DeepSWE
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
30B-A3B open NVIDIA sibling. 836B this week (+999% WoW) on the free leaderboard row. This card is the paid catalog slug nvidia/nemotron-3.5-lightning at $0.08 / $0.20. AA 24. Hosted NVIDIA is Ultra and Super free, not Lightning. No DeepSWE or vals row.
Open weights at nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16. Catalog created unix 1786452751 (11 Aug 2026). 1,048,576 / 131,072.
Week-board #18 is the free Lightning lane (836B, +999% WoW). This card’s OpenRouter id is the paid slug. Do not invent a :free hosted id.
Use Lightning when you want this 30B-A3B checkpoint. AA Intelligence Index 24. We do not invent a DeepSWE percent. Hub API 19 Aug 2026: 176 likes, 88,402 downloads.
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
We did not open a vals.ai card for this identity. Chip omitted.
Ranked view: Best coding models: the independent leaderboard puts this row and every other card that carries an independent coding score on one board, with the confidence intervals left visible.
Copied from AA or vals HTML we opened. 0.0% placeholder bars are omitted. Do not average these into the hero tiles, and do not invent CI, $/task, or steps for Artificial Analysis.
Plus is $25/mo with $25 weekly hosted usage. The Mac app stays free with your own keys. Get Plus is not Download for Mac.
Community quants: Community quants are community.
This is the model repo, not Download for Mac. Downloads and likes from the Hugging Face API on 2026-08-19.
Not listed as a Continuum hosted id. OpenRouter nvidia/nemotron-3.5-lightning.
We list first-party and OpenRouter, plus Continuum only when the live public allowlist named the id. This is not a 15-host routing table.
OpenRouter catalog 19 Aug 2026: $0.08 / $0.20, cache read $0.04 /M. AA prints $0.07 / $0.22, 313 tok/s, $71.45 Index eval. Cite both. No DeepSWE $/task.
Artificial Analysis Intelligence Index 24, fetched 19 Aug 2026. Same page: 313 tok/s; $71.45 Index eval. AA $0.07 / $0.22 vs OR $0.08 / $0.20.
| Claim | Source | As of |
|---|---|---|
| OR catalog $0.08 / $0.20, cache $0.04, 1,048,576 / 131,072, created 1786452751 | OpenRouter catalog | 2026-08-19 |
| AA Index 24; $0.07 / $0.22; 313 tok/s; $71.45 Index eval | Artificial Analysis Nemotron 3.5 Lightning | 2026-08-19 |
| HF likes 176; downloads 88,402; usedStorage 65,844,953,520; safetensors.total 31,577,937,344; created 2026-08-01T06:55:21Z | Hugging Face API | 2026-08-19 |
| 836B week tokens on the free Lightning lane (+999% WoW), #18 | OpenRouter rankings This Week | 2026-08-19 |
| OpenRouter id nvidia/nemotron-3.5-lightning, context 1,048,576 | OpenRouter /api/v1/models | 2026-08-19 |
| HF downloads 88,402 | Hugging Face API nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | 2026-08-19 |
No other card in this cluster shares a published DeepSWE official row we can put next to this one. We will not compare on vendor-blog numbers.
Continue through NVIDIA's model family with Nemotron 3 Super (free).
No. Hosted Super is nvidia/nemotron-3-super-120b-a12b:free. Lightning is nvidia/nemotron-3.5-lightning.
Lab posts pick a harness, an effort, a split, and sometimes a private eval set. DeepSWE publishes the official mini-swe-agent row with cost, tokens, and steps. Scale SWE-bench Pro only counts when the public shared-harness board has a row we can fetch. A higher lab number is usually a different test, not a better one.
No Continuum hosted id is verified for this model, so this page does not invent a curl target. Use the first-party API or the OpenRouter slug nvidia/nemotron-3.5-lightning.