6,142
  • LLM calls7
  • Tool calls7
  • Compactions0
passed
AD100-DBG-12
int overflow in size arithmetic
4/4 drivers
100.0%
100.0%
3.5
3.50
4810
29.6s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillardebugging
  • Languagecpp
  • Difficultyeasy
  • Weight3.5
  • Tagsinteger-overflow, size-arithmetic, validation
  • Exit code0
  • Timed outFalse
  • Context tokens4,810
  • LLM calls7
  • Tool calls7
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

passed
AD100-DBG-13
size_t underflow on singleton/empty
4/4 drivers
100.0%
100.0%
7.5
7.50
6387
47.6s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillardebugging
  • Languagecpp
  • Difficultymedium
  • Weight7.5
  • Tagssize-t, underflow, empty-singleton
  • Exit code0
  • Timed outFalse
  • Context tokens6,387
  • LLM calls11
  • Tool calls11
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

passed
AD100-DBG-15
hash-order nondeterminism
12/12
100.0%
100.0%
3
3.00
3202
25.6s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillardebugging
  • Languagepython
  • Difficultyeasy
  • Weight3
  • Tagshash-order, determinism, nondeterminism, sorting
  • Exit code0
  • Timed outFalse
  • Context tokens3,202
  • LLM calls6
  • Tool calls6
  • Compactions0
passed
AD100-DBG-17
wrong exception type on error path
4/4 drivers
100.0%
100.0%
4.5
4.50
9373
69.7s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillardebugging
  • Languagecpp
  • Difficultyeasy
  • Weight4.5
  • Tagsexception-contract, parsing, error-path
  • Exit code0
  • Timed outFalse
  • Context tokens9,373
  • LLM calls9
  • Tool calls8
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

passed
AD100-DBG-19
multiple interacting bug classes
19/19
100.0%
100.0%
3
3.00
12.7k
117.8s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillardebugging
  • Languagepython
  • Difficultyeasy
  • Weight3
  • Tagsmulti-bug, mutable-default, off-by-one, exception-contract, aliasing
  • Exit code0
  • Timed outFalse
  • Context tokens12,661
  • LLM calls12
  • Tool calls12
  • Compactions0
passed
AD100-DBG-20
path traversal + expression injection
50/50
100.0%
100.0%
3
3.00
18.0k
129.8s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillardebugging
  • Languagepython
  • Difficultyeasy
  • Weight3
  • Tagssecurity, path-traversal, injection, input-validation
  • Exit code0
  • Timed outFalse
  • Context tokens18,006
  • LLM calls24
  • Tool calls24
  • Compactions0
passed
AD100-DBG-21
unseeded RNG / wall-clock dependence
19/19
100.0%
100.0%
3
3.00
5239
41.6s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillardebugging
  • Languagepython
  • Difficultyeasy
  • Weight3
  • Tagsdeterminism, rng, wall-clock, reproducibility
  • Exit code0
  • Timed outFalse
  • Context tokens5,239
  • LLM calls8
  • Tool calls7
  • Compactions0
failed
AD100-DBG-23
erase-while-iterating + related bugs
0/4 drivers
0.0%
0.0%
3
0.00
7223
51.6s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillardebugging
  • Languagecpp
  • Difficultyeasy
  • Weight3
  • Tagserase-while-iterating, vector, iterator, off-by-one
  • Exit code0
  • Timed outFalse
  • Context tokens7,223
  • LLM calls8
  • Tool calls8
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

Failed tests

  • test_bugs
  • test_bugs_public
  • test_listops
  • test_regression
failed
AD100-DBG-26
snapshot restore service
22/24
91.7%
35.0%
15.5
5.42
67.7k
721.8s
DEADLINE

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillardebugging
  • Languagepython
  • Difficultyhard
  • Weight15.5
  • Tagssecurity-review, cve-derived, filesystem, symlinks, transactional
  • Exit code0
  • Timed outFalse
  • Context tokens67,692
  • LLM calls50
  • Tool calls59
  • Compactions0

