DeepSWEmini-swe-agent
73%±3%
- bench
- DeepSWE
- version
- v1.1
- split
- public 113 tasks
- harness
- mini-swe-agent
- effort
- max
- n
- 113
- metric
- Pass@1
- value
- 73%
- ci
- ±3%
- $/task
- $8.39
- tokens
- 60k out
- steps
- 61
gpt-5.6-solcodex -m gpt-5.6-sol. See Codex models.Closed. Same family window as Luna and Terra. Effort ladder includes ultra on Codex; DeepSWE cites max.
Requests over 272k prompt tokens bill the whole request at 2x input / 1.5x output on OpenAI’s published surcharge. Continuum pricing.json records that; ccusage does not.
Use Sol when Terra already failed or the task is hard reasoning. DeepSWE official: 73% ±3% at max, $8.39 per task, 60k out, 61 steps. Tight CI, fewer steps than the Claude rows.
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.
gpt-5.6-luna), Terra for balanced work (gpt-5.6-terra). Official DeepSWE row is max.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.
OpenAI does not publish Sol 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 gpt-5.6-sol, plus Terra and Luna, on the 19 Aug 2026 public allowlist.
gpt-5.6-sol
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.
DeepSWE official: $8.39 per task at max (60k out, 61 steps). That is the hero economics number.
Official OpenAI pricing.md, 19 Aug 2026: $5 / $30 per million; cache $0.50 / $6.25 write; ≥272k $10 / $45. Continuum’s rate card matches that official list.
OpenRouter catalog 19 Aug 2026 prints $2.50 / $15 for openai/gpt-5.6-sol. That is a second published table, not a typo of $5 / $30. Luna’s official list is $0.20 / $1.20. Do not paste Sol onto Luna or the reverse.
Artificial Analysis footnote, 19 Aug 2026: about $1.23 per AA task, 66.0 tok/s. The AA tile is Intelligence Index 61. AA did not publish a DeepSWE-style CI or step count we will copy onto the chip. Do not average AA cost with DeepSWE $8.39/task.
| Claim | Source | As of |
|---|---|---|
| DeepSWE 73% ±3% at max | DeepSWE official board | 2026-08-13 |
| Official Sol $5 / $0.50 cached / $6.25 write / $30 out; ≥272k $10 / $1 / $12.50 / $45; Batch Supported | OpenAI pricing.md | 2026-08-19 |
| OR catalog $2.50 / $15 for openai/gpt-5.6-sol (not the official $5 / $30) | OpenRouter catalog | 2026-08-19 |
| Hosted id gpt-5.6-sol | GET /v1/chat/hosted/models/public | 2026-08-19 |
| OpenRouter id openai/gpt-5.6-sol, context 1,050,000 | OpenRouter /api/v1/models | 2026-08-19 |
Same official DeepSWE harness (mini-swe-agent, public 113 tasks), fetched 2026-08-19. Different effort labels are the lab's own setting on that board, shown here rather than normalized.
Continue through OpenAI's model family with GPT-5.6 Terra.
Week tokens measure routing volume. Luna is the flagship card. Sol stays because it is the coding sibling Continuum also hosts.
Official OpenAI pricing.md is $5 / $30. OpenRouter’s catalog row is $2.50 / $15. We cite both. Continuum’s rate card follows the official list.
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":"gpt-5.6-sol","messages":[{"role":"user","content":"Review this diff."}]}'