Project Files
benchmark / results / run.log
[2026-07-10T23:03:21.395Z] Starting benchmark run 2026-07-10T23-03-21-395Z
[2026-07-10T23:03:21.428Z] Discovered 8 model(s): local:qwen3.5-4b, local:zai-org/glm-4.6v-flash, local:qwen/qwen3-4b, local:llama-3.2-3b-instruct, local:ibm/granite-4-h-tiny, local:microsoft/phi-4-mini-reasoning, local:qwen/qwen3.5-9b, local:google/gemma-4-e4b
[2026-07-10T23:03:21.431Z] Loading local:qwen3.5-4b (qwen3.5-4b)...
[2026-07-10T23:03:25.402Z] [local:qwen3.5-4b] running arith-1...
[2026-07-10T23:03:49.299Z] [local:qwen3.5-4b] running arith-2...
[2026-07-10T23:04:27.202Z] [local:qwen3.5-4b] running logic-1...
[2026-07-10T23:05:00.787Z] [local:qwen3.5-4b] running needle-haystack...