Comparing
alvinttang:fix/arize-langfuse-otel-pydantic-usage
(a74772c
) withlitellm-oss-staging-04-25-2026
(0beec45
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py-1%
78.8 µs79.4 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py+1%
543.6 µs539.4 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py+1%
1.7 ms1.7 ms
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
543.5 µs541.1 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
79.8 µs80.1 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
79.7 µs79.9 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
413.5 µs412.7 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
143.7 µs143.9 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
183 µs183.3 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
235 µs235.4 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
566.5 µs567.2 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
82.2 µs82.2 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
136.6 µs136.7 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
137.9 µs138 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py0%
80 µs80 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
141.2 µs141.2 µs
Commits
Click on a commit to change the comparison rangeBase
main
0beec45
-0.02%
fix(arize/langfuse_otel): handle Pydantic usage objects without `.get`
a74772c
4 months ago