Muse Spark 1.3 vs GLM 5.3: Benchmark Comparison
Muse Spark 1.3 has the higher score on 2 of 12 shared benchmarks; GLM 5.3 leads on 10.
The largest observed score gap is 28.28 pts on Terminal-Bench 4.0 , where GLM 5.3 leads.
Reported ±1 standard-error ranges overlap on 7 of 12 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 | Muse Spark 1.3 | GLM 5.3 | Gap | Reported uncertainty |
|---|---|---|---|---|
| Immigration | 65.00% ±1.56 | 66.73% ±1.62 | 1.73 pts | Reported ±1 SE ranges overlap |
| Legal Research Bench | 40.87% ±3.42 | 49.04% ±3.48 | 8.17 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 37.89% ±3.45 | 43.33% ±3.56 | 5.43 pts | Reported ±1 SE ranges overlap |
| ProofBench v1.1 | 55.00% ±5.00 | 49.00% ±5.02 | 6.00 pts | Reported ±1 SE ranges overlap |
| Terminal-Bench-Science | 4.29% ±2.44 | 5.71% ±2.79 | 1.43 pts | Reported ±1 SE ranges overlap |
| IOI | 43.94% ±1.45 | 68.44% ±7.48 | 24.50 pts | Reported ±1 SE ranges do not overlap |
| ProgramBench | 0.50% ±0.50 | 1.50% ±0.86 | 1.00 pts | Reported ±1 SE ranges overlap |
| Terminal-Bench 4.0 | 10.61% ±1.75 | 38.89% ±1.82 | 28.28 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 82.86% ±2.90 | 78.13% ±3.94 | 4.73 pts | Reported ±1 SE ranges overlap |
| CyberBench v1.1 | 69.41% ±5.76 | 72.08% ±5.41 | 2.68 pts | Reported ±1 SE ranges overlap |
| Access to Justice Benchmark | 72.18% ±0.72 | 73.70% ±0.71 | 1.52 pts | Reported ±1 SE ranges do not overlap |
| Financial Coaching Bench | 70.99% ±1.53 | 74.06% ±1.46 | 3.07 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Muse Spark 1.3 average | GLM 5.3 average |
|---|---|---|
| Legal | 52.93% | 57.88% |
| Finance | 37.89% | 43.33% |
| Math | 55.00% | 49.00% |
| Science | 4.29% | 5.71% |
| Coding | 34.48% | 46.74% |
| Cyber | 69.41% | 72.08% |
| Social Mobility | 71.58% | 73.88% |
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 | Muse Spark 1.3 cost | GLM 5.3 cost | Muse Spark 1.3 latency | GLM 5.3 latency |
|---|---|---|---|---|
| Immigration | $0.05 | $0.12 | 79.86s | 5m44s |
| Legal Research Bench | $0.65 | $2.24 | 8m51s | 51m50s |
| Tax Agent Bench | $0.32 | $1.80 | 8m25s | 50m53s |
| ProofBench v1.1 | $0.43 | $2.08 | 8m54s | 42m23s |
| Terminal-Bench-Science | $4.41 | $15.63 | 1h08m | 2h45m |
| IOI | $2.36 | $7.67 | 29m51s | 1h46m |
| ProgramBench | $11.56 | $21.96 | 1h09m | 4h16m |
| Terminal-Bench 4.0 | $7.04 | $9.37 | 1h59m | 1h23m |
| Vibe Code Bench v1.1 | $2.10 | $12.45 | 12m54s | 1h04m |
| CyberBench v1.1 | $4.26 | $2.69 | 24m53s | 30m18s |
| Access to Justice Benchmark | $0.18 | $0.46 | 2m10s | 11m30s |
| Financial Coaching Bench | $0.07 | $0.09 | 3m12s | 5m38s |
Results available only for Muse Spark 1.3
None.
Results available only for GLM 5.3
- Vals Index
- Vals RSI Index
- Vals Finance Index
- Vals Legal Index
- HLAB-Vals-1.1
- LegalBench
- EMB v1.1
- Finance Agent v2.1
- TaxEval v2
- MedCode
- MedScribe
- MysteryMechanism
- GPQA Diamond
- MMLU Pro
- Code Migration v1.1
- LiveCodeBench
- SkillsBench
- SWE-bench
- Vibe Code Bench 1-100 v1.1
- SRE Bench
- Public Benefits Bench v1.1