Follow Discord
Sweep 22 Oct 2026 · 21:04Z Build v2.1.309 528 read Stable v2.1.308 Latest v2.1.309 Next v2.1.309 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Developer Platform 23 Oct 2026
One change · api

develop-tests changedtest-and-evaluate/develop-tests

Nearest release: v2.1.309, published 3 hours before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Recorded here
Lines+27added
Lines−27removed
From line 1,118 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits12to this page, all time

The whole hunk

from line 1118, old and new numbered
/
lines
from line 1118
11181118 
11191119 // ROUGE-L measures the longest common subsequence (LCS) of words between the
11201120 // candidate and reference summaries, reported here as an F1 score. Tokenization
1121 // is simplified to whitespace words; scores may differ from the Python rouge library.
1121 // is simplified to whitespace words; scores might differ from the Python rouge library.
11221122 function rougeL(candidate: string, reference: string): number {
11231123 const candidateWords = candidate.toLowerCase().trim().split(/\s+/);
11241124 const referenceWords = reference.toLowerCase().trim().split(/\s+/);
from line 1187
11871187 
11881188 // ROUGE-L measures the longest common subsequence (LCS) of words between the
11891189 // candidate and reference summaries, reported here as an F1 score. Tokenization
1190 // is simplified to whitespace words; scores may differ from the Python rouge library.
1190 // is simplified to whitespace words; scores might differ from the Python rouge library.
11911191 double RougeL(string candidate, string reference)
11921192 {
11931193 var candidateWords = Regex.Split(candidate.ToLowerInvariant().Trim(), @"\s+");
from line 1290
12901290 
12911291 // ROUGE-L measures the longest common subsequence (LCS) of words between the
12921292 // candidate and reference summaries, reported here as an F1 score. Tokenization
1293 // is simplified to whitespace words; scores may differ from the Python rouge library.
1293 // is simplified to whitespace words; scores might differ from the Python rouge library.
12941294 func rougeL(candidate, reference string) float64 {
12951295 candidateWords := strings.Fields(strings.ToLower(candidate))
12961296 referenceWords := strings.Fields(strings.ToLower(reference))
from line 1371
13711371 
13721372 // ROUGE-L measures the longest common subsequence (LCS) of words between the
13731373 // candidate and reference summaries, reported here as an F1 score. Tokenization
1374 // is simplified to whitespace words; scores may differ from the Python rouge library.
1374 // is simplified to whitespace words; scores might differ from the Python rouge library.
13751375 double rougeL(String candidate, String reference) {
13761376 var candidateWords = candidate.toLowerCase().strip().split("\\s+");
13771377 var referenceWords = reference.toLowerCase().strip().split("\\s+");
from line 1443
14431443 
14441444 // ROUGE-L measures the longest common subsequence (LCS) of words between the
14451445 // candidate and reference summaries, reported here as an F1 score. Tokenization
1446 // is simplified to whitespace words; scores may differ from the Python rouge library.
1446 // is simplified to whitespace words; scores might differ from the Python rouge library.
14471447 function rougeL(string $candidate, string $reference): float
14481448 {
14491449 $candidateWords = preg_split('/\s+/', strtolower(trim($candidate)));
from line 1527
15271527 
15281528 # ROUGE-L measures the longest common subsequence (LCS) of words between the
15291529 # candidate and reference summaries, reported here as an F1 score. Tokenization
1530 # is simplified to whitespace words; scores may differ from the Python rouge library.
1530 # is simplified to whitespace words; scores might differ from the Python rouge library.
15311531 def rouge_l(candidate, reference)
15321532 candidate_words = candidate.downcase.split
15331533 reference_words = reference.downcase.split
from line 1602
16021602 5: Perfectly {target_tone}
16031603 Output only the number."""
16041604 
1605 # Generally best practice to use a different model to evaluate than the model used to generate the evaluated output
1605 # Generally best practice to evaluate with a different model from the one used to generate the evaluated output
16061606 response = client.messages.create(
16071607 model="claude-opus-5-5",
16081608 max_tokens=1024,
from line 1660
16601660 5: Perfectly ${targetTone}
16611661 Output only the number.`;
16621662 
1663 // Generally best practice to use a different model to evaluate than the model used to generate the evaluated output
1663 // Generally best practice to evaluate with a different model from the one used to generate the evaluated output
