Qwen 3.8 Max vs GLM 5.2: Benchmark Comparison
Qwen 3.8 Max has the higher score on 10 of 16 shared benchmarks; GLM 5.2 leads on 6.
The largest observed score gap is 18.35 pts on LiveCodeBench , where Qwen 3.8 Max leads.
Reported ±1 standard-error ranges overlap on 10 of 16 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 3.8 Max | GLM 5.2 | Gap | Reported uncertainty |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | 10.42% ±2.29 | 7.08% ±2.00 | 3.33 pts | Reported ±1 SE ranges overlap |
| Legal Research Bench | 47.60% ±3.47 | 31.25% ±3.22 | 16.35 pts | Reported ±1 SE ranges do not overlap |
| LegalBench | 83.61% ±0.42 | 84.07% ±0.45 | 0.46 pts | Reported ±1 SE ranges overlap |
| EMB | 60.07% ±3.35 | 61.53% ±2.88 | 1.47 pts | Reported ±1 SE ranges overlap |
| Finance Agent (v2) | 50.59% ±0.58 | 49.70% ±0.88 | 0.89 pts | Reported ±1 SE ranges overlap |
| TaxEval v2 | 75.55% ±0.84 | 73.34% ±0.86 | 2.21 pts | Reported ±1 SE ranges do not overlap |
| MedCode | 40.67% ±2.03 | 40.77% ±2.17 | 0.10 pts | Reported ±1 SE ranges overlap |
| MedScribe | 84.95% ±2.00 | 83.53% ±2.00 | 1.41 pts | Reported ±1 SE ranges overlap |
| GPQA Diamond | 93.69% ±1.22 | 85.61% ±1.77 | 8.08 pts | Reported ±1 SE ranges do not overlap |
| MMLU Pro | 88.60% ±0.31 | 86.71% ±0.33 | 1.89 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 23.96% ±4.31 | 37.87% ±4.14 | 13.91 pts | Reported ±1 SE ranges do not overlap |
| LiveCodeBench | 87.85% ±0.95 | 69.50% ±1.18 | 18.35 pts | Reported ±1 SE ranges do not overlap |
| ProgramBench | 0.00% ±0.00 | 0.50% ±0.50 | 0.50 pts | Reported ±1 SE ranges overlap |
| SkillsBench | 42.01% ±4.43 | 45.08% ±4.39 | 3.07 pts | Reported ±1 SE ranges overlap |
| SWE-bench | 85.60% ±1.57 | 82.80% ±1.69 | 2.80 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench v1.1 | 64.70% ±5.36 | 63.96% ±4.79 | 0.73 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | Qwen 3.8 Max average | GLM 5.2 average |
|---|---|---|
| Legal | 47.21% | 40.80% |
| Finance | 62.07% | 61.52% |
| Healthcare | 62.81% | 62.15% |
| Academic | 91.14% | 86.16% |
| Coding | 50.69% | 49.95% |
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 3.8 Max cost | GLM 5.2 cost | Qwen 3.8 Max latency | GLM 5.2 latency |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | $2.37 | $2.06 | 49m12s | 20m51s |
| Legal Research Bench | $2.49 | $0.89 | 1h01m | 17m03s |
| LegalBench | N/A | N/A | 36.37s | 5.77s |
| EMB | $2.66 | $4.47 | 57m47s | 58m52s |
| Finance Agent (v2) | $1.24 | $0.71 | 19m35s | 7m53s |
| TaxEval v2 | N/A | N/A | 4m26s | 64.94s |
| MedCode | N/A | N/A | 6m18s | 95.27s |
| MedScribe | N/A | N/A | 4m11s | 2m18s |
| GPQA Diamond | N/A | N/A | 4m27s | 3m45s |
| MMLU Pro | N/A | N/A | 63.58s | 51.64s |
| Code Migration | $10.54 | $12.64 | 4h28m | 1h54m |
| LiveCodeBench | N/A | N/A | 5m38s | 8m52s |
| ProgramBench | $12.36 | $12.58 | 5h54m | 2h06m |
| SkillsBench | $0.52 | $0.81 | 15m48s | 19m52s |
| SWE-bench | $1.13 | $0.71 | 41m42s | 11m10s |
| Vibe Code Bench v1.1 | $8.24 | $8.49 | 2h49m | 1h02m |
Results available only for Qwen 3.8 Max
- Vals Index
- Vals RSI Index
- MortgageTax
- Tax Agent Bench
- ProofBench v1.1
- MysteryMechanism
- Terminal-Bench Science
- MMMU Pro
- SAGE
- IOI
- Terminal-Bench 4.0
- Vibe Code Bench 1-100
- CyberBench v1.1
- Public Benefits Bench v1.1
Results available only for GLM 5.2
- SRE Bench