Failed tests

  • test_security_parent_after_symlink[bridge/../secret]
  • test_security_parent_after_symlink[/r/bridge/../secret]
failed
AD100-DBG-27
verified block ingestion
43/44
97.7%
65.0%
10
6.50
44.1k
388.5s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillardebugging
  • Languagepython
  • Difficultyhard
  • Weight10
  • Tagssecurity-review, cve-derived, integrity, streaming, short-reads
  • Exit code0
  • Timed outFalse
  • Context tokens44,128
  • LLM calls41
  • Tool calls50
  • Compactions0

Failed tests

  • test_regression_independent_empty_block
passed
AD100-DBG-28
indexed document reader
26/26
100.0%
100.0%
3
3.00
35.0k
432.1s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillardebugging
  • Languagepython
  • Difficultyeasy
  • Weight3
  • Tagssecurity-review, cve-derived, parser, progress, random-access
  • Exit code0
  • Timed outFalse
  • Context tokens34,967
  • LLM calls22
  • Tool calls21
  • Compactions0
failed
AD100-DBG-31
stylesheet inspection pipeline
26/33
78.8%
35.0%
22.5
7.87
8473
45.6s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillardebugging
  • Languagepython
  • Difficultyexpert
  • Weight22.5
  • Tagssecurity-review, cve-derived, tokenizer, escaping, parser-differential
  • Exit code0
  • Timed outFalse
  • Context tokens8,473
  • LLM calls8
  • Tool calls13
  • Compactions0

Failed tests

  • test_security_even_backslashes_terminate[2]
  • test_security_even_backslashes_terminate[4]
  • test_security_even_backslashes_terminate[6]
  • test_security_even_backslashes_terminate[8]
  • test_security_hidden_declaration_not_consumed[2]
  • test_security_hidden_declaration_not_consumed[4]
  • test_security_hidden_declaration_not_consumed[6]
failed
AD100-DBG-33
multipart metadata processing
17/19
89.5%
35.0%
13
4.55
59.6k
610.4s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillardebugging
  • Languagepython
  • Difficultymedium
  • Weight13
  • Tagssecurity-review, cve-derived, regex, complexity, multipart
  • Exit code0
  • Timed outFalse
  • Context tokens59,650
  • LLM calls48
  • Tool calls47
  • Compactions0

Failed tests

  • test_security_long_unassigned_parameter
  • test_security_large_malformed_then_valid
passed
AD100-DBG-34
URL text and form gateway
29/29
100.0%
100.0%
6
6.00
80.3k
660.4s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillardebugging
  • Languagepython
  • Difficultymedium
  • Weight6
  • Tagssecurity-review, cve-derived, percent-encoding, utf8, complexity
  • Exit code0
  • Timed outFalse
  • Context tokens80,288
  • LLM calls48
  • Tool calls51
  • Compactions0
passed
AD100-DBG-35
schema identifier registry
24/24
100.0%
100.0%
10.5
10.50
117.7k
721.5s
DEADLINE

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillardebugging
  • Languagepython
  • Difficultymedium
  • Weight10.5
  • Tagssecurity-review, cve-derived, asn1, canonicalization, integer-bounds
  • Exit code0
  • Timed outFalse
  • Context tokens117,675
  • LLM calls64
  • Tool calls64
  • Compactions1
passed
AD100-DBG-36
Walk or drive to the car wash
1/1
100.0%
100.0%
4
4.00
4003
31.7s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillardebugging
  • Languagepython
  • Difficultyeasy
  • Weight4
  • Tagsreasoning, deliverable, file-io, single-word-answer
  • Exit code0
  • Timed outFalse
  • Context tokens4,003
  • LLM calls7
  • Tool calls6
  • Compactions0
passed
AD100-DBG-37
Which is larger, 9.11 or 9.9?
1/1
100.0%
100.0%
3
3.00
2696
8.6s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillardebugging
  • Languagepython
  • Difficultyeasy
  • Weight3
  • Tagsreasoning, numeric-literals, deliverable, file-io
  • Exit code0
  • Timed outFalse
  • Context tokens2,696
  • LLM calls4
  • Tool calls3
  • Compactions0
passed
AD100-OPT-17
quicksort worst-case pivot
2/2 drivers
100.0%
100.0%
3
3.00
11.3k
83.7s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillaroptimization
  • Languagecpp
  • Difficultyeasy
  • Weight3
  • Tagscomplexity, quicksort, pivot, worst-case
  • Exit code0
  • Timed outFalse
  • Context tokens11,297
  • LLM calls11
  • Tool calls10
  • Compactions0

