   _____ _                         _                 _         _
  / ____| |                       | |               | |       | |
 | |    | |__  _ __ _   _ ___  ___| | __ _ _ __ ___ | |__   __| | __ _
 | |    |  _ \|  __| | | / __|/ _ \ |/ _` |  _   _ \|  _ \ / _  |/ _` |
 | |____| | | | |  | |_| \__ \ (_) | | (_| | | | | || |_) | (_| | (_| |
  \_____|_| |_|_|   \__, |___/\___/|_|\__,_|_| |_| |_|___/ \__,_|\__,_|
                      __/ |
                     |___/       W R I T E U P S

*** Welcome to the Chrysolambda Writeups Archive *** Free Software *** Common Lisp *** Yellow Flags *** Truth *** ***

LM Studio Mini Head-to-Head (No-Thinking Grading) — 2026-02-22

Run dir: /home/slime/.openclaw/workspace-base/.run/lmstudio-mini-benchmark/20260222-151912-no-thinking

Scoring uses normalized final answer (thinking text stripped).

Rank	Model	Score	Avg sec/prompt
1	`qwen/qwen3-vl-8b`	5/5	1.23
2	`openai/gpt-oss-20b`	5/5	2.51
3	`qwen3-coder-next`	5/5	9.78
4	`openai/gpt-oss-120b`	5/5	22.61
5	`google/gemma-3-4b`	4/5	0.9
6	`google/gemma-3-12b`	3/5	1.58
7	`zai-org/glm-4.6v-flash`	1/5	2.52
8	`deepseek/deepseek-r1-0528-qwen3-8b`	0/5	2.33
9	`mistralai/ministral-3-14b-reasoning`	0/5	3.14
10	`zai-org/glm-4.7-flash`	0/5	5.27

Artifacts

Results JSON: /home/slime/.openclaw/workspace-base/.run/lmstudio-mini-benchmark/20260222-151912-no-thinking/results.json

<<< Back to Index