16641664 const response = await client.messages.create({
16651665 model: "claude-opus-5-5",
16661666 max_tokens: 1024,
from line 1721
17211721 Output only the number.
17221722 """;
17231723 
1724 // Generally best practice to use a different model to evaluate than the model used to generate the evaluated output
1724 // Generally best practice to evaluate with a different model from the one used to generate the evaluated output
17251725 var response = await client.Messages.Create(new MessageCreateParams
17261726 {
17271727 Model = Model.ClaudeOpus5_5,
from line 1804
18041804 5: Perfectly %[1]s
18051805 Output only the number.`, targetTone, modelOutput)
18061806 
1807 // Generally best practice to use a different model to evaluate than the model used to generate the evaluated output
1807 // Generally best practice to evaluate with a different model from the one used to generate the evaluated output
18081808 response, err := client.Messages.New(context.Background(), anthropic.MessageNewParams{
18091809 Model: anthropic.ModelClaudeOpus5_5,
18101810 MaxTokens: 1024,
from line 1873
18731873 5: Perfectly %1$s
18741874 Output only the number.""".formatted(targetTone, modelOutput);
18751875 
1876 // Generally best practice to use a different model to evaluate than the model used to generate the evaluated output
1876 // Generally best practice to evaluate with a different model from the one used to generate the evaluated output
18771877 var params = MessageCreateParams.builder()
18781878 .model(Model.CLAUDE_OPUS_5_5)
18791879 .maxTokens(1024L)
from line 1931
19311931 Output only the number.
19321932 PROMPT;
19331933 
1934 // Generally best practice to use a different model to evaluate than the model used to generate the evaluated output
1934 // Generally best practice to evaluate with a different model from the one used to generate the evaluated output
19351935 $response = $client->messages->create(
19361936 model: Model::CLAUDE_OPUS_5_5,
19371937 maxTokens: 1024,
from line 2008
20082008 Output only the number.
20092009 PROMPT
20102010 
2011 # Generally best practice to use a different model to evaluate than the model used to generate the evaluated output
2011 # Generally best practice to evaluate with a different model from the one used to generate the evaluated output
20122012 response = client.messages.create(
20132013 model: Anthropic::Model::CLAUDE_OPUS_5_5,
20142014 max_tokens: 1024,
from line 2082
20822082 <response>{model_output}</response>
20832083 Output only 'yes' or 'no'."""
20842084 
2085 # Generally best practice to use a different model to evaluate than the model used to generate the evaluated output
2085 # Generally best practice to evaluate with a different model from the one used to generate the evaluated output
20862086 response = client.messages.create(
20872087 model="claude-opus-5-5",
20882088 max_tokens=1024,
from line 2159
21592159 <response>${modelOutput}</response>
21602160 Output only 'yes' or 'no'.`;
21612161 
2162 // Generally best practice to use a different model to evaluate than the model used to generate the evaluated output
2162 // Generally best practice to evaluate with a different model from the one used to generate the evaluated output
21632163 const response = await client.messages.create({
21642164 model: "claude-opus-5-5",
21652165 max_tokens: 1024,
from line 2227
22272227 Output only 'yes' or 'no'.
22282228 """;
22292229 
2230 // Generally best practice to use a different model to evaluate than the model used to generate the evaluated output
2230 // Generally best practice to evaluate with a different model from the one used to generate the evaluated output
22312231 var response = await client.Messages.Create(new MessageCreateParams
22322232 {
22332233 Model = Model.ClaudeOpus5_5,
from line 2324
23242324 <response>%s</response>
23252325 Output only 'yes' or 'no'.`, modelOutput)
23262326 
2327 // Generally best practice to use a different model to evaluate than the model used to generate the evaluated output
2327 // Generally best practice to evaluate with a different model from the one used to generate the evaluated output
23282328 response, err := client.Messages.New(context.Background(), anthropic.MessageNewParams{
23292329 Model: anthropic.ModelClaudeOpus5_5,
23302330 MaxTokens: 1024,
from line 2401
24012401 <response>%s</response>
24022402 Output only 'yes' or 'no'.""".formatted(modelOutput);
24032403 
2404 // Generally best practice to use a different model to evaluate than the model used to generate the evaluated output
2404 // Generally best practice to evaluate with a different model from the one used to generate the evaluated output
24052405 var params = MessageCreateParams.builder()
24062406 .model(Model.CLAUDE_OPUS_5_5)
24072407 .maxTokens(1024L)
