Inkling 2 Mini
Thinking Machines' small open-weights multimodal model joins the catalog. A 26.4B looped MoE with 1M context.
Open Inkling 2 Mini
thinkingmachines/inkling-2-mini is Thinking Machines Lab's smallest second-generation model. It is a 26.4B-parameter mixture-of-experts transformer with 3.4B active parameters and a 1M-token context, trained and deployed natively in NVFP4. Its middle layers run three times per token, which the lab calls looping. That gives it more reasoning per token without more parameters. It leads open-weights models under 100B on agentic coding and runs in about 20GB, small enough for a laptop.
Call it with your own key. AnyRouter adds no per-token charge List price is $0.15 per 1M input and $0.50 per 1M output.
import { createAnyRouter } from "@anyr/ai-sdk-provider"
import { generateText } from "ai"
const anyrouter = createAnyRouter()
const { text } = await generateText({
model: anyrouter("thinkingmachines/inkling-2-mini"),
prompt: "Summarise what makes a looped transformer different from a normal one.",
})
console.log(text)anyr claude --model "thinkingmachines/inkling-2-mini"Inkling 2 Mini vs open-weight peers
Thinking Machines' Inkling 2 Mini against the four models its launch post compares it with, across coding, agentic search, vision, reasoning and safety, plus the independent evals our catalog holds.
| Vendor benchmarks | Inkling 2 Mini | Gemma 4 31B | Muse Glimmer 30B | Qwen3.8-27B | Nemotron 3.5 Super VL 120B A12B |
|---|---|---|---|---|---|
| Model info | |||||
| Inkling 2 Mini has 3.4B unique active parameters. The vendor's 'activated' column below counts weight activations per token (5.4B), which includes the three loop passes. | |||||
| Params (B)activated per token (incl. loops) / total | 5.4/26.4 | 30.7/30.7 (Highest reported score in this row) | 30.0/30.0 (Second-highest reported score in this row) | 27.0/27.0 | 12.0/124.5 |
| Third party index | |||||
| AA Index (v5.0) | 20.1 (Highest reported score in this row) | 4.4 | 6.3 | 20.1 (Highest reported score in this row) | 13.6 (Second-highest reported score in this row) |
| Vals Index (v2.2) | 46.5% (Highest reported score in this row) | – | – | – | 29.8% (Second-highest reported score in this row) |
| Coding and autoresearch | |||||
| FrontierCode v2.0stirrup v0.2.1 | 15.1% (Highest reported score in this row) | 0.0% | 1.5% | 14.9% (Second-highest reported score in this row) | 6.1% |
| DeepSWE v1.1mini-swe-agent v2.4.6 | 48.2% (Highest reported score in this row) | 0.3% | 4.4% | 42.2% (Second-highest reported score in this row) | 24.7% |
| Terminal Bench v4.0mini-swe-agent v2.4.6 | 5.6% (Highest reported score in this row) | 0.0% | 0.5% (Second-highest reported score in this row) | 5.6% (Highest reported score in this row) | 0.0% |
| Terminal Bench v2.1Inkling 2 Mini in pi v0.83.0 | 71.6% (Second-highest reported score in this row) | 43.4% | 51.7% | 73.0% (Highest reported score in this row) | 60.7% |
| SWEBench Pro v2 (Hard)mini-swe-agent v2.4.6 | 77.9% (Highest reported score in this row) | 14.2% | 44.3% | 73.8% (Second-highest reported score in this row) | 44.1% |
| SWEBench MultilingualInkling 2 Mini with bash only | 73.7% (Highest reported score in this row) | 43.0% | 66.9% | 70.0% (Second-highest reported score in this row) | 67.7% |
| SWEBench Verifiedbash only | 79.2% (Highest reported score in this row) | 46.1% | 76.0% | 77.8% (Second-highest reported score in this row) | 71.1% |
| Vibe Code Bench v1.1openhands (vals) | 77.9% (Highest reported score in this row) | – | – | 64.9% (Second-highest reported score in this row) | 3.5% |
