← Back to Benchmark Results

Advanced AL Patterns

RecordRef, FieldRef, Queries, SingleInstance, Fluent API, and modern collections

Report generated: February 14, 2026 at 8:13 PM

Benchmark data: Feb 8, 2026 – Feb 13, 2026

12
Models
10
Tasks
44.2%
Pass Rate

Model Rankings

pass@1 pass@3 (additional)
GPT-5.2 (high, t0.1)
50%
10%
60.0%
Gemini 3 Pro (t0.1)
47%
23%
70.0%
Kimi K2.5 (t0.1)
37%
40.0%
Glm 5 (t0.1)
30%
30.0%
Minimax M2.5 (t0.1)
17%
13%
30.0%

Model Performance

anthropic/claude-opus-4-5-20251101@thinking=50000

Runs:3
pass@1:70.0%
pass@3:70.0%
Consistency:100.0%
1st: 182nd: 3Failed: 37/10 passed
Temperature:0.1
Thinking:50,000
Tokens/run:37,114
Cost/run:$0.58

Known Shortcomings (8)

  • page-extension-with-table-extension 1x
  • reserved-keyword-as-parameter-name 1x
  • dictionary-iteration-syntax 1x
  • empty-or-malformed-code-generation 1x
  • temporary-table-parameter-handling 1x
+3 more View all 8
View details ›

anthropic/claude-opus-4-6

Runs:3
pass@1:70.0%
pass@3:70.0%
Consistency:100.0%
1st: 152nd: 6Failed: 37/10 passed
Temperature:0.1
Thinking:-
Tokens/run:49,075
Cost/run:$0.78

Known Shortcomings (6)

  • reserved-keyword-as-parameter-name 1x
  • cross-join-dataitem-link 1x
  • incomplete-procedure-body 1x
  • flowfield-calcfields-requirement 1x
  • parse-failure 1x
+1 more View all 6
View details ›

openai/gpt-5.2-2025-12-11@thinking=high

Runs:3
pass@1:50.0%
pass@3:60.0%
Consistency:80.0%
1st: 32nd: 12Failed: 46/10 passed
Temperature:0.1
Thinking:high
Tokens/run:34,540
Cost/run:$0.28

Known Shortcomings (10)

  • interface-definition-syntax 2x
  • table-field-caption-property 1x
  • query-object-syntax 1x
  • query-crossjoin-syntax 1x
  • parse-failure 1x
+5 more View all 10
View details ›

gemini/gemini-3-pro-preview

Runs:3
pass@1:46.7%
pass@3:70.0%
Consistency:60.0%
1st: 132nd: 1Failed: 37/10 passed
Temperature:0.1
Thinking:-
Tokens/run:203,631
Cost/run:$0.24

Known Shortcomings (9)

  • multiline-string-literals 1x
  • inherent-permissions-syntax 1x
  • query-crossjoin-column-datasource 1x
  • complete-codeunit-generation 1x
  • yaml-parsing-string-manipulation 1x
+4 more View all 9
View details ›

openrouter/moonshotai/kimi-k2.5

Runs:3
pass@1:36.7%
pass@3:40.0%
Consistency:90.0%
1st: 92nd: 2Failed: 64/10 passed
Temperature:0.1
Thinking:-
Tokens/run:66,338
Cost/run:$0.63

Known Shortcomings (3)

  • event-subscriber-parameter-syntax 1x
  • page-extension-cardpageid-override 1x
  • parse-failure 1x
View details ›

anthropic/claude-sonnet-4-5-20250929

Runs:3
pass@1:33.3%
pass@3:40.0%
Consistency:90.0%
1st: 92nd: 1Failed: 64/10 passed
Temperature:0.1
Thinking:-
Tokens/run:40,976
Cost/run:$0.36

Known Shortcomings (8)

  • multiline-string-literals 1x
  • query-filter-element-syntax 1x
  • jsonobject-get-method-signature 1x
  • cross-join-dataitem-link-constraints 1x
  • reserved-keyword-as-variable-name 1x
+3 more View all 8
View details ›

openrouter/deepseek/deepseek-v3.2

Runs:3
pass@1:33.3%
pass@3:40.0%
Consistency:80.0%
1st: 82nd: 2Failed: 64/10 passed
Temperature:0.1
Thinking:-
Tokens/run:33,883
Cost/run:$0.24

Known Shortcomings (18)

  • dictionary-clear-method 1x
  • application-area-in-page-extension-field 1x
  • multiline-string-literals 1x
  • page-extension-cardpageid-override 1x
  • errorinfo-custom-dimensions-api 1x
+13 more View all 18
View details ›

openrouter/z-ai/glm-5

Runs:3
pass@1:30.0%
pass@3:30.0%
Consistency:100.0%
1st: 72nd: 2Failed: 73/10 passed
Temperature:0.1
Thinking:-
Tokens/run:61,105
Cost/run:$0.56

