SvelteBench Visualization

← Back to All Results

Anthropic

▼

claude-3-5-haiku-20241022

▼
Test Status Tests Passed Errors Actions
counter ✅ PASS 4/4 0
View Prompt View Tests
derived ✅ PASS 2/2 0
View Prompt View Tests
each ✅ PASS 2/2 0
View Prompt View Tests
effect ✅ PASS 2/2 0
View Prompt View Tests
hello-world ✅ PASS 2/2 0
View Prompt View Tests

claude-3-5-sonnet-20240620

▼
Test Status Tests Passed Errors Actions
counter ✅ PASS 4/4 0
View Prompt View Tests
derived ✅ PASS 2/2 0
View Prompt View Tests
each ❌ FAIL 0/0 1
View Prompt View Tests
effect ❌ FAIL 0/0 1
View Prompt View Tests
hello-world ✅ PASS 2/2 0
View Prompt View Tests

claude-3-5-sonnet-20241022

▼
Test Status Tests Passed Errors Actions
counter ✅ PASS 4/4 0
View Prompt View Tests
derived ✅ PASS 2/2 0
View Prompt View Tests
each ❌ FAIL 0/0 1
View Prompt View Tests
effect ✅ PASS 2/2 0
View Prompt View Tests
hello-world ✅ PASS 2/2 0
View Prompt View Tests

claude-3-7-sonnet-20250219

▼
Test Status Tests Passed Errors Actions
counter ✅ PASS 4/4 0
View Prompt View Tests
derived ✅ PASS 2/2 0
View Prompt View Tests
each ❌ FAIL 0/2 2
View Prompt View Tests
effect ✅ PASS 2/2 0
View Prompt View Tests
hello-world ✅ PASS 2/2 0
View Prompt View Tests

claude-3-opus-20240229

▼
Test Status Tests Passed Errors Actions
counter ❌ FAIL 0/0 1
View Prompt View Tests
derived ❌ FAIL 0/2 2
View Prompt View Tests
each ✅ PASS 2/2 0
View Prompt View Tests
effect ❌ FAIL 0/0 1
View Prompt View Tests
hello-world ✅ PASS 2/2 0
View Prompt View Tests

OpenAI

▼

gpt-4o

▼
Test Status Tests Passed Errors Actions
counter ❌ FAIL 0/0 1
View Prompt View Tests
derived ❌ FAIL 0/0 1
View Prompt View Tests
each ✅ PASS 2/2 0
View Prompt View Tests
effect ❌ FAIL 0/0 1
View Prompt View Tests
hello-world ✅ PASS 2/2 0
View Prompt View Tests

o3-mini

▼
Test Status Tests Passed Errors Actions
counter ❌ FAIL 0/0 1
View Prompt View Tests
derived ❌ FAIL 0/0 1
View Prompt View Tests
each ✅ PASS 2/2 0
View Prompt View Tests
effect ❌ FAIL 0/0 1
View Prompt View Tests
hello-world ✅ PASS 2/2 0
View Prompt View Tests