DeepSWE
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
claude-sonnet-5Closed. Same 1M / 128k window as Opus 5 and Fable 5. OpenRouter catalog created unix 1782843083 (30 Jun 2026).
Anthropic pricing.md (19 Aug 2026) says the $2 / $10 introductory rate is now the standard price and the scheduled $3 / $15 increase will not occur.
Use Sonnet 5 as the everyday Claude. AA Intelligence Index 55; vals hero 59.61% ±1.15. Escalate to Opus or Fable only after this SKU failed. We do not invent a DeepSWE percent. The 13 Aug family notes name Fable and Opus, not Sonnet.
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
vals.ai Accuracy Rankings hero for Sonnet 5, fetched 19 Aug 2026: 59.61% ±1.15. Not DeepSWE.
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.
Anthropic does not publish Sonnet 5 weights. No HF Files button. Get Plus is hosted inference.
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.
Continuum hosts claude-sonnet-5 on the 19 Aug 2026 bundled allowlist, with Opus 5 and Fable 5.
claude-sonnet-5
click to select
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.
No DeepSWE $/task: that board has no Sonnet 5 row.
Official Anthropic + OpenRouter catalog, 19 Aug 2026: $2 / $10 per million. Cache read $0.20 /M. Cache write $2.50 /M (1-hour write $4 official). Opus is $5 / $25. Fable is $10 / $50.
On a Claude plan? The plan picker models the weekly caps.
Artificial Analysis Intelligence Index 55 at max, fetched 19 Aug 2026. Same page: 79 output tokens/s; $4,010.51 to run the Index. The tile is the published integer 55.
| Claim | Source | As of |
|---|---|---|
| Official Sonnet 5 $2 / $2.50 5m write / $4 1h write / $0.20 hits / $10; $2/$10 now standard | Anthropic pricing.md | 2026-08-19 |
| OR catalog $2 / $10, cache r/w $0.20 / $2.50, search $0.01, 1,000,000 / 128,000, created 1782843083 | OpenRouter catalog | 2026-08-19 |
| AA Index 55 (max); 79 tok/s; $4,010.51 Index eval | Artificial Analysis Claude Sonnet 5 | 2026-08-19 |
| vals Accuracy 59.61% ±1.15 | vals.ai Accuracy Rankings 2026-08-19 | 2026-08-19 |
| Hosted id claude-sonnet-5 | Continuum HostedKeyProvider bundled catalog | 2026-08-19 |
| 1.08T week tokens (+5% WoW) | OpenRouter rankings This Week | 2026-08-19 |
| OpenRouter id anthropic/claude-sonnet-5, context 1,000,000 | 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 Anthropic's model family with Claude Opus 5 (Fast).
No. Anthropic pricing.md on 19 Aug says $2 / $10 is now the standard price and the scheduled increase will not occur.
The 13 Aug official-board family notes name Fable 5 and Opus 5, not Sonnet 5. Omitting is the rule.
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.
Verified against the live public allowlist on 2026-08-19. Base URL is https://continuumcode.ai/v1. Keys are cont_sk_ from Settings, Account, Inference API. Personal keys need Plus or above.
curl https://continuumcode.ai/v1/chat/completions \
-H "Authorization: Bearer $CONTINUUM_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"claude-sonnet-5","messages":[{"role":"user","content":"Review this diff."}]}'