Tests

C++ test drivers (executed stages only): correctness: passed; performance: passed.

passed
AD100-PRJ-01
taskcli: TSV task manager
20/20
100.0%
100.0%
3.5
3.50
25.9k
201.9s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultyeasy
  • Weight3.5
  • Tagscli, persistence, exit-codes, json-store
  • Exit code0
  • Timed outFalse
  • Context tokens25,913
  • LLM calls22
  • Tool calls21
  • Compactions0
passed
AD100-PRJ-02
INI config library
3/3 drivers
100.0%
100.0%
3
3.00
10.3k
73.7s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagecpp
  • Difficultyeasy
  • Weight3
  • Tagsparsing, ini, api-design, exceptions
  • Exit code0
  • Timed outFalse
  • Context tokens10,328
  • LLM calls10
  • Tool calls11
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

failed
AD100-PRJ-08
Markdown→HTML subset
25/26
96.2%
70.0%
22
15.40
31.1k
274.0s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultyhard
  • Weight22
  • Tagsmarkdown, parser, html, escaping
  • Exit code0
  • Timed outFalse
  • Context tokens31,112
  • LLM calls19
  • Tool calls22
  • Compactions0

Failed tests

  • test_unmatched_markers_stay_literal
passed
AD100-PRJ-09
KV store: TTL + LRU + snapshot
23/23
100.0%
100.0%
4.5
4.50
20.5k
177.9s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultyeasy
  • Weight4.5
  • Tagskv-store, ttl, lru, persistence
  • Exit code0
  • Timed outFalse
  • Context tokens20,492
  • LLM calls19
  • Tool calls18
  • Compactions0
failed
AD100-PRJ-10
cron next-fire calculator
20/21
95.2%
70.0%
3.5
2.45
15.4k
119.7s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultyeasy
  • Weight3.5
  • Tagscron, schedules, calendar, parsing
  • Exit code0
  • Timed outFalse
  • Context tokens15,359
  • LLM calls10
  • Tool calls12
  • Compactions0

Failed tests

  • test_invalid_schedules
passed
AD100-PRJ-11
access-log analyzer (stats + filters)
16/16
100.0%
100.0%
3.5
3.50
17.9k
139.8s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultyeasy
  • Weight3.5
  • Tagslogs, parsing, aggregation, cli
  • Exit code0
  • Timed outFalse
  • Context tokens17,905
  • LLM calls11
  • Tool calls13
  • Compactions0
passed
AD100-PRJ-12
HTTP/1.1 message parser
3/3 drivers
100.0%
100.0%
5
5.00
25.8k
221.8s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagecpp
  • Difficultyeasy
  • Weight5
  • Tagshttp, parser, chunked, protocol
  • Exit code0
  • Timed outFalse
  • Context tokens25,800
  • LLM calls14
  • Tool calls15
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

passed
AD100-PRJ-13
mustache-lite template engine
3/3 drivers
100.0%
100.0%
6.5
6.50
19.5k
169.8s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagecpp
  • Difficultymedium
  • Weight6.5
  • Tagstemplates, mustache, html-escaping, recursion
  • Exit code0
  • Timed outFalse
  • Context tokens19,491
  • LLM calls23
  • Tool calls24
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

failed
AD100-PRJ-14
mini scripting language interpreter
20/21
95.2%
70.0%
10.5
7.35
54.6k
481.2s
DEADLINE

