DeepSWE
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
Closed. OpenRouter catalog 19 Aug 2026: $2 / $12, cache read $0.20 /M, cache write $0.375 /M, web search $0.014/request, 1,048,576 / 65,536, created unix 1771509627.
google/gemma-4-31b is missing from that catalog. The live instruct SKU is google/gemma-4-31b-it. Hosted Google remains gemini-3.5-flash and gemma-4-31b-it:free.
Use 3.1 Pro Preview when you want the live Google Pro sibling. The only published coding tile on this cluster is vals Accuracy 41.90% ±1.17. AA 404s. DeepSWE family notes name 3.6 / 3.7 Flash, not this Pro.
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
No Intelligence Index integer fetched for this identity. Chip omitted.
vals.ai Accuracy Rankings hero, 19 Aug 2026: 41.90% ±1.17. Only published coding tile for this SKU on this cluster.
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 |
|---|---|---|---|---|---|
| OpenRouter list pair | $2 / $12 per 1M | Catalog row. AA page 404s. | OpenRouter catalog | 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.
Google does not publish 3.1 Pro Preview weights. No HF Files button.
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.
Not listed as a Continuum hosted id.
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: $2 / $12 per million. No DeepSWE $/task. No AA cost table: that page 404s.
| Claim | Source | As of |
|---|---|---|
| OR catalog $2 / $12, cache $0.20 / $0.375 write, search $0.014, 1,048,576 / 65,536, created 1771509627 | OpenRouter catalog | 2026-08-19 |
| vals Accuracy 41.90% ±1.17 | vals.ai Accuracy Rankings 2026-08-19 | 2026-08-19 |
| AA /models/gemini-3.1-pro-preview 404 | Artificial Analysis | 2026-08-19 |
| OpenRouter id google/gemini-3.1-pro-preview, 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 Google's model family with Gemini 3.5 Flash.
google/gemma-4-31b is not in the 19 Aug catalog. The owner asked for whichever of gemini-3.1-pro-preview or gemma-4-31b is live and leading. Pro is the live paid sibling.
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 google/gemini-3.1-pro-preview.