humaneval-plus@1.0 (unreviewed) on GPT-6.1 Sol
164 tasks, 1 attempt, open network. Updated 24 Oct 2026.
164 tasks from humaneval-plus@1.0 on ghcr.io. Nobody has reviewed this dataset, so a score here says nothing about the benchmark it's named after.
Compare
Pick two harnesses to compare them task by task.
DeepSeek Harness 0.2.1-rc.2 against Claude Code 2.1.309, task by task
Over the 164 tasks both ran, 1 attempt each
DeepSeek Harness 0.2.1-rc.2 minus Claude Code 2.1.309, pass rate
+0.6 points
95% interval 0.0 to +1.8
The interval includes zero, so the paired test can't tell the two apart.
Where the tasks landed
- 1Only DeepSeek Harness 0.2.1-rc.2 solved
- 157Both solved
- 0Only Claude Code 2.1.309 solved
- 6Neither solved
Of 164 tasks, 1 only DeepSeek Harness 0.2.1-rc.2 solved, 0 only Claude Code 2.1.309 solved, 157 both solved and 6 neither did.
| Task | Reward | Tokens | Time | |||
|---|---|---|---|---|---|---|
| DeepSeek Harness 0.2.1-rc.2 | Claude Code 2.1.309 | DeepSeek Harness 0.2.1-rc.2 | Claude Code 2.1.309 | DeepSeek Harness 0.2.1-rc.2 | Claude Code 2.1.309 | |
humaneval-plus-34 | 1 | 0 | 19k | 40k | 27 s | 22 s |