DeepSWE
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
Open Llama 4 Community weights, gated on Hugging Face, same gate as Maverick. Catalog hugging_face_id meta-llama/Llama-4-Scout-17B-16E-Instruct. Created unix 1743881519 (5 Apr 2025). 1,310,720 in / 16,384 out.
Maverick is the 400B-A17B / 128E card on this hub (AA 14 on that card). Muse Spark 1.2 is a separate Meta identity, not a Llama 4 weight.
Use Scout when you want the smaller Llama 4 instruct. AA Intelligence Index 10. We do not invent a DeepSWE percent. Hub API 19 Aug 2026: 1,333 likes, 411,931 downloads. File tree 401s without a token: no invented shard list.
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. Official repo is gated.
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 meta-llama/llama-4-scout. No /models/meta-llama/ URL.
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: $0.10 / $0.30 per million, 1,310,720 / 16,384. AA prints $0.18 / $0.66, 136 tok/s, $11.60 Index eval. Cite both. No DeepSWE $/task.
Artificial Analysis Intelligence Index 10, fetched 19 Aug 2026. Same page: 136 tok/s; $11.60 Index eval. AA $0.18 / $0.66 vs OR $0.10 / $0.30.
| Claim | Source | As of |
|---|---|---|
| OR catalog $0.10 / $0.30, 1,310,720 / 16,384, created 1743881519, HF meta-llama/Llama-4-Scout-17B-16E-Instruct | OpenRouter catalog | 2026-08-19 |
| AA Index 10; $0.18 / $0.66; 136 tok/s; $11.60 Index eval | Artificial Analysis Llama 4 Scout | 2026-08-19 |
| HF likes 1,333; downloads 411,931; usedStorage 217,343,257,722; safetensors.total 108,641,793,536; gated; created 2025-04-02T13:34:17Z | Hugging Face API | 2026-08-19 |
| OpenRouter id meta-llama/llama-4-scout, context 1,310,720 | OpenRouter /api/v1/models | 2026-08-19 |
| HF downloads 411,931 | Hugging Face API meta-llama/Llama-4-Scout-17B-16E-Instruct | 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 Meta's model family with Llama 3.1 8B Instruct.
No. Maverick is 400B-A17B / 128E. Scout is 17B-A / 16E. Same Llama 4 family, different invoices and different AA integers.
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 meta-llama/llama-4-scout.