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultymedium
  • Weight10.5
  • Tagsinterpreter, lexer, parser, tree-walker, cli
  • Exit code0
  • Timed outFalse
  • Context tokens54,614
  • LLM calls23
  • Tool calls23
  • Compactions0

Failed tests

  • test_syntax_errors
passed
AD100-PRJ-15
mini pytest (discovery, fixtures, report)
18/18
100.0%
100.0%
4.5
4.50
13.7k
115.7s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultyeasy
  • Weight4.5
  • Tagstest-runner, discovery, fixtures, reporting
  • Exit code0
  • Timed outFalse
  • Context tokens13,707
  • LLM calls13
  • Tool calls12
  • Compactions0
passed
AD100-PRJ-16
Game of Life engine (seeded, census)
11/11
100.0%
100.0%
3.5
3.50
25.1k
481.3s
DEADLINE

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultyeasy
  • Weight3.5
  • Tagsgame-of-life, simulation, prng, cycle-detection
  • Exit code0
  • Timed outFalse
  • Context tokens25,084
  • LLM calls14
  • Tool calls14
  • Compactions0
passed
AD100-PRJ-17
LZ77+RLE codec with checksum
4/4 drivers
100.0%
100.0%
4.5
4.50
19.5k
166.9s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagecpp
  • Difficultyeasy
  • Weight4.5
  • Tagscompression, lz77, rle, checksum, codec
  • Exit code0
  • Timed outFalse
  • Context tokens19,544
  • LLM calls13
  • Tool calls13
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

passed
AD100-PRJ-18
discrete-event simulator (deterministic)
4/4 drivers
100.0%
100.0%
3.5
3.50
9921
481.5s
DEADLINE

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagecpp
  • Difficultyeasy
  • Weight3.5
  • Tagssimulation, event-queue, deterministic-ordering
  • Exit code0
  • Timed outFalse
  • Context tokens9,921
  • LLM calls7
  • Tool calls8
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

passed
AD100-PRJ-19
C++ mini test framework
4/4 drivers
100.0%
100.0%
3.5
3.50
10.3k
67.6s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagecpp
  • Difficultyeasy
  • Weight3.5
  • Tagstest-framework, macros, registry, fixtures
  • Exit code0
  • Timed outFalse
  • Context tokens10,254
  • LLM calls12
  • Tool calls12
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

passed
AD100-PRJ-20
SQL subset engine (DDL/DML/SELECT/JOIN)
4/4 drivers
100.0%
100.0%
15.5
15.50
61.3k
530.2s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagecpp
  • Difficultyhard
  • Weight15.5
  • Tagssql, parser, join, query-engine
  • Exit code0
  • Timed outFalse
  • Context tokens61,347
  • LLM calls32
  • Tool calls33
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

failed
AD100-PRJ-21
Indexed archive utility
5/8 drivers
62.5%
20.0%
30
6.00
159.3k
1202.1s
DEADLINE

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagecpp
  • Difficultyexpert
  • Weight30
  • Tagsmini-project, idea-1, zip, indexed-access, posix-metadata
  • Exit code0
  • Timed outFalse
  • Context tokens159,306
  • LLM calls77
  • Tool calls82
  • Compactions1

Tests

C++ test drivers (one per hidden .cpp file).

Failed tests

  • test_core_metadata
  • test_errors
  • test_errors_structure
failed
AD100-PRJ-22
Silence-aware MP3 splitter
17/18
94.4%
40.0%
11.5
4.60
83.5k
822.7s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultymedium
  • Weight11.5
  • Tagsmini-project, idea-2
  • Exit code0
  • Timed outFalse
  • Context tokens83,475
  • LLM calls43
  • Tool calls44
  • Compactions0

Failed tests

  • test_core_plan_min_track_merges_and_leading_trailing_silence
failed
AD100-PRJ-23
FAT32/VFAT filesystem recovery
16/24
66.7%
20.0%
30
6.00
163.6k
1200.7s
DEADLINE

