GPT-6 Luna vs Qwen3.6 35B A3B
GPT-6 Luna is ahead. GPT-6 Luna is the cheaper one, by 4.8×.
GrindBench-PubSec
CGPT-6 LunaOpenAI54% 49–60%0.11¢ a task · 300 tasksDQwen3.6 35B A3BAlibaba (Qwen)33% 27–38%0.53¢ a task · 300 tasks
GPT-6 Luna is ahead here by 22 points, more than chance explains.
| Kind of work | GPT-6 Luna | Qwen3.6 35B A3B |
|---|---|---|
| ATIP redaction | 2% | 0% |
| Procurement evaluation | 69% | 58% |
| Performance analysis | 54% | 11% |
| Bilingual equivalence | 90% | 85% |
GrindBench-Banking
FGPT-6 LunaOpenAI18% 10–28%0.38¢ a task · 60 tasksFQwen3.6 35B A3BAlibaba (Qwen)3% 0–8%1.8¢ a task · 60 tasks
GPT-6 Luna is ahead here by 15 points, more than chance explains.
| Kind of work | GPT-6 Luna | Qwen3.6 35B A3B |
|---|---|---|
| Lending & mortgages | 20% | 20% |
| AML & KYC | 20% | 0% |
| Deposits & payments | 20% | 0% |
| Complaints & conduct | 30% | 0% |
| Credit risk | 10% | 0% |
| Capital & liquidity | 10% | 0% |
Each kind of work here rests on 10 tasks per model, so a single row can easily be 20 points off. A lead of 10 points or more is in bold; read it as a hint, not a result.