Comparing
mubashir1osmani:fix-gpt-5.4
(23c7e99
) withmain
(40d4e79
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py+2%
148.9 µs146.5 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py+2%
88.6 µs87.1 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py-2%
1.7 ms1.7 ms
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py+1%
144.9 µs143 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py+1%
150.6 µs149.2 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
542.9 µs540.6 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
187.3 µs186.7 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
238.8 µs238 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
85.2 µs85.4 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
142.2 µs142.3 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
417.7 µs417.4 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
570.2 µs570.8 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
87.5 µs87.5 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
542.2 µs542.5 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
85.7 µs85.7 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py0%
83.8 µs83.8 µs
Commits
Click on a commit to change the comparison rangeBase
main
40d4e79
+0.28%
fix gpt-5.4 pricing
23c7e99
5 months ago
by mubashir1osmani