Qwen 3.6 Plus vs GPT 5.4 Nano: Benchmark Comparison
Qwen 3.6 Plus has the higher score on 13 of 18 shared benchmarks; GPT 5.4 Nano leads on 5.
The largest observed score gap is 11.88 pts on EMB , where GPT 5.4 Nano leads.
Reported ±1 standard-error ranges overlap on 6 of 18 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 3.6 Plus | GPT 5.4 Nano | Gap | Reported uncertainty |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | 1.25% ±0.83 | 0.00% ±0.00 | 1.25 pts | Reported ±1 SE ranges do not overlap |
| Legal Research Bench | 14.90% ±2.48 | 6.25% ±1.68 | 8.65 pts | Reported ±1 SE ranges do not overlap |
| LegalBench | 84.23% ±0.42 | 77.92% ±0.43 | 6.31 pts | Reported ±1 SE ranges do not overlap |
| EMB | 32.87% ±2.81 | 44.75% ±3.12 | 11.88 pts | Reported ±1 SE ranges do not overlap |
| Finance Agent (v2) | 40.85% ±0.13 | 38.22% ±1.19 | 2.63 pts | Reported ±1 SE ranges do not overlap |
| MortgageTax | 67.97% ±0.91 | 59.10% ±0.96 | 8.86 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 32.84% ±2.75 | 26.58% ±2.52 | 6.27 pts | Reported ±1 SE ranges do not overlap |
| TaxEval v2 | 74.73% ±0.85 | 67.42% ±0.93 | 7.32 pts | Reported ±1 SE ranges do not overlap |
| MedCode | 36.89% ±2.02 | 41.03% ±2.26 | 4.14 pts | Reported ±1 SE ranges overlap |
| MedScribe | 76.96% ±1.92 | 77.09% ±1.89 | 0.13 pts | Reported ±1 SE ranges overlap |
| GPQA Diamond | 87.37% ±1.67 | 77.53% ±2.42 | 9.85 pts | Reported ±1 SE ranges do not overlap |
| MMLU Pro | 87.67% ±0.32 | 77.17% ±0.43 | 10.50 pts | Reported ±1 SE ranges do not overlap |
| MMMU Pro | 84.16% ±0.88 | 73.58% ±1.06 | 10.58 pts | Reported ±1 SE ranges do not overlap |
| SAGE | 44.86% ±3.43 | 38.08% ±3.09 | 6.78 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 11.10% ±1.31 | 14.47% ±4.03 | 3.37 pts | Reported ±1 SE ranges overlap |
| LiveCodeBench | 85.95% ±0.98 | 84.01% ±1.04 | 1.94 pts | Reported ±1 SE ranges overlap |
| SWE-bench | 73.40% ±1.98 | 69.80% ±2.06 | 3.60 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench v1.1 | 25.57% ±3.91 | 26.10% ±5.08 | 0.53 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | Qwen 3.6 Plus average | GPT 5.4 Nano average |
|---|---|---|
| Legal | 33.46% | 28.06% |
| Finance | 49.85% | 47.21% |
| Healthcare | 56.93% | 59.06% |
| Academic | 86.40% | 76.09% |
| Education | 44.86% | 38.08% |
| Coding | 49.00% | 48.59% |
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 3.6 Plus cost | GPT 5.4 Nano cost | Qwen 3.6 Plus latency | GPT 5.4 Nano latency |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | $3.94 | $0.18 | 14m48s | 6m03s |
| Legal Research Bench | $0.70 | $0.14 | 10m59s | 8m47s |
| LegalBench | N/A | N/A | 19.07s | 2.70s |
| EMB | $2.87 | $0.57 | 31m14s | 29m27s |
| Finance Agent (v2) | $0.81 | $0.16 | 10m12s | 5m35s |
| MortgageTax | N/A | N/A | 78.18s | 14.53s |
| Tax Agent Bench | $0.30 | $0.07 | 6m18s | 3m40s |
| TaxEval v2 | N/A | N/A | 70.63s | 15.90s |
| MedCode | N/A | N/A | 56.22s | 8.04s |
| MedScribe | N/A | N/A | 2m54s | 20.53s |
| GPQA Diamond | N/A | N/A | 2m02s | 29.50s |
| MMLU Pro | N/A | N/A | 46.18s | 8.21s |
| MMMU Pro | N/A | N/A | 111.94s | 21.91s |
| SAGE | N/A | N/A | 3m49s | 34.33s |
| Code Migration | $4.78 | $0.42 | 29m50s | 26m34s |
| LiveCodeBench | N/A | N/A | 7m56s | 60.09s |
| SWE-bench | $0.87 | $0.10 | 7m04s | 4m23s |
| Vibe Code Bench v1.1 | $5.45 | $1.28 | 38m10s | 54m36s |
Results available only for Qwen 3.6 Plus
- ProgramBench
Results available only for GPT 5.4 Nano
None.