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultyexpert
  • Weight30
  • Tagsmini-project, idea-3, fat32, vfat, reverse-engineering
  • Exit code0
  • Timed outFalse
  • Context tokens163,558
  • LLM calls78
  • Tool calls81
  • Compactions1

Failed tests

  • test_core_independent_trees[2027]
  • test_core_unicode_short_escape_and_full_lfn_parts
  • test_core_fsinfo_hints_and_primary_boot_authority
  • test_errors_geometry[fat16]
  • test_errors_geometry[truncated]
  • test_errors_lfn_records
  • test_errors_namespace_and_depth_limits
  • test_errors_mirror_disagreement_and_invalid_alias
passed
AD100-PRJ-24
Image similarity and grouping
17/17
100.0%
100.0%
5
5.00
74.2k
852.2s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultyeasy
  • Weight5
  • Tagsmini-project, idea-4
  • Exit code0
  • Timed outFalse
  • Context tokens74,169
  • LLM calls47
  • Tool calls47
  • Compactions0
passed
AD100-PRJ-25
Binary delta generator and applier
3/3 drivers
100.0%
100.0%
6.5
6.50
58.5k
471.2s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagecpp
  • Difficultyeasy
  • Weight6.5
  • Tagsmini-project, idea-5
  • Exit code0
  • Timed outFalse
  • Context tokens58,523
  • LLM calls30
  • Tool calls31
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

passed
AD100-PRJ-26
Incremental build tool
40/40
100.0%
100.0%
10
10.00
62.4k
546.3s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultyhard
  • Weight10
  • Tagsmini-project, idea-6
  • Exit code0
  • Timed outFalse
  • Context tokens62,422
  • LLM calls63
  • Tool calls63
  • Compactions0
failed
AD100-PRJ-27
ELF executable inspector
0/79
0.0%
0.0%
21
0.00
156.7k
1202.0s
DEADLINE

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultyhard
  • Weight21
  • Tagsmini-project, idea-7, elf64, binary-recovery, stdlib
  • Exit code0
  • Timed outFalse
  • Context tokens156,653
  • LLM calls66
  • Tool calls74
  • Compactions1

