ironbench leaderboard - firmware-agent benchmark

Modelpass@kTaskscontrolfsmioprotocolresilience
glm-4.6v-flash54%134/8 (50%)1/2 (50%)4/4 (100%)0/8 (0%)2/8 (25%)
qwen2.5-7b-instruct54%134/8 (50%)2/2 (100%)3/4 (75%)0/8 (0%)2/8 (25%)
qwen3.5-4b46%131/8 (12%)1/2 (50%)4/4 (100%)1/8 (12%)3/8 (38%)
qwen3.5-9b38%133/8 (38%)0/2 (0%)4/4 (100%)0/8 (0%)1/8 (12%)
zai-org/glm-4.7-flash69%136/8 (75%)1/2 (50%)4/4 (100%)2/8 (25%)4/8 (50%)