Muse Spark Open vs Step 5 Preview: Benchmark Comparison
Muse Spark Open has the higher score on 2 of 8 shared benchmarks; Step 5 Preview leads on 6.
The largest observed score gap is 25.25 pts on Terminal-Bench 4.0 , where Step 5 Preview leads.
Reported ±1 standard-error ranges overlap on 5 of 8 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 | Step 5 Preview | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Finance Index | 52.99% ±1.44 | 55.43% ±1.44 | 2.44 pts | Reported ±1 SE ranges overlap |
| Legal Research Bench | 38.46% ±3.38 | 40.38% ±3.41 | 1.92 pts | Reported ±1 SE ranges overlap |
| EMB v1.1 | 61.98% ±2.70 | 69.55% ±2.49 | 7.57 pts | Reported ±1 SE ranges do not overlap |
| Finance Agent v2.1 | 60.66% ±2.06 | 58.90% ±2.05 | 1.77 pts | Reported ±1 SE ranges overlap |
| Tax Agent Bench | 26.32% ±2.65 | 27.27% ±3.11 | 0.95 pts | Reported ±1 SE ranges overlap |
| Code Migration v1.1 | 26.89% ±3.23 | 47.00% ±3.43 | 20.11 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench 4.0 | 6.57% ±0.51 | 31.82% ±2.62 | 25.25 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 76.19% ±3.32 | 70.40% ±4.27 | 5.79 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | Muse Spark Open average | Step 5 Preview average |
|---|---|---|
| Legal | 38.46% | 40.38% |
| Finance | 49.66% | 51.91% |
| Coding | 36.55% | 49.74% |
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 | Step 5 Preview cost | Muse Spark Open latency | Step 5 Preview latency |
|---|---|---|---|---|
| Vals Finance Index | $3.00 | $0.82 | 41m04s | 24m42s |
| Legal Research Bench | $1.56 | $0.84 | 29m23s | 36m08s |
| EMB v1.1 | $5.35 | $1.33 | 1h25m | 43m35s |
| Finance Agent v2.1 | $2.76 | $0.58 | 26m52s | 9m03s |
| Tax Agent Bench | $0.88 | $0.55 | 11m42s | 21m29s |
| Code Migration v1.1 | $3.77 | $8.61 | 1h24m | 3h17m |
| Terminal-Bench 4.0 | $7.26 | $3.11 | 2h04m | 1h58m |
| Vibe Code Bench v1.1 | $1.66 | $5.86 | 31m09s | 1h31m |
Results available only for Muse Spark Open
- Vals Index
- Vals Legal Index
- HLAB-Vals-1.1
Results available only for Step 5 Preview
- Vals Science Index
- ProofBench v1.1
- BioMysteryBench
- MysteryMechanism
- Terminal-Bench-Science
- IOI
- SWE-bench Multimodal
- SRE Bench
- Public Benefits Bench v1.1