Failed tests

  • test_core_reports[raw-sections]
  • test_core_reports[raw-symbols]
  • test_core_reports[raw-relocations]
  • test_core_reports[raw-segments]
  • test_core_reports[multiple-sections]
  • test_core_reports[multiple-symbols]
  • test_core_reports[multiple-relocations]
  • test_core_reports[multiple-segments]
  • test_core_reports[rel-sections]
  • test_core_reports[rel-symbols]
  • test_core_reports[rel-relocations]
  • test_core_reports[rel-segments]
  • test_core_reports[shared-sections]
  • test_core_reports[shared-symbols]
  • test_core_reports[shared-relocations]
  • test_core_reports[shared-segments]
  • test_core_reports[buffers-sections]
  • test_core_reports[buffers-symbols]
  • test_core_reports[buffers-relocations]
  • test_core_reports[buffers-segments]
  • test_core_absent_names[sections]
  • test_core_absent_names[symbols]
  • test_core_absent_names[relocations]
  • test_core_absent_names[segments]
  • test_core_no_tables
  • test_core_numeric_metadata_and_reserved_symbols
  • test_core_accessed_tables_only
  • test_core_review_valid_inputs[sections-null-program]
  • test_core_review_valid_inputs[sections-empty-symbol-names]
  • test_core_review_valid_inputs[sections-symbol-free-relocations]
  • test_core_review_valid_inputs[symbols-null-program]
  • test_core_review_valid_inputs[symbols-empty-symbol-names]
  • test_core_review_valid_inputs[symbols-symbol-free-relocations]
  • test_core_review_valid_inputs[relocations-null-program]
  • test_core_review_valid_inputs[relocations-empty-symbol-names]
  • test_core_review_valid_inputs[relocations-symbol-free-relocations]
  • test_core_review_valid_inputs[segments-null-program]
  • test_core_review_valid_inputs[segments-empty-symbol-names]
  • test_core_review_valid_inputs[segments-symbol-free-relocations]
  • test_errors_type_header_bounds[sections]
  • test_errors_type_header_bounds[symbols]
  • test_errors_type_header_bounds[relocations]
  • test_errors_type_header_bounds[segments]
  • test_errors_sections[payload]
  • test_errors_sections[name-type]
  • test_errors_sections[name-range]
  • test_errors_sections[name-end]
  • test_errors_sections[name-start]
  • test_errors_symbols[stride]
  • test_errors_symbols[remainder]
  • test_errors_symbols[link-range]
  • test_errors_symbols[link-type]
  • test_errors_symbols[info]
  • test_errors_symbols[name-range]
  • test_errors_symbols[section-range]
  • test_errors_symbols[string-end]
  • test_errors_symbols[string-start]
  • test_errors_relocations[stride]
  • test_errors_relocations[remainder]
  • test_errors_relocations[link-range]
  • test_errors_relocations[link-type]
  • test_errors_relocations[target]
  • test_errors_relocations[symbol-range]
  • test_errors_relocations[linked-stride]
  • test_errors_relocations[linked-string]
  • test_errors_segments
  • test_errors_review_boundaries[null-as-load]
  • test_errors_review_boundaries[null-as-note]
  • test_errors_review_boundaries[empty-name-nonzero]
  • test_errors_review_boundaries[empty-name-bad-type]
  • test_errors_review_boundaries[empty-name-bounds]
  • test_errors_review_boundaries[no-table-nonzero-symbol]
  • test_errors_review_boundaries[no-table-bad-link]
  • test_errors_review_boundaries[no-table-wrong-type]
  • test_resources_light_envelope[sections]
  • test_resources_light_envelope[symbols]
  • test_resources_light_envelope[relocations]
  • test_resources_light_envelope[segments]
  • test_resources_untrusted_sizes
passed
AD100-PRJ-28
Dependency-aware package resolver
29/29
100.0%
100.0%
9
9.00
129.9k
984.8s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultyhard
  • Weight9
  • Tagsmini-project, idea-8
  • Exit code0
  • Timed outFalse
  • Context tokens129,879
  • LLM calls72
  • Tool calls73
  • Compactions1
failed
AD100-PRJ-29
RAW Bayer development pipeline
2/3 drivers
66.7%
40.0%
7
2.80
47.1k
264.0s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagecpp
  • Difficultyeasy
  • Weight7
  • Tagsmini-project, idea-9
  • Exit code0
  • Timed outFalse
  • Context tokens47,128
  • LLM calls27
  • Tool calls27
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

Failed tests

  • test_core
passed
AD100-PRJ-30
Image registration (translation)
3/3 drivers
100.0%
100.0%
3.5
3.50
52.4k
314.0s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagecpp
  • Difficultyeasy
  • Weight3.5
  • Tagsmini-project, idea-10
  • Exit code0
  • Timed outFalse
  • Context tokens52,447
  • LLM calls30
  • Tool calls30
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

failed
AD100-PRJ-31
Score language to WAV synthesizer
11/12
91.7%
40.0%
28
11.20
48.7k
646.5s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultyexpert
  • Weight28
  • Tagsmini-project, idea-11
  • Exit code0
  • Timed outFalse
  • Context tokens48,677
  • LLM calls37
  • Tool calls36
  • Compactions0

Failed tests

  • test_core_voice_continuation
failed
AD100-PRJ-32
Fixed-timestep 2D physics sandbox
10/12
83.3%
20.0%
9.5
1.90
25.4k
215.8s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultyhard
  • Weight9.5
  • Tagsmini-project, idea-12
  • Exit code0
  • Timed outFalse
  • Context tokens25,441
  • LLM calls18
  • Tool calls19
  • Compactions0