from line 2472
24722472 Output only 'yes' or 'no'.
24732473 PROMPT;
24742474 
2475 // Generally best practice to use a different model to evaluate than the model used to generate the evaluated output
2475 // Generally best practice to evaluate with a different model from the one used to generate the evaluated output
24762476 $response = $client->messages->create(
24772477 model: Model::CLAUDE_OPUS_5_5,
24782478 maxTokens: 1024,
from line 2558
25582558 Output only 'yes' or 'no'.
25592559 PROMPT
25602560 
2561 # Generally best practice to use a different model to evaluate than the model used to generate the evaluated output
2561 # Generally best practice to evaluate with a different model from the one used to generate the evaluated output
25622562 response = client.messages.create(
25632563 model: Anthropic::Model::CLAUDE_OPUS_5_5,
25642564 max_tokens: 1024,
from line 2656
26562656 5: Perfectly utilizes context
26572657 Output only the number and nothing else."""
26582658 
2659 # Generally best practice to use a different model to evaluate than the model used to generate the evaluated output
2659 # Generally best practice to evaluate with a different model from the one used to generate the evaluated output
26602660 response = client.messages.create(
26612661 model="claude-opus-5-5",
26622662 max_tokens=1024,
from line 2748
27482748 5: Perfectly utilizes context
27492749 Output only the number and nothing else.`;
27502750 
2751 // Generally best practice to use a different model to evaluate than the model used to generate the evaluated output
2751 // Generally best practice to evaluate with a different model from the one used to generate the evaluated output
27522752 const response = await client.messages.create({
27532753 model: "claude-opus-5-5",
27542754 max_tokens: 1024,
from line 2829
28292829 Output only the number and nothing else.
28302830 """;
28312831 
2832 // Generally best practice to use a different model to evaluate than the model used to generate the evaluated output
2832 // Generally best practice to evaluate with a different model from the one used to generate the evaluated output
28332833 var response = await client.Messages.Create(new MessageCreateParams
28342834 {
28352835 Model = Model.ClaudeOpus5_5,
from line 2940
29402940 5: Perfectly utilizes context
29412941 Output only the number and nothing else.`, conversationText.String(), modelOutput)
29422942 
2943 // Generally best practice to use a different model to evaluate than the model used to generate the evaluated output
2943 // Generally best practice to evaluate with a different model from the one used to generate the evaluated output
29442944 response, err := client.Messages.New(context.Background(), anthropic.MessageNewParams{
29452945 Model: anthropic.ModelClaudeOpus5_5,
29462946 MaxTokens: 1024,
from line 3029
30293029 5: Perfectly utilizes context
30303030 Output only the number and nothing else.""".formatted(conversationText, modelOutput);
30313031 
3032 // Generally best practice to use a different model to evaluate than the model used to generate the evaluated output
3032 // Generally best practice to evaluate with a different model from the one used to generate the evaluated output
30333033 var params = MessageCreateParams.builder()
30343034 .model(Model.CLAUDE_OPUS_5_5)
30353035 .maxTokens(1024L)
from line 3100
31003100 Output only the number and nothing else.
31013101 PROMPT;
31023102 
3103 // Generally best practice to use a different model to evaluate than the model used to generate the evaluated output
3103 // Generally best practice to evaluate with a different model from the one used to generate the evaluated output
31043104 $response = $client->messages->create(
31053105 model: Model::CLAUDE_OPUS_5_5,
31063106 maxTokens: 1024,
from line 3187
31873187 Output only the number and nothing else.
31883188 PROMPT
31893189 
3190 # Generally best practice to use a different model to evaluate than the model used to generate the evaluated output
3190 # Generally best practice to evaluate with a different model from the one used to generate the evaluated output
31913191 response = client.messages.create(
31923192 model: Anthropic::Model::CLAUDE_OPUS_5_5,
31933193 max_tokens: 1024,
Feedback