Inkling-Small
Inkling-Small (Thinking Machines) was released on Jul 15, 2026. In the Epoch AI capability ranking (ECI), it ranks #54 out of 267 models, with 150.18. On Arena, which measures human preference in blind comparisons, it has 1,463 ELO points (#101).
Where Inkling-Small stands out and where it falls behind, by the numbers
Inkling-Small has published results on 12 tests compiled by Epoch AI. The yardstick here is its generation: its position among the models released between Oct 18, 2025 and Oct 13, 2026 that took the same test. Against the whole archive, which includes 2023 models, a recent release lands near the top of almost everything, and that says nothing.
Where it stands out
Tests where it sits in the top third of its own generation.
It is not in the top third of its generation on any test with 6 or more models compared.
Where it falls behind
Tests where it sits in the bottom half of its own generation.
See all 12 tests, one by one
| Test | Score | In its generation | Overall | Test record |
|---|---|---|---|---|
| GPQA Diamond | 88.5% | #47 / 80 | #48 / 173 | 96.4% Gemini 4 Argon |
| AIME 2024 and 2025 (OTIS) | 90.0% | #55 / 82 | #57 / 168 | 100.0% GPT-5.5 |
| CritPt | 8.3% | #53 / 79 | #54 / 112 | 32.3% GPT-5.6 Sol |
| SciCode | 49.7% | #50 / 76 | #50 / 104 | 66.9% Claude Opus 5.5 |
| Frontiermath Tiers 1 3 V2 | 46.3% | #49 / 67 | #53 / 86 | 93.7% GPT-6 Astra |
| ARC-AGI 2 | 40.1% | #37 / 50 | #37 / 83 | 95.0% GPT-6 Astra |
| WebDev Arena | 1,407 | #58 / 75 | #59 / 82 | 1,820 Claude Opus 5.5 |
| ARC-AGI | 84.0% | #38 / 50 | #38 / 81 | 98.5% Claude Fable 5 |
| SimpleQA Verified | 19.1% | #60 / 63 | #71 / 81 | 76.0% Gemini 4 Argon |
| Game puzzles | 6.0% | #62 / 62 | #73 / 77 | 84.0% GPT-6 Astra |
| ProofBench | 6.0% | #63 / 70 (tied with 1) | #67 / 74 | 100.0% Claude Fable 5.1 |
| Frontiermath Tier 4 V2 | 17.1% | #44 / 57 (tied with 4) | #47 / 67 | 100.0% GPT-6.1 Sol |
For each test, the model's best effort level counts, as in the ranking. Source of the scores: Epoch AI, under CC BY 4.0.
What to compare Inkling-Small with
The models from other labs closest in capability and released in the same period, at most two per lab. Click any of them to see its page.
| Model | Lab | ECI | ELO | LiveBench | Release |
|---|---|---|---|---|---|
| Kimi K2.6 | Moonshot | 150.92 | 1,521 | 70.5 | Apr 20, 2026 |
| Inkling-Small | Thinking Machines | 150.18 | 1,463 | n/a | Jul 15, 2026 |
| Claude Opus 4.5 | Anthropic | 150.17 | 1,504 | 72.6 | Nov 24, 2025 |
| GLM-5.1 | Z.ai (Zhipu AI) | 149.99 | 1,514 | n/a | Apr 7, 2026 |
| Kimi K2.7 Code | Moonshot | 149.87 | n/a | 68.4 | Jun 12, 2026 |
| GPT-5.1 | OpenAI | 149.76 | 1,495 | n/a | Nov 13, 2025 |
| Qwen 3.6 Max (Preview) | Alibaba | 149.24 | 1,488 | n/a | Apr 20, 2026 |
Inkling-Small or Claude Opus 4.5?
Claude Opus 4.5 is the model from another lab closest to Inkling-Small in capability. Across the 10 tests both took, this is the score:
| Test | Inkling-Small | Claude Opus 4.5 |
|---|---|---|
| ProofBench | 6.0% | 36.0% |
| Game puzzles | 6.0% | 22.0% |
| Frontiermath Tier 4 V2 | 17.1% | 4.9% |
| SimpleQA Verified | 19.1% | 45.7% |
| Frontiermath Tiers 1 3 V2 | 46.3% | 34.4% |
| ARC-AGI 2 | 40.1% | 37.6% |
| WebDev Arena | 1,407 | 1,495 |
| ARC-AGI | 84.0% | 80.0% |
| AIME 2024 and 2025 (OTIS) | 90.0% | 86.1% |
| GPQA Diamond | 88.5% | 86.0% |
Unweighted score: each test counts one point, whether math or coding. The dot marks who did better on each row.
Other models from Thinking Machines
The models from the same lab closest in time, newest first.
| Model | Release | ECI | ELO | LiveBench | Access |
|---|---|---|---|---|---|
| Inkling-Small | Jul 15, 2026 | 150.18 | 1,463 | n/a | Open weights (unrestricted) |
| Inkling | Jul 15, 2026 | 148.59 | 1,492 | 71.9 | Open weights (unrestricted) |
Have you used Inkling-Small? Rate it
Users' opinion, not measurement: the rating is kept apart from the ranking and does not move anyone's position. One vote per browser, no sign-up, and you can change your rating later.
What people ask about Inkling-Small
Where does Inkling-Small rank among AI models?
In the ROO3 AI Benchmark, ordered by the Epoch AI ECI, Inkling-Small ranks #54 out of 267 models, with an ECI of 150.18. The ECI is a composite index that combines several hard benchmarks into a single scale. The position changes when a new model comes out, and the page is refreshed six times a day.
Is Inkling-Small better than Claude Opus 4.5?
Across the 10 tests both models took and Epoch AI compiled, Inkling-Small comes out ahead on 6, behind on 4 and tied on 0. It is a test-by-test count with no weighting: a win in math counts the same as a win in coding. To choose between the two, look at the tests that resemble your own use.
Where do the numbers on this page come from?
From the same three sources as the ranking, all openly licensed: Epoch AI (ECI and individual tests, CC BY 4.0), Arena (human-preference ELO, CC BY 4.0) and LiveBench (overall average, CC BY-SA 4.0). ROO3 does not measure any model. When the page shows a figure published by the maker itself, it appears in the written analysis, labeled as the maker's, and never enters the ranking.
Where each number comes from
Epoch AI, "AI Benchmarking Hub". Published at epoch.ai. Data under the CC BY 4.0 licence, reordered by roo3.co.
The Arena (LMArena) leaderboard, from the public lmarena-ai/leaderboard-dataset on Hugging Face, under the CC BY 4.0 licence. We are not affiliated with the Arena.
LiveBench, by the LiveBench team, published at livebench.ai under the CC BY-SA 4.0 license. The overall average is recomputed by roo3.co with the same formula as the website (average of the categories), and those numbers stay under CC BY-SA 4.0. We are not affiliated with LiveBench.
← See the full ranking