Data Exchange
JSON handling, HTTP integration, XMLport I/O, and external APIs
Report generated: February 14, 2026 at 8:13 PM
Benchmark data: Feb 8, 2026 – Feb 13, 2026
12
Models
6
Tasks
25.0%
Pass Rate
Model Rankings
Model Performance
anthropic/claude-opus-4-6
Runs:3
pass@1:77.8%
pass@3:83.3%
Consistency:83.3%
1st: 52nd: 9Failed: 15/6 passed
Temperature:0.1
Thinking:-
Tokens/run:21,986
Cost/run:$0.37
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
anthropic/claude-opus-4-5-20251101@thinking=50000
Runs:3
pass@1:66.7%
pass@3:66.7%
Consistency:100.0%
1st: 32nd: 9Failed: 24/6 passed
Temperature:0.1
Thinking:50,000
Tokens/run:26,652
Cost/run:$0.44
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
gemini/gemini-3-pro-preview
Runs:3
pass@1:22.2%
pass@3:33.3%
Consistency:83.3%
1st: 32nd: 1Failed: 42/6 passed
Temperature:0.1
Thinking:-
Tokens/run:148,762
Cost/run:$0.18
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
openrouter/moonshotai/kimi-k2.5
Runs:3
pass@1:16.7%
pass@3:33.3%
Consistency:66.7%
1st: 12nd: 2Failed: 42/6 passed
Temperature:0.1
Thinking:-
Tokens/run:44,776
Cost/run:$0.42
Known Shortcomings (3)
- event-subscriber-parameter-syntax 1x
- page-extension-cardpageid-override 1x
- parse-failure 1x
openai/gpt-5.2-2025-12-11@thinking=high
Runs:3
pass@1:16.7%
pass@3:16.7%
Consistency:100.0%
2nd: 3Failed: 51/6 passed
Temperature:0.1
Thinking:high
Tokens/run:26,077
Cost/run:$0.23
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
anthropic/claude-sonnet-4-5-20250929
Runs:3
pass@1:16.7%
pass@3:16.7%
Consistency:100.0%
2nd: 3Failed: 51/6 passed
Temperature:0.1
Thinking:-
Tokens/run:24,081
Cost/run:$0.22
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
openrouter/deepseek/deepseek-v3.2
Runs:3
pass@1:16.7%
pass@3:16.7%
Consistency:100.0%
2nd: 3Failed: 51/6 passed
Temperature:0.1
Thinking:-
Tokens/run:21,860
Cost/run:$0.19
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
openrouter/z-ai/glm-5
Runs:3
pass@1:11.1%
pass@3:16.7%
Consistency:83.3%
1st: 12nd: 1Failed: 51/6 passed
Temperature:0.1
Thinking:-
Tokens/run:34,852
Cost/run:$0.31
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
openrouter/x-ai/grok-code-fast-1
Runs:3
pass@1:11.1%
pass@3:16.7%
Consistency:83.3%
2nd: 2Failed: 51/6 passed
Temperature:0.1
Thinking:-
Tokens/run:117,847
Cost/run:$0.44
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
openrouter/minimax/minimax-m2.5
Runs:3
pass@1:0.0%
pass@3:0.0%
Consistency:100.0%
Failed: 60/6 passed
Temperature:0.1
Thinking:-
Tokens/run:27,793
Cost/run:$0.20
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
openrouter/qwen/qwen3-max-thinking
Runs:3
pass@1:0.0%
pass@3:0.0%
Consistency:100.0%
Failed: 60/6 passed
Temperature:0.1
Thinking:-
Tokens/run:20,141
Cost/run:$0.15
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
openrouter/qwen/qwen3-coder-next
Runs:3
pass@1:0.0%
pass@3:0.0%
Consistency:100.0%
Failed: 60/6 passed
Temperature:0.1
Thinking:-
Tokens/run:18,181
Cost/run:$0.15
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
Task Results Matrix
N/M = passed N of M runs (hover for details)
| Task | Description | Claude Opus 4.6 | Claude Opus 4.5 (50K) | Gemini 3 Pro | Kimi K2.5 | GPT-5.2 | Claude Sonnet 4.5 | Deepseek V3.2 | Glm 5 | Grok Code Fast 1 | Minimax M2.5 | Qwen3 Max Thinking | Qwen3 Coder Next |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CG-AL-E009 | Create a simple AL XMLport called "Item Export" with ID 70000. The XMLport should export Item data with the following structure: - Root element: Items - Item element containing: No, Description, Unit Price, Inventory | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 |
| CG-AL-H014 | Create an AL codeunit named "CG JSON Parser" with ID 70014 that uses the typed JSON getter methods: | 3/3 | 3/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 |
| CG-AL-M005 | Create an integration codeunit called "External Payment Service" with ID 70002 that handles external API communication. The codeunit should implement the following procedures: | 2/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 |
| CG-AL-M020 | Create an AL codeunit named "CG JSON Value Extractor" with ID 70120. | 3/3 | 3/3 | 1/3 | 2/3 | 0/3 | 0/3 | 0/3 | 0/3 | 2/3 | 0/3 | 0/3 | 0/3 |
| CG-AL-M021 | Create an AL codeunit named "CG YAML Handler" with ID 70121 that handles reading and writing YAML. | 3/3 | 3/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 | 0/3 |
| CG-AL-M022 | Create a codeunit named "CG Weather Service" with ID 70122 that makes HTTP calls to an external weather API. This tests whether the LLM can properly implement HttpClient usage. | 3/3 | 3/3 | 3/3 | 1/3 | 3/3 | 3/3 | 3/3 | 2/3 | 0/3 | 0/3 | 0/3 | 0/3 |