DeepSWEmini-swe-agent
53%±3%
- bench
- DeepSWE
- version
- v1.1
- split
- public 113 tasks
- harness
- mini-swe-agent
- effort
- xhigh
- n
- 113
- metric
- Pass@1
- value
- 53%
- ci
- ±3%
- $/task
- $2.36
- tokens
- 74k out
- steps
- 96
Context window on the 2026-08-19 OpenRouter row: 1,048,576 tokens.
Max completion tokens were not listed on that row.
Input / output on that row: $1.25 / $4.25 per 1M tokens.
Architecture fields: text+image+file+audio+video->text · Other.
No hugging_face_id on the 2026-08-19 OpenRouter row.
Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks.
When you want the 2026-07-16 catalog SKU, not a later rename.
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.
| Bench | Printed | Note | Source | URL | As of |
|---|---|---|---|---|---|
| GDPval-AA v2 | 43.7% | Printed on the AA Intelligence Evaluations grid for Muse Spark 1.1 (xhigh). Not a DeepSWE chip. Tile effort: xhigh. | Artificial Analysis Muse Spark 1.1 (xhigh) | source | 2026-08-19 |
| τ³-Banking | 31.8% | Printed on the AA Intelligence Evaluations grid for Muse Spark 1.1 (xhigh). Not a DeepSWE chip. Tile effort: xhigh. | Artificial Analysis Muse Spark 1.1 (xhigh) | source | 2026-08-19 |
| Terminal-Bench v2.1 | 77.9% | Printed on the AA Intelligence Evaluations grid for Muse Spark 1.1 (xhigh). Not a DeepSWE chip. Tile effort: xhigh. | Artificial Analysis Muse Spark 1.1 (xhigh) | source | 2026-08-19 |
| SciCode | 58.2% | Printed on the AA Intelligence Evaluations grid for Muse Spark 1.1 (xhigh). Not a DeepSWE chip. Tile effort: xhigh. | Artificial Analysis Muse Spark 1.1 (xhigh) | source | 2026-08-19 |
| Humanity's Last Exam | 46.2% | Printed on the AA Intelligence Evaluations grid for Muse Spark 1.1 (xhigh). Not a DeepSWE chip. Tile effort: xhigh. | Artificial Analysis Muse Spark 1.1 (xhigh) | source | 2026-08-19 |
| GPQA Diamond | 89.8% | Printed on the AA Intelligence Evaluations grid for Muse Spark 1.1 (xhigh). Not a DeepSWE chip. Tile effort: xhigh. | Artificial Analysis Muse Spark 1.1 (xhigh) | source | 2026-08-19 |
| CritPt | 15.1% | Printed on the AA Intelligence Evaluations grid for Muse Spark 1.1 (xhigh). Not a DeepSWE chip. Tile effort: xhigh. | Artificial Analysis Muse Spark 1.1 (xhigh) | source | 2026-08-19 |
| AA-Omniscience Accuracy | 52% | Printed on the AA Intelligence Evaluations grid for Muse Spark 1.1 (xhigh). Not a DeepSWE chip. Tile effort: xhigh. | Artificial Analysis Muse Spark 1.1 (xhigh) | source | 2026-08-19 |
| AA-LCR | 81.3% | Printed on the AA Intelligence Evaluations grid for Muse Spark 1.1 (xhigh). Not a DeepSWE chip. Tile effort: xhigh. | Artificial Analysis Muse Spark 1.1 (xhigh) | source | 2026-08-19 |
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.
Closed API SKU. The 2026-08-19 OpenRouter row lists pricing and context; there is no official Hugging Face weight dump on that row.
Lab card and OpenRouter listing only. No Hugging Face Files button, because there is no official repo to point at.
Fetched OpenRouter catalog on 2026-08-19. hugging_face_id was empty.
OpenRouter slug meta/muse-spark-1.1 on the 2026-08-19 catalog.
First party: https://www.llama.com/.
Not on the Continuum host list fetched 2026-08-19.
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 2026-08-19: $1.25 in / $4.25 out per 1M tokens. Context 1,048,576 in.
No separate internal-reasoning price on that row.
| Claim | Source | As of |
|---|---|---|
| DeepSWE 53% ±3% at xhigh | DeepSWE official board | 2026-08-19 |
| OpenRouter id meta/muse-spark-1.1; context 1048576; created 1784215741; $1.25 / $4.25 per 1M | OpenRouter /api/v1/models | 2026-08-19 |
| DeepSWE 53% ±3% at xhigh; $2.36/task | DeepSWE official mini-swe-agent board | 2026-08-19 |
| AA Intelligence Index 53 (xhigh); 9 printed Index benches | Artificial Analysis model page | 2026-08-19 |
| OpenRouter id meta/muse-spark-1.1, context 1,048,576 | OpenRouter /api/v1/models | 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 3.3 70B Instruct.
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/muse-spark-1.1.