DeepSWE
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
Open MIT weights at XiaomiMiMo/MiMo-V2.5-Pro. Catalog $0.435 / $0.87, cache read $0.0036 /M, 1,048,576 / 131,072, created unix 1776874273.
Base MiMo-V2.5 is the ranking-week Xiaomi card.
Use Pro when you specifically want this checkpoint. AA 43; vals 40.97% ±1.38. We do not invent a DeepSWE percent. Hub API 19 Aug 2026: 742 likes, 57,658 downloads.
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
vals.ai Accuracy Rankings hero, 19 Aug 2026: 40.97% ±1.38. Base V2.5 on the same board is 46.45% ±1.18. The base card chips 39.91% from its own vals model page.
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 |
|---|---|---|---|---|---|
| AA throughput | 64 tok/s | Printed Speed row. | Artificial Analysis MiMo-V2.5-Pro | 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.
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 xiaomi/mimo-v2.5-pro.
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: $0.435 / $0.87, cache read $0.0036 /M. AA 43 page: 64 tok/s, $98.86 Index eval. No DeepSWE $/task.
Artificial Analysis Intelligence Index 43, fetched 19 Aug 2026. Same page: 64 tok/s; $98.86 Index eval.
| Claim | Source | As of |
|---|---|---|
| OR catalog $0.435 / $0.87, cache $0.0036, 1,048,576 / 131,072, created 1776874273 | OpenRouter catalog | 2026-08-19 |
| AA Index 43; 64 tok/s; $98.86 Index eval | Artificial Analysis MiMo-V2.5-Pro | 2026-08-19 |
| vals Accuracy 40.97% ±1.38 | vals.ai Accuracy Rankings 2026-08-19 | 2026-08-19 |
| HF likes 742; downloads 57,658; usedStorage 1,033,418,613,038; safetensors.total 1,023,244,718,976; MIT; created 2026-04-27T12:52:53Z | Hugging Face API | 2026-08-19 |
| OpenRouter id xiaomi/mimo-v2.5-pro, context 1,048,576 | OpenRouter /api/v1/models | 2026-08-19 |
| HF downloads 57,658 | Hugging Face API XiaomiMiMo/MiMo-V2.5-Pro | 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 Xiaomi's model family with MiMo-V2.5.
Dearer on the 19 Aug catalog. Not better on the published tiles this cluster has for this SKU: AA 43 vs base card 38, vals Accuracy 40.97% vs 46.45% on the shared 19 Aug board. DeepSWE stays on the base card.
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 xiaomi/mimo-v2.5-pro.