Qwen 3.7 Plus vs GPT 5.4 Mini: Benchmark Comparison
Qwen 3.7 Plus has the higher score on 4 of 9 shared benchmarks; GPT 5.4 Mini leads on 4.
The largest observed score gap is 11.56 pts on SAGE , where GPT 5.4 Mini leads.
Reported ±1 standard-error ranges overlap on 6 of 9 shared benchmarks with comparable uncertainty data. This is not a pairwise statistical significance test.
Shared benchmark results
Scores and reported standard errors come from the latest visible Vals benchmark version available for both models.
| Benchmark | Qwen 3.7 Plus | GPT 5.4 Mini | Gap | Reported uncertainty |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | 0.00% ±0.00 | 0.00% ±0.00 | 0.00 pts | Reported ±1 SE ranges overlap |
| Legal Research Bench | 16.35% ±2.57 | 12.50% ±2.30 | 3.85 pts | Reported ±1 SE ranges overlap |
| EMB | 49.34% ±3.18 | 45.43% ±3.65 | 3.92 pts | Reported ±1 SE ranges overlap |
| Finance Agent (v2) | 38.22% ±1.04 | 45.36% ±0.45 | 7.14 pts | Reported ±1 SE ranges do not overlap |
| MortgageTax | 66.18% ±0.93 | 63.51% ±0.91 | 2.66 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 38.71% ±2.81 | 36.59% ±3.10 | 2.13 pts | Reported ±1 SE ranges overlap |
| SAGE | 39.25% ±3.38 | 50.81% ±3.40 | 11.56 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 12.86% ±2.93 | 12.94% ±3.64 | 0.08 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench v1.1 | 46.39% ±4.61 | 47.97% ±5.61 | 1.58 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | Qwen 3.7 Plus average | GPT 5.4 Mini average |
|---|---|---|
| Legal | 8.17% | 6.25% |
| Finance | 48.11% | 47.72% |
| Education | 39.25% | 50.81% |
| Coding | 29.62% | 30.45% |
Cost and latency
Cost per test appears only where the benchmark reports it for both models. Latency is the measured completion time for that benchmark.
| Benchmark | Qwen 3.7 Plus cost | GPT 5.4 Mini cost | Qwen 3.7 Plus latency | GPT 5.4 Mini latency |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | $0.23 | $1.00 | 8m49s | 11m21s |
| Legal Research Bench | $0.30 | $1.86 | 13m52s | 37m36s |
| EMB | $0.60 | $2.15 | 36m49s | 43m21s |
| Finance Agent (v2) | $0.36 | $1.20 | 9m02s | 35m54s |
| MortgageTax | N/A | N/A | 60.55s | 2m06s |
| Tax Agent Bench | $0.09 | $0.81 | 5m10s | 16m46s |
| SAGE | N/A | N/A | 2m57s | 2m21s |
| Code Migration | $0.42 | $1.95 | 35m47s | 28m53s |
| Vibe Code Bench v1.1 | $1.08 | $1.19 | 37m12s | 34m15s |
Results available only for Qwen 3.7 Plus
- SkillsBench
Results available only for GPT 5.4 Mini
- Vals Index
- TaxEval v2
- GPQA Diamond
- MMLU Pro
- MMMU Pro
- LiveCodeBench
- ProgramBench
- SWE-bench
- Terminal-Bench 4.0