whatmodel.sh / Inkling 2 Small (594B-A17B)
Inkling 2 Small (594B-A17B)
↗ share
+ contribute
Inkling 2 Small (594B-A17B) is an open-weights language model from Thinking Machines, released November 2026. Its published size is 594B parameters (17B active per token) and a 1M-token context window. Licence: apache-2.0.
Catalogue identity notes
New, distinct second-generation model, not a revision of inkling-small (266B-A12B, open weights, July 2026). Announced 2026-11-05 ('Today we are introducing our second model generation with Inkling 2 Small'); 594B total / 17B active MoE with image input. Weights published 2026-11-12: Thinking Machines' post carries a 'Nov 12, 2026 Update' saying the weights are available on Hugging Face, at thinkingmachines/Inkling-2-Small (pinned 8361e7a; repository created 2026-11-04 as a placeholder, model uploaded 2026-11-12), Apache-2.0 per the card's front matter, not gated. Also served for inference and fine-tuning on Tinker. No local run command is listed yet. List price not recorded: only the Tinker docs page states it.
Model information sources
Release date ↗ · Weights licence ↗ · Parameter count ↗
Model card 'Parameters: 594B total parameters, 17B active'; 48-layer MoE, 8 of 384 experts per token.
Score within the LMArena (text) comparison set only.
$ how it compares
The LLMs ranked either side of Inkling 2 Small (594B-A17B), out of 897 with a score, then more from Thinking Machines.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 34 | 75±1 | api $2.00/M | |||
| 35 | 75±1 | api $1.50/M | |||
| 36 | 75±1 | api price unknown | |||
| 37 | 75±1 | api $6.00/M +local | |||
| 38 | 75±1 | api $0.17/M +local | |||
| more from Thinking Machines | |||||
| 118 | 68±1 | api $0.64/M +local | |||
| 125 | 67±1 | api $1.73/M +local | |||
$ what it's good at
agent tasks▁▁▃▆█▄▅▅▃▃▂▁ #33 of 319 * · 51% of its score · 5 tests
Beats GPT-5.5, GPT-5.6 Terra, Hy4 preview (770B-A49B) here, though they rank higher overall. Trails GLM-5.3-Flash, Grok 4.7, Qwen3.8 Max (0902) here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena Agent (October 2026 aggregate IPS) | 0.0251 IPS ✎ | ▁▁▁▃▃█▂▁▁▁·▁ beats 44/63 | 51% |
| SWE-bench Verified lab | 82.2% ✎ | ▁▁▁▁▁▁▂▄█▆▁▁ beats 134/140 | — |
| SWE-bench Multilingual lab | 81.2% ✎ | ▁··▂▂▃▆█▃▂▁▁ beats 59/69 | — |
| DeepSearchQA lab | 90.9% ✎ | ▃·▃▃···▃▃··█ beats 6/7 | — |
| JobBench lab | 70.5% ✎ | ▄·▄▄···█···▄ beats 3/5 | — |
coding▁▁▁▃▆▇█▆▆▃▃▁ #22 of 474 * · 31% of its score · 3 tests
Beats GPT-5.6 Sol, Claude Fable 5, GPT-5.5 here, though they rank higher overall. Trails Qwen3.8 Max (0902), Kimi K3 here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena WebDev (Code Arena) | 1647.1 ✎ | ▁▂▄▃▇█▅▇▇▅▂▁ beats 114/134 | 31% |
| SWE-bench Verified lab | 82.2% ✎ | ▁▁▁▁▁▁▂▄█▆▁▁ beats 134/140 | — |
| SWE-bench Multilingual lab | 81.2% ✎ | ▁··▂▂▃▆█▃▂▁▁ beats 59/69 | — |
chat & writing▁▁▁▃▅▄▆█▇▇▇▃ #107 of 405 * · 17% of its score · 1 test
Trails Mistral Large 3 (675B-A41B), Gemma 4 12B, Qwen3-VL 235B-A22B Instruct here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena (text) | 1411.8 ✎ | ▁▁▁▂▃▂▃▆▆▇█▃ beats 259/388 | 17% |
mathnot ranked on this task yet · 1 test
| test | result | vs the others in its run | counts |
|---|---|---|---|
| HMMT February 2026 lab | 95.8% ✎ | ▃▃▁▄▇▇▇█▅▃▃▃ beats 37/38 | — |
vision & documentsnot ranked on this task yet · 2 tests
| test | result | vs the others in its run | counts |
|---|---|---|---|
| CharXiv (reasoning questions) lab | 85.6% ✎ | ▂▄▃▄▅▅▅▅▅█▆▂ beats 98/105 | — |
| ScreenSpot-Pro lab | 83.8% ✎ | ▂▃▅▆██▅▂▃··▂ beats 24/25 | — |
web searchnot ranked on this task yet · 1 test
| test | result | vs the others in its run | counts |
|---|---|---|---|
| DeepSearchQA lab | 90.9% ✎ | ▃·▃▃···▃▃··█ beats 6/7 | — |
other tests3 not in a task · 0.0% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| GPQA Diamond lab | 93.0% ✎ | ▁▁▁▁▂▃▅▆▇▇█▂ beats 313/336 | — |
| LongBench v2 lab | 70.6% ✎ | ▂·▁·▂▂▂▃▃▃█▃ beats 35/35 | — |
| BabyVision with tools lab | 93.7% ✎ | ▄·····▄··▄█▄ beats 4/5 | — |
$ where to run it
Through an API
api · Thinking Machines (Tinker) · price unknown · 1M context · tinker-docs.thinkingmachines.ai ↗
Model repository and documentation: huggingface.co/thinkingmachines ↗
$ how the score was worked out · LMArena leaderboard dataset 99%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
| 3 | 99% | |
| prior · pull toward the middle | 1% | |
| weighted average | = 74.8 |
not counted (10)
| Thinking Machines model card (lab-reported scores) | GPQA Diamond [correct] | 93.0% | fewer than three models have this test yet, or this source ran it for this model alone |
| Thinking Machines model card (lab-reported scores) | HMMT February 2026 [correct] | 95.8% | fewer than three models have this test yet, or this source ran it for this model alone |
| Thinking Machines model card (lab-reported scores) | SWE-bench Verified [correct] | 82.2% | fewer than three models have this test yet, or this source ran it for this model alone |
| Thinking Machines model card (lab-reported scores) | SWE-bench Multilingual [correct] | 81.2% | fewer than three models have this test yet, or this source ran it for this model alone |
| Thinking Machines model card (lab-reported scores) | LongBench v2 [correct] | 70.6% | fewer than three models have this test yet, or this source ran it for this model alone |
| Thinking Machines model card (lab-reported scores) | CharXiv (reasoning questions) [correct] | 85.6% | fewer than three models have this test yet, or this source ran it for this model alone |
| Thinking Machines model card (lab-reported scores) | ScreenSpot-Pro [correct] | 83.8% | fewer than three models have this test yet, or this source ran it for this model alone |
| Thinking Machines model card (lab-reported scores) | BabyVision with tools [correct] | 93.7% | fewer than three models have this test yet, or this source ran it for this model alone |
| Thinking Machines model card (lab-reported scores) | JobBench [correct] | 70.5% | fewer than three models have this test yet, or this source ran it for this model alone |
| Thinking Machines model card (lab-reported scores) | DeepSearchQA [correct] | 90.9% | fewer than three models have this test yet, or this source ran it for this model alone |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json