Run of 2025-12-17 15:00:16

24
Models Tested
13
Total Tasks
48.4%
Overall Success Rate
151/312
Passed Combinations

Details

Score Model task10_multiple_tests task11_relationship_classifier task12_need_reply task13_meeting_action_items task14_graph_money_distribution task1_file_list task2_fix_python_syntax task4_web_fetch task5_dedup_contact task6_config_merger task7_log_parser task8_regex_extraction task9_cpp_footguns
92.3% openrouter/openai/gpt-5.2
84.6% openrouter/openai/gpt-5
84.6% openrouter/google/gemini-3-pro-preview
76.9% openrouter/anthropic/claude-haiku-4.5
76.9% openrouter/anthropic/claude-sonnet-4.5
76.9% openrouter/openai/gpt-5-mini
69.2% openrouter/anthropic/claude-opus-4.5
69.2% openrouter/qwen/qwen3-coder
69.2% openrouter/openai/gpt-4.1-mini
61.5% openrouter/openai/gpt-5-nano
61.5% litellm/GLM-4.5-Air-FP8-dev
53.8% openrouter/google/gemini-2.5-pro
46.2% openrouter/x-ai/grok-3-mini
46.2% openrouter/deepseek/deepseek-v3.1-terminus
46.2% openrouter/x-ai/grok-code-fast-1
38.5% openrouter/openai/gpt-oss-20b
30.8% openrouter/openai/gpt-4o-mini
23.1% openrouter/openai/gpt-oss-120b
15.4% openrouter/google/gemini-2.5-flash-preview-09-2025
15.4% openrouter/google/gemini-2.5-flash-lite-preview-09-2025
15.4% openrouter/openai/gpt-4.1-nano
7.7% openrouter/deepseek/deepseek-chat-v3-0324
0.0% litellm/DeepSeek-V3.2-sandbox
0.0% litellm/GLM-4.6-trtllm-sandbox