Inkling-Small
by Thinking Machines Lab · Model · Language & code models
promising
Strong open model for coding and agent work, but large and newly released
Inkling 2 Small open weights are now on the Hugging Face Hub
AccessOpen weightsPrice$0.3 in · $1 out per M tokensContext1,049K tokensNeeds~532 GB; smallest build ~160 GBDownloadabout 393 GB; 4-bit quants need about 160 GBLicenseApache 2.0
Why we say so
Arena puts Inkling-2-Small second on agent tasks and third on web development among open weights, behind Kimi K3.1, and MathArena has it top on BrokenArXiv. SpeedRunBench has it clearing a game level ahead of Opus 5 and GPT-5.6 Sol, a single narrow test. The claim that it cheats less than most models comes from its own team, and there is no hands-on review yet.
Ranks #2 for agents (open weights) · #3 for web development (open weights)
Evidence
- Nov 17Cleared SuperTux 1-1 in 1,988 frames on SpeedRunBench, ahead of Opus 5 and GPT-5.6 Sol
- Nov 15#2 on Arena agent among open weights
- Nov 15#3 on Arena webdev among open weights (1644)
- Nov 14
- Nov 14#1 US open model on Code Arena WebDev at 1647; #2 open on Agent Arena at $0.26 per task; top open on MathArena BrokenArXiv
Show all 14
- Nov 13
- Nov 11#3 on Arena webdev among open weights (1647)
- Aug 2Inkling Small: omnimodal (text, audio, image, video), 276B total with 12B active, about a quarter of full Inkling; 532 GB
- Aug 2Holds up against DeepSeek V4 Flash (old version) and GPT-6 Luna; its edge is audio input, which those lack
- Aug 2One point below full Inkling on Artificial Analysis, but behind the latest DeepSeek V4 Flash in intelligence
- Jul 30Converted a form image to structured JSON quickly and without missed fields; vision and audio judged good quality
- Jul 30Claimed to match or beat the larger Inkling on reasoning and agentic coding tasks, with 12B vs 41B active parameters
- Jul 19Open-weights multimodal MoE: ~975B total, 41B active, 1M context, trained on 45T tokens of text, image, audio and video
- Jul 19Trails GLM 5.2 and Kimi K3 on Artificial Analysis and is far slower than MiniMax M3 and GLM 5.2; strength is audio and vision
Cost to run
Alternatives
Made for Inkling-Small