Failed tests

  • test_core_bounds_reflection
  • test_resources_many_bodies
failed
AD100-PRJ-33
Columnar data compressor
1/3 drivers
33.3%
20.0%
30
6.00
56.5k
460.1s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagecpp
  • Difficultyexpert
  • Weight30
  • Tagsmini-project, idea-13
  • Exit code0
  • Timed outFalse
  • Context tokens56,454
  • LLM calls36
  • Tool calls37
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

Failed tests

  • test_core
  • test_errors
failed
AD100-PRJ-34
DTMF decoder
0/13
0.0%
0.0%
18.5
0.00
36.9k
417.2s
PI_EXIT

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultyhard
  • Weight18.5
  • Tagsmini-project, idea-14
  • Exit code0
  • Timed outFalse
  • Context tokens36,879
  • LLM calls4
  • Tool calls5
  • Compactions0

Failed tests

  • test_core_all_twelve_symbols
  • test_core_timing_frames
  • test_core_quiet_tone_still_found
  • test_core_very_quiet_tone_ignored
  • test_core_noise_tolerant
  • test_core_distractor_frequency_ignored
  • test_core_short_blip_rejected
  • test_core_gap_bridging
  • test_core_sample_rate_16000
  • test_errors_bad_container
  • test_errors_bad_format
  • test_errors_truncated_chunks
  • test_resources_one_minute_audio
failed
AD100-PRJ-35
Mobile-robot path planner
11/12
91.7%
40.0%
9.5
3.80
18.5k
147.8s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultymedium
  • Weight9.5
  • Tagsmini-project, idea-15
  • Exit code0
  • Timed outFalse
  • Context tokens18,544
  • LLM calls13
  • Tool calls15
  • Compactions0

Failed tests

  • test_core_tie_break_deterministic
failed
AD100-PRJ-36
Two-link robot-arm controller
13/14
92.9%
80.0%
23
18.40
43.7k
350.0s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultyexpert
  • Weight23
  • Tagsmini-project, idea-16
  • Exit code0
  • Timed outFalse
  • Context tokens43,729
  • LLM calls33
  • Tool calls32
  • Compactions0

Failed tests

  • test_errors_configs
passed
AD100-PRJ-37
Fiducial-marker detector
3/3 drivers
100.0%
100.0%
12.5
12.50
75.0k
704.4s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagecpp
  • Difficultymedium
  • Weight12.5
  • Tagsmini-project, idea-17
  • Exit code0
  • Timed outFalse
  • Context tokens75,006
  • LLM calls60
  • Tool calls62
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

failed
AD100-PRJ-38
Multi-object tracker
9/11
81.8%
20.0%
15.5
3.10
164.3k
1200.0s
DEADLINE

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultyhard
  • Weight15.5
  • Tagsmini-project, idea-18
  • Exit code0
  • Timed outFalse
  • Context tokens164,299
  • LLM calls70
  • Tool calls72
  • Compactions1

Failed tests

  • test_core_crossing_identity_swap
  • test_errors_frames
failed
AD100-PRJ-39
Parametric audio equalizer
1/3 drivers
33.3%
20.0%
28
5.60
58.2k
479.2s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagecpp
  • Difficultyexpert
  • Weight28
  • Tagsmini-project, idea-19
  • Exit code0
  • Timed outFalse
  • Context tokens58,180
  • LLM calls48
  • Tool calls49
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

Failed tests

  • test_core
  • test_errors
failed
AD100-PRJ-40
Barcode scanner (EAN-13)
—
—
0.0%
24
0.00
151.0k
1202.2s
DEADLINE

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagecpp
  • Difficultyexpert
  • Weight24
  • Tagsmini-project, idea-20
  • Exit code0
  • Timed outFalse
  • Context tokens151,039
  • LLM calls57
  • Tool calls60
  • Compactions1

Tests

C++ test drivers: results unavailable or incomplete.

failed
AD100-PRJ-41
JSONL chat-log to Markdown converter
25/32
78.1%
20.0%
30
6.00
73.5k
528.2s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultyexpert
  • Weight30
  • Tagsmini-project, idea-21
  • Exit code0
  • Timed outFalse
  • Context tokens73,530
  • LLM calls48
  • Tool calls47
  • Compactions0

