Qwen 3.7 Max vs GLM 5.3 Flash: Benchmark Comparison
Qwen 3.7 Max has the higher score on 6 of 14 shared benchmarks; GLM 5.3 Flash leads on 8.
The largest observed score gap is 23.20 pts on SWE-bench , where GLM 5.3 Flash leads.
Reported ±1 standard-error ranges overlap on 2 of 14 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 Max | GLM 5.3 Flash | Gap | Reported uncertainty |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | 1.67% ±0.83 | 6.67% ±1.65 | 5.00 pts | Reported ±1 SE ranges do not overlap |
| Legal Research Bench | 25.48% ±3.03 | 45.19% ±3.46 | 19.71 pts | Reported ±1 SE ranges do not overlap |
| LegalBench | 84.91% ±0.41 | 83.93% ±0.43 | 0.98 pts | Reported ±1 SE ranges do not overlap |
| EMB | 57.04% ±2.85 | 55.93% ±3.56 | 1.11 pts | Reported ±1 SE ranges overlap |
| Finance Agent (v2) | 47.78% ±0.73 | 57.85% ±2.06 | 10.07 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 47.41% ±3.24 | 61.96% ±3.26 | 14.55 pts | Reported ±1 SE ranges do not overlap |
| TaxEval v2 | 75.31% ±0.84 | 75.59% ±0.84 | 0.29 pts | Reported ±1 SE ranges overlap |
| MedScribe | 79.40% ±1.91 | 88.94% ±1.91 | 9.54 pts | Reported ±1 SE ranges do not overlap |
| GPQA Diamond | 90.15% ±1.50 | 86.36% ±2.13 | 3.79 pts | Reported ±1 SE ranges do not overlap |
| MMLU Pro | 89.31% ±0.30 | 86.06% ±0.34 | 3.25 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 13.07% ±2.86 | 20.52% ±4.21 | 7.45 pts | Reported ±1 SE ranges do not overlap |
| LiveCodeBench | 87.06% ±0.97 | 80.51% ±1.05 | 6.55 pts | Reported ±1 SE ranges do not overlap |
| SWE-bench | 68.80% ±2.07 | 92.00% ±1.21 | 23.20 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 47.67% ±4.63 | 30.76% ±5.28 | 16.91 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Qwen 3.7 Max average | GLM 5.3 Flash average |
|---|---|---|
| Legal | 37.35% | 45.26% |
| Finance | 56.88% | 62.83% |
| Healthcare | 79.40% | 88.94% |
| Academic | 89.73% | 86.21% |
| Coding | 54.15% | 55.95% |
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 Max cost | GLM 5.3 Flash cost | Qwen 3.7 Max latency | GLM 5.3 Flash latency |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | $1.58 | $0.57 | 32m03s | 52m17s |
| Legal Research Bench | $1.40 | $0.12 | 13m29s | 51m07s |
| LegalBench | N/A | N/A | 11.85s | 12.52s |
| EMB | $2.86 | $0.71 | 32m37s | 1h15m |
| Finance Agent (v2) | $0.55 | $0.05 | 10m35s | 14m51s |
| Tax Agent Bench | $0.44 | $0.14 | 3m30s | 21m37s |
| TaxEval v2 | N/A | N/A | 57.68s | 53.06s |
| MedScribe | N/A | N/A | 108.05s | 86.98s |
| GPQA Diamond | N/A | N/A | 2m07s | 2m11s |
| MMLU Pro | N/A | N/A | 29.15s | 44.76s |
| Code Migration | $1.93 | $3.13 | 25m32s | 3h26m |
| LiveCodeBench | N/A | N/A | 3m12s | 5m02s |
| SWE-bench | $3.23 | $0.02 | 16m16s | 1h04m |
| Vibe Code Bench v1.1 | $11.40 | $2.35 | 1h18m | 1h24m |
Results available only for Qwen 3.7 Max
- MedCode
Results available only for GLM 5.3 Flash
- ProofBench v1.1
- Terminal-Bench Science
- MMMU Pro
- IOI
- ProgramBench
- SkillsBench
- Vibe Code Bench 1-100
- CyberBench v1.1