Inkling holds #9 among open models, with Bash Recovery as its clear strength
arena · x · 2026-07-21
Inkling is now ranked #9 among open models and #30 overall in Agent Arena.
- Best spot: Bash Recovery at #16 with +6.4% net improvement.
- Weak spots: Praise vs Complaint (#38, -18.0%), Steerability (#35, -10.4%), and Confirmed Task Success (#29, -5.6%).
- Tool hallucination is roughly flat at #35 (-0.9%).
- The post is a compact snapshot of Inkling’s strengths and weaknesses in long-horizon agent tasks.
Related event: Thinking Machines' Inkling Debuts at 9th in Open-Weight on Agent Arena(3 posts)→
More from Models
- BullshitBench update: GPT-6-Astra beats all prior OpenAI models but still trails Anthropic — scaling01 · 2026-09-11
- Astra Scores 83% on GauntletBench, First Computer-Use Agent to Beat Human Baseline — ducha_aiki · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11