Muse Spark Open vs GLM 5.3 Flash: Benchmark Comparison
Muse Spark Open has the higher score on 3 of 11 shared benchmarks; GLM 5.3 Flash leads on 8.
The largest observed score gap is 45.43 pts on Vibe Code Bench v1.1 , where Muse Spark Open leads.
Reported ±1 standard-error ranges overlap on 7 of 11 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 Open | GLM 5.3 Flash | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Finance Index | 52.99% ±1.44 | 55.83% ±1.51 | 2.84 pts | Reported ±1 SE ranges overlap |
| Vals Index | 48.57% ±1.09 | 50.86% ±1.25 | 2.29 pts | Reported ±1 SE ranges overlap |
| Vals Legal Index | 68.51% ±1.76 | 71.05% ±1.83 | 2.54 pts | Reported ±1 SE ranges overlap |
| HLAB-Vals-1.1 | 25.00% ±3.60 | 10.42% ±2.57 | 14.58 pts | Reported ±1 SE ranges do not overlap |
| Legal Research Bench | 38.46% ±3.38 | 45.19% ±3.46 | 6.73 pts | Reported ±1 SE ranges overlap |
| EMB v1.1 | 61.98% ±2.70 | 66.25% ±2.69 | 4.27 pts | Reported ±1 SE ranges overlap |
| Finance Agent v2.1 | 60.66% ±2.06 | 60.59% ±2.03 | 0.08 pts | Reported ±1 SE ranges overlap |
| Tax Agent Bench | 26.32% ±2.65 | 31.55% ±3.35 | 5.23 pts | Reported ±1 SE ranges overlap |
| Code Migration v1.1 | 26.89% ±3.23 | 51.65% ±2.99 | 24.75 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench 4.0 | 6.57% ±0.51 | 37.37% ±2.67 | 30.81 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 76.19% ±3.32 | 30.76% ±5.28 | 45.43 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Muse Spark Open average | GLM 5.3 Flash average |
|---|---|---|
| Legal | 31.73% | 27.80% |
| Finance | 49.66% | 52.80% |
| Coding | 36.55% | 39.93% |
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 Open cost | GLM 5.3 Flash cost | Muse Spark Open latency | GLM 5.3 Flash latency |
|---|---|---|---|---|
| Vals Finance Index | $3.00 | $0.31 | 41m04s | 33m49s |
| Vals Index | $4.72 | $1.13 | 1h22m | 1h04m |
| Vals Legal Index | $5.36 | $0.19 | 1h33m | 28m23s |
| HLAB-Vals-1.1 | $13.63 | $0.32 | 3h59m | 12m25s |
| Legal Research Bench | $1.56 | $0.12 | 29m23s | 51m07s |
| EMB v1.1 | $5.35 | $0.71 | 1h25m | 1h15m |
| Finance Agent v2.1 | $2.76 | $0.07 | 26m52s | 4m56s |
| Tax Agent Bench | $0.88 | $0.14 | 11m42s | 21m37s |
| Code Migration v1.1 | $3.77 | $4.48 | 1h24m | 3h20m |
| Terminal-Bench 4.0 | $7.26 | $1.22 | 2h04m | 1h01m |
| Vibe Code Bench v1.1 | $1.66 | $2.35 | 31m09s | 1h24m |
Results available only for Muse Spark Open
None.
Results available only for GLM 5.3 Flash
- LegalBench
- TaxEval v2
- MedScribe
- ProofBench v1.1
- Terminal-Bench-Science
- GPQA Diamond
- MMLU Pro
- MMMU Pro
- IOI
- LiveCodeBench
- ProgramBench
- SkillsBench
- SWE-bench
- Vibe Code Bench 1-100
- CyberBench v1.1
- SRE Bench