Failed tests

  • test_core_unterminated_fence_runs_to_end
  • test_core_tool_result_and_empty_text
  • test_core_message_default_text
  • test_errors_blank_line
  • test_errors_unknown_type
  • test_errors_empty_role
  • test_errors_tool_call_fields
failed
AD100-PRJ-42
RFC 3986 URL utility
119/129
92.2%
0.0%
30
0.00
155.6k
1200.1s
DEADLINE

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultyexpert
  • Weight30
  • Tagsmini-project, idea-22, rfc3986, native-oracle
  • Exit code0
  • Timed outFalse
  • Context tokens155,590
  • LLM calls67
  • Tool calls67
  • Compactions1

Failed tests

  • test_core_rfc3986_resolution[/g-http://a/g]
  • test_core_rfc3986_resolution[-http://a/b/c/d;p?q]
  • test_core_rfc3986_resolution[/./g-http://a/g]
  • test_core_rfc3986_resolution[/../g-http://a/g]
  • test_errors_malformed_url[http://%C3%A9/]
  • test_errors_malformed_url[http://h/\ud800]
  • test_errors_api_types_and_escapes[parse-args4-kwargs4]
  • test_errors_api_types_and_escapes[decode-args15-kwargs15]
  • test_errors_all_input_length_limits
  • test_resources_long_zero_port
passed
AD100-PRJ-43
Nonlinear least-squares solver
3/3 drivers
100.0%
100.0%
7.5
7.50
48.6k
472.2s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagecpp
  • Difficultymedium
  • Weight7.5
  • Tagsmini-project, idea-23
  • Exit code0
  • Timed outFalse
  • Context tokens48,559
  • LLM calls23
  • Tool calls23
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

passed
AD100-PRJ-44
IBAN and credit-card validator
9/9
100.0%
100.0%
6
6.00
51.7k
358.1s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultyeasy
  • Weight6
  • Tagsmini-project, idea-24
  • Exit code0
  • Timed outFalse
  • Context tokens51,730
  • LLM calls36
  • Tool calls39
  • Compactions0
failed
AD100-PRJ-45
Arbitrary-precision integer arithmetic
1/3 drivers
33.3%
20.0%
14.5
2.90
72.6k
1200.0s
DEADLINE

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagecpp
  • Difficultyhard
  • Weight14.5
  • Tagsmini-project, idea-25
  • Exit code0
  • Timed outFalse
  • Context tokens72,555
  • LLM calls33
  • Tool calls34
  • Compactions0

Tests

C++ test drivers (one per hidden .cpp file).

Failed tests

  • test_core
  • test_resources
passed
AD100-PRJ-47
Recover a hidden phrase from an executable
6/6
100.0%
100.0%
5.5
5.50
27.2k
139.8s

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultymedium
  • Weight5.5
  • Tagsmini-project, idea-27
  • Exit code0
  • Timed outFalse
  • Context tokens27,207
  • LLM calls23
  • Tool calls22
  • Compactions0
failed
AD100-PRJ-48
Black-box image transformation utility clone
—
—
0.0%
30
0.00
243.2k
1200.2s
DEADLINE

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagecpp
  • Difficultyexpert
  • Weight30
  • Tagsmini-project, idea-28
  • Exit code0
  • Timed outFalse
  • Context tokens243,204
  • LLM calls76
  • Tool calls80
  • Compactions2

Tests

C++ test drivers: results unavailable or incomplete.

passed
AD100-PRJ-49
Closed-loop differential-drive line follower
21/21
100.0%
100.0%
13.5
13.50
136.6k
1200.2s
DEADLINE

Challenge

  • Observed modelsunsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ3_XXS
  • Pillarproject
  • Languagepython
  • Difficultyhard
  • Weight13.5
  • Tagsmini-project, idea-29
  • Exit code0
  • Timed outFalse
  • Context tokens136,580
  • LLM calls43
  • Tool calls46
  • Compactions1