| PMPP-Hard (AUC, 0-10h)pi v0.83.0 | 455.8 (Highest reported score in this row) | – | – | 262.5 (Second-highest reported score in this row) | – |
| Agentic search, tool use and knowledge work | |||||
| BrowseCompInkling 2 Mini with compaction | 79.0% (Highest reported score in this row) | 37.0% | 63.9% | 61.6% | 78.9% (Second-highest reported score in this row) |
| DeepSearchQAInkling 2 Mini with compaction | 85.3% (Highest reported score in this row) | 61.7% | 74.6% | 79.7% (Second-highest reported score in this row) | 77.7% |
| MCP AtlasPublic | 82.7% (Highest reported score in this row) | 54.2% | 75.5% | 77.3% (Second-highest reported score in this row) | 67.7% |
| AA-Briefcase v1.1 | 1263.0 (Second-highest reported score in this row) | 369.0 | 478.0 | 1391.0 (Highest reported score in this row) | 999.0 |
| GDPVal-AA v2.1 | 1319.0 (Second-highest reported score in this row) | 627.0 | 792.0 | 1427.0 (Highest reported score in this row) | 1162.0 |
| JobBench | 49.6% (Highest reported score in this row) | 8.2% | 16.1% | 33.4% | 36.5% (Second-highest reported score in this row) |
| AutomationBench-AA v1.0.6 | 41.8% (Second-highest reported score in this row) | 4.9% | 6.8% | 48.2% (Highest reported score in this row) | 14.8% |
| EnterpriseOps-Gym | 42.0% (Second-highest reported score in this row) | 28.4% | 34.7% | 44.2% (Highest reported score in this row) | 28.1% |
| Vals Finance Index | 50.1% (Highest reported score in this row) | – | – | – | 41.0% (Second-highest reported score in this row) |
| AA-AnalystAgent | 46.3% (Highest reported score in this row) | – | 20.0% (Second-highest reported score in this row) | – | – |
| Diligence Benchbest harness | 48.6% (Highest reported score in this row) | – | 40.9% | 46.4% (Second-highest reported score in this row) | 45.0% |
| Vision interpretation and creation | |||||
| GDP.pdf | 16.8% (Highest reported score in this row) | 6.0% | 11.8% | 16.4% (Second-highest reported score in this row) | 8.0% |
| PerceptionBench | 57.5% (Highest reported score in this row) | 40.7% | 42.8% | 52.4% (Second-highest reported score in this row) | 36.8% |
| MMMU Prostandard 10 | 74.9% (Second-highest reported score in this row) | 73.4% | 74.3% | 76.3% (Highest reported score in this row) | 72.3% |
| OmniDocBench v1.6 | 92.8% (Highest reported score in this row) | 82.5% | 90.4% | 91.5% (Second-highest reported score in this row) | 77.9% |
| ScreenSpot Prooriginal / with Python | 76.5/87.7% (Highest reported score in this row) | 5.9%/– | 75.4%/– (Second-highest reported score in this row) | 57.6/78.9% | 43.5%/– |
| Chartographyoriginal / with Python | 22.1/72.5% (Highest reported score in this row) | 12.0/11.8% | 17.4/25.1% (Second-highest reported score in this row) | 12.2/52.1% | 9.7/29.3% |
| ZeroBench (main)original / with Python | 17.0/34.0% (Highest reported score in this row) | 9.0/12.0% | 9.0/17.0% | 12.0%/– (Second-highest reported score in this row) | 11.0/12.0% |
| MuirBench | 77.5% (Second-highest reported score in this row) | 72.3% | 77.6% (Highest reported score in this row) | 65.9% | 72.7% |
| BVB | 68.4% (Second-highest reported score in this row) | 47.0% | 50.5% | 70.7% (Highest reported score in this row) | 52.1% |
| Reasoning, knowledge and epistemics | |||||
| HLE-Diamond | 15.2% (Second-highest reported score in this row) | 7.2% | 9.1% | 15.3% (Highest reported score in this row) | 8.8% |
| CritPt v2full / hard | 31.4/17.0% (Second-highest reported score in this row) | –/4.0% | –/7.0% | 10.6/4.0% | 36.9/13.5% (Highest reported score in this row) |
| Apex 2025 | 34.4% (Highest reported score in this row) | 5.2% | 4.2% | 18.8% | 22.9% (Second-highest reported score in this row) |
