Comparing
claude/funny-fermat-xUS28
(8323ea3
) withlitellm_internal_staging
(06f6cfc
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py+2%
80.7 µs79.2 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py-1%
183.4 µs186.1 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py-1%
235.1 µs237.6 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py-1%
1.7 ms1.7 ms
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py+1%
81.5 µs80.7 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py-1%
136.9 µs137.6 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
563.3 µs565.9 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
556.7 µs554.2 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
79.9 µs80.2 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
144.1 µs144.6 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
82.1 µs82.4 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
143 µs142.5 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
413.3 µs414.3 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
80.1 µs80.3 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
558 µs557 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
138.5 µs138.7 µs
Commits
Click on a commit to change the comparison rangeBase
main
06f6cfc
-0.15%
fix(otel): end proxy SERVER span on management-endpoint success without http_request
8323ea3
24 days ago
by claude