Qwen3 Coder 480B Turbo (Venice) vs GLM 4.7 (Venice)
On the 11 use cases both models ran, Qwen3 Coder 480B Turbo (Venice) won 6 to 4, with 1 tied (better outcome first, then lower cost).
Pass rate: Qwen3 Coder 480B Turbo (Venice) 64% (11 runs) vs GLM 4.7 (Venice) 82% (11 runs). Average cost per run: $0.0089 vs $0.03.
| Metric | Qwen3 Coder 480B Turbo (Venice) | GLM 4.7 (Venice) |
|---|---|---|
| Runs on shared use cases | 11 | 11 |
| Pass rate | 64% (7/11) | 82% (9/11) |
| Avg cost per run | $0.0089 | $0.03 |
| Avg wall time | 2m | 6m |
| Step-ins per run | 0.00 | 0.00 |
| Use cases won | 6 | 4 |
Use case by use case
- Backtest a moving-average crossover on a bundled synthetic price file: Qwen3 Coder 480B Turbo (Venice) better (pass 100% vs 100%)
- Boat fuel range with a reserve over a planned trip: Qwen3 Coder 480B Turbo (Venice) better (pass 100% vs 0%)
- Catch log checked against a made-up fishing regulations table: tie (pass 0% vs 0%)
- Dead reckoning, estimated position with current, and computed set and drift: Qwen3 Coder 480B Turbo (Venice) better (pass 100% vs 100%)
- Debt avalanche vs snowball schedule to the cent: GLM 4.7 (Venice) better (pass 0% vs 100%)
- Discounted cash flow valuation with mid-year option and a sensitivity grid: Qwen3 Coder 480B Turbo (Venice) better (pass 100% vs 100%)
- Progressive tax on fictional brackets, and pre-tax vs after-tax savings comparison: GLM 4.7 (Venice) better (pass 0% vs 100%)
- Read a synthetic annual-report excerpt and compute financial ratios: GLM 4.7 (Venice) better (pass 0% vs 100%)
- Retirement drawdown with a 4% rule, inflation raises and a skip-raise-after-loss guardrail: Qwen3 Coder 480B Turbo (Venice) better (pass 100% vs 100%)
- Seeded Monte Carlo retirement odds against a stated success threshold: Qwen3 Coder 480B Turbo (Venice) better (pass 100% vs 100%)
- Work backward from a retirement budget to a savings target, contributions and earliest retirement age: GLM 4.7 (Venice) better (pass 100% vs 100%)
Only use cases both models ran are compared; all settings of each model are grouped. How we score.