benchmark_stats.json

{
  "total_models": 20,
  "temperatures_tested": [
    0,
    0.5,
    1.0
  ],
  "total_tests": 60,
  "successful_tests": 35,
  "failed_tests": 25,
  "models_with_at_least_one_success": 15,
  "average_response_time": 10.812262760965448,
  "successful_model_ids": [
    "moonshotai/Kimi-K2-Instruct",
    "Qwen/Qwen3-Coder-480B-A35B-Instruct",
    "Qwen/Qwen3-235B-A22B-Instruct-2507",
    "meta-llama/Llama-3.1-8B-Instruct",
    "zai-org/GLM-4.5",
    "deepseek-ai/DeepSeek-R1",
    "zai-org/GLM-4.1V-9B-Thinking",
    "Qwen/Qwen3-235B-A22B",
    "meta-llama/Llama-3.2-3B-Instruct",
    "meta-llama/Meta-Llama-3-8B-Instruct",
    "Qwen/Qwen3-32B",
    "Qwen/Qwen3-4B",
    "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
    "meta-llama/Llama-4-Scout-17B-16E-Instruct",
    "Qwen/Qwen3-30B-A3B"
  ]
}