Codex vs WorkBuddy — WorkBuddy vs Codex: 2 side-by-side tests
2 posts from X ran OpenAI Codex and Tencent WorkBuddy on the same task, between Oct 19, 2026 and Nov 4, 2026. Models: GPT-6.1 Sol, Hy4, DeepSeek V4.1 Flash 1017, DeepSeek V4.1 Flash. All harness comparisons.
- 1 post states a time for both: OpenAI Codex was faster in it, by ~5.9×.
- None keeps the model fixed: each side ran its own model, so harness and model effects are mixed — not a controlled comparison.
From 2 posts; costs and times as stated by each author, not a controlled benchmark.
Posts
2
Codex vs WorkBuddy, test by test
| Test | Codex: model | WorkBuddy: model | Time (Codex / WorkBuddy) | Author’s pick |
|---|---|---|---|---|
| Pelican on a bicycle, GPT-6.1 Sol vs Hy4@bangbuilds | GPT-6.1 Sol | Hy4 | 4.5 min / 26.6 min | — |
| Pelican test, DeepSeek 1017 in DSH vs WorkBuddy@xueyu1125 | GPT-6.1 Sol | DeepSeek V4.1 Flash 1017 | — | — |
Numbers are as each post states them; “—” means the post gives none. Tests and models differ from row to row.
Codex vs WorkBuddy pricing: plans
From each vendor’s official pricing page (checked 2026-10-19); prices exclude tax and can change. Usage limits differ by plan and model.
API list prices of the models in these tests
| Model | Used with | Input $/1M tokens | Output $/1M tokens |
|---|---|---|---|
| GPT-6.1 Sol | Codex | $2prompts up to 272K tokens | $10prompts up to 272K tokens |
| Hy4 | WorkBuddy | ||
| DeepSeek V4.1 Flash 1017 | WorkBuddy | $0.30peak hours; off-peak is half price | $1.20peak hours; off-peak is half price |
Official API list prices where verified; a blank cell has no verified official price in the archive (older or retired models).
What each test showed
In every test below each side ran its own model, so these are not controlled comparisons of the harnesses alone.
Pelican on a bicycle, GPT-6.1 Sol vs Hy4 — GPT-6.1 Sol in Codex vs Hy4 in WorkBuddy
GPT-6.1 Sol in Codex and Tencent Hy4 in WorkBuddy each make a pelican-riding-a-bicycle animation: 4 min 32 s against 26 min 39 s.
- OpenAI Codex with GPT-6.1 Sol: time 4.5 min.
- Tencent WorkBuddy with Hy4: time 26.6 min.
Note: The poster asks whether the extra 22 minutes are worth it; no winner named.
Posted Nov 4, 2026 by @bangbuilds (@bangbuilds). Post on X · Video and details
Pelican test, DeepSeek 1017 in DSH vs WorkBuddy — GPT-6.1 Sol in Codex vs DeepSeek V4.1 Flash 1017 in WorkBuddy
The author tests the free DeepSeek V4.1 Flash 1017 in WorkBuddy’s overseas version against the same model in DeepSeek Harness, next to an older V4.1 Flash 0910 run in DSH and GPT-6.1 Sol in Codex, all on the pelican on a bicycle. The post also includes DeepSeek Harness.
- DeepSeek Harness with DeepSeek V4.1 Flash 1017 — Top left; labelled "DeepSeek V4.1 Flash 1017(dsh)". Author’s pick.
- DeepSeek Harness with DeepSeek V4.1 Flash — Top right.
- Tencent WorkBuddy with DeepSeek V4.1 Flash 1017 — Bottom left; labelled "DeepSeek V4.1 Flash 1017(Workbuddy)".
- OpenAI Codex with GPT-6.1 Sol — Bottom right; labelled "GPT-6.1 Sol(Codex)".
Verdict from @xueyu1125: The free DeepSeek V4.1 Flash 1017 in WorkBuddy looks watered down and falls well short of the same model in DeepSeek Harness (paraphrased).
Posted Oct 19, 2026 by @xueyu1125 (@xueyu1125). Post on X · Video and details
Codex vs WorkBuddy (WorkBuddy vs Codex): FAQ
Is Codex better than WorkBuddy?
None of the 2 posts names a winner between the two.
Which is faster, Codex or WorkBuddy?
OpenAI Codex, going by the posts' own numbers: it was faster in the one post that gives a time for each side (by ~5.9×). Times are as each author states them; models and settings differ.
Which is cheaper, Codex or WorkBuddy?
Codex plans (official pricing page, checked 2026-10-19): Free $0/month, Go $8/month, Plus $20/month, Pro From $100/month, Business $25/user/month, API key API pricing.
Which models were used with Codex and WorkBuddy?
With Codex: GPT-6.1 Sol. With WorkBuddy: Hy4, DeepSeek V4.1 Flash 1017.