Known Shortcomings (17)

  • list-dictionary-of-interface-clear-method 1x
  • event-subscriber-event-name 1x
  • al-string-literal-escaping 1x
  • query-object-syntax 1x
  • fluent-api-return-self-codeunit 1x
+12 more View all 17
View details ›

openrouter/qwen/qwen3-max-thinking

Runs:3
pass@1:26.7%
pass@3:30.0%
Consistency:90.0%
1st: 32nd: 5Failed: 73/10 passed
Temperature:0.1
Thinking:-
Tokens/run:31,936
Cost/run:$0.24

Known Shortcomings (12)

  • option-field-optionmembers-required 2x
  • enum-frominteger-syntax 1x
  • list-iteration-pattern 1x
  • variant-type-argument-and-interface-definition 1x
  • json-object-api-methods 1x
+7 more View all 12
View details ›

openrouter/x-ai/grok-code-fast-1

Runs:3
pass@1:23.3%
pass@3:30.0%
Consistency:90.0%
1st: 62nd: 1Failed: 73/10 passed
Temperature:0.1
Thinking:-
Tokens/run:66,841
Cost/run:$0.58

Known Shortcomings (12)

  • query-object-syntax 2x
  • multiline-string-literals 1x
  • page-extension-cardpageid-override 1x
  • json-api-methods 1x
  • recordref-fieldref-dynamic-manipulation 1x
+7 more View all 12
View details ›

openrouter/qwen/qwen3-coder-next

Runs:3
pass@1:20.0%
pass@3:20.0%
Consistency:100.0%
1st: 6Failed: 82/10 passed
Temperature:0.1
Thinking:-
Tokens/run:32,089
Cost/run:$0.21

Known Shortcomings (19)

  • codeunit-generation-empty-output 5x
  • interface-definition-syntax 3x
  • query-object-syntax 2x
  • initvalue-vs-defaultvalue 1x
  • text-trim-method-unavailable 1x
+14 more View all 19
View details ›

openrouter/minimax/minimax-m2.5

Runs:3
pass@1:16.7%
pass@3:30.0%
Consistency:80.0%
1st: 32nd: 2Failed: 73/10 passed
Temperature:0.1
Thinking:-
Tokens/run:44,644
Cost/run:$0.37

Known Shortcomings (18)

  • interface-definition-syntax 2x
  • text-char-conversion-copystr 1x
  • page-object-definition 1x
  • event-subscriber-attribute-syntax 1x
  • page-extension-and-table-extension-generation 1x
+13 more View all 18
View details ›

Task Results Matrix

N/M = passed N of M runs (hover for details)

TaskDescriptionClaude Opus 4.5 (50K)Claude Opus 4.6GPT-5.2Gemini 3 ProKimi K2.5Claude Sonnet 4.5Deepseek V3.2Glm 5Qwen3 Max ThinkingGrok Code Fast 1Qwen3 Coder NextMinimax M2.5
CG-AL-H003Create a codeunit called "CG Temp Table Processor" with ID 70202 that demonstrates correct temporary table handling.3/33/30/33/32/30/30/33/30/30/30/30/3
CG-AL-H005Create a table and codeunit that test understanding of Rec vs xRec and Modify behavior.0/30/30/30/30/30/30/30/30/30/30/30/3
CG-AL-H006Create a SingleInstance codeunit that maintains state across calls within the same session.3/33/33/33/33/33/32/33/33/33/33/33/3
CG-AL-H011Create an AL query object named "CG Sales Summary" with ID 70011 that:3/30/31/33/30/31/33/30/30/30/30/30/3
CG-AL-H017Create an AL query object named "CG Dimension Matrix" with ID 70017 that:3/33/30/31/30/30/30/30/30/30/30/30/3
CG-AL-H018Create an AL codeunit named "CG Request Builder" with ID 70018 implementing a fluent API pattern:3/33/33/32/33/33/30/30/32/30/30/30/3
CG-AL-H020Create an AL codeunit named "CG Collection Processor" with ID 70020 demonstrating List and Dictionary types:0/33/33/31/30/30/32/30/30/31/30/30/3
CG-AL-H022Create a codeunit named "CG Dynamic Record Handler" with ID 70224 that demonstrates advanced RecordRef and FieldRef usage for dynamic record manipulation.3/33/32/30/30/30/30/30/30/30/30/31/3
CG-AL-H023Create a codeunit named "CG Record Introspector" with ID 70226 for dynamic record manipulation and introspection using RecordRef and FieldRef.0/30/30/30/30/30/30/30/30/30/30/30/3
CG-AL-M023Create a codeunit named "CG Partial Record Loader" with ID 70123 that demonstrates the SetLoadFields method for optimized partial record loading.3/33/33/31/33/33/33/33/33/33/33/31/3