| ARC-AGIv1 / v2 | 84.5/49.3% (Second-highest reported score in this row) | – | – | 87.5/42.4% (Highest reported score in this row) | 22.7/1.5% |
| LongBench v2 | 66.9% (Highest reported score in this row) | 52.9% | 33.1% | 52.3% | 62.1% (Second-highest reported score in this row) |
| GraphWalks BFS256K | 69.7% (Highest reported score in this row) | – | – | 50.4% | 63.3% (Second-highest reported score in this row) |
| MRCR v28-needle 256K-512K | 46.4% (Highest reported score in this row) | – | – | 38.0% (Second-highest reported score in this row) | 5.7% |
| AA-Omniscience v1.1score | -8.6 | -48.5 | -32.2 | -6.4 (Second-highest reported score in this row) | -2.9 (Highest reported score in this row) |
| AA-Omniscience v1.1non-hallucination rate | 63.4% | 14.5% | 16.4% | 71.4% (Highest reported score in this row) | 69.5% (Second-highest reported score in this row) |
| ComplexConstraints v1.1openhands v1.45.0 | 33.4% (Second-highest reported score in this row) | 31.6% | 35.6% (Highest reported score in this row) | 30.1% | 30.1% |
| Safety and alignment | |||||
| FORTRESSadversarial public | 89.5% (Second-highest reported score in this row) | 67.8% | 90.3% (Highest reported score in this row) | 78.8% | 79.6% |
| FORTRESSbenign public | 96.4% | 97.6% (Second-highest reported score in this row) | 89.1% | 97.8% (Highest reported score in this row) | 92.7% |
| StrongREJECTnone | 97.8% | 98.1% | 99.0% (Second-highest reported score in this row) | 99.0% (Second-highest reported score in this row) | 99.4% (Highest reported score in this row) |
| Misbehavior (internal)lower is better | 9.8% (Highest reported score in this row) | 27.6% (Second-highest reported score in this row) | 46.4% | 57.7% | 52.8% |
| Covert misbehavior (internal)lower is better | 8.3% (Highest reported score in this row) | 24.3% (Second-highest reported score in this row) | 45.6% | 33.2% | 43.4% |
| Destructive actions (internal)lower is better | 10.2% (Highest reported score in this row) | 75.8% | 68.8% | 35.2% (Second-highest reported score in this row) | 65.6% |
Coding score against theoretical decoding speed for models under 100B total parameters.
Decoding speed is a theoretical ceiling at 614 GB/s with BF16 weights, batch size one, including repeated reads across loops. Evaluation setups vary by model. Source: Introducing Inkling 2 Mini (Thinking Machines Lab), as of 2026-11-21.
Coding score against theoretical decoding speed for models under 100B total parameters.
Decoding speed is a theoretical ceiling at 614 GB/s with BF16 weights, batch size one, including repeated reads across loops. Evaluation setups vary by model. Source: Introducing Inkling 2 Mini (Thinking Machines Lab), as of 2026-11-21.
Mean score against price or time. Lower and to the left is cheaper or faster; the dashed line joins the models nothing else beats on both.
The mean counts only the percent rows a model reports; (n/total) shows when it misses some. Not plotted (no list price or no score): Muse Glimmer 30B, Nemotron 3.5 Super VL 120B A12B.
How much room each benchmark has left for these models. Headroom is 100% minus the best score here; the grey band runs from the worst to the best model.
Sources: Introducing Inkling 2 Mini (Thinking Machines Lab) (vendor-reported, as of 2026-11-21); catalog benchmarks from Artificial Analysis, Epoch AI. A dash means the source reports no value.
Benchmark data from Epoch AI (CC-BY 4.0).
Updated 2026-11-21.
Playbooks: AI SDK, OpenAI SDK, coding agents, playground.


Related posts
Looking for the full catalog?Muốn xem toàn bộ danh mục?想看完整目录? Browse all modelsXem tất cả model浏览全部模型.