DeepSeek V4 Pro 0813 vs Muse Spark Open: Benchmark Comparison
DeepSeek V4 Pro 0813 has the higher score on 8 of 11 shared benchmarks; Muse Spark Open leads on 3.
The largest observed score gap is 25.09 pts on Code Migration v1.1 , where DeepSeek V4 Pro 0813 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 | DeepSeek V4 Pro 0813 | Muse Spark Open | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Finance Index | 52.94% ±1.41 | 52.99% ±1.44 | 0.05 pts | Reported ±1 SE ranges overlap |
| Vals Index | 52.97% ±1.04 | 48.57% ±1.09 | 4.41 pts | Reported ±1 SE ranges do not overlap |
| Vals Legal Index | 69.01% ±1.77 | 68.51% ±1.76 | 0.50 pts | Reported ±1 SE ranges overlap |
| HLAB-Vals-1.1 | 10.83% ±2.72 | 25.00% ±3.60 | 14.17 pts | Reported ±1 SE ranges do not overlap |
| Legal Research Bench | 40.87% ±3.42 | 38.46% ±3.38 | 2.40 pts | Reported ±1 SE ranges overlap |
| EMB v1.1 | 65.13% ±2.35 | 61.98% ±2.70 | 3.15 pts | Reported ±1 SE ranges overlap |
| Finance Agent v2.1 | 57.12% ±2.08 | 60.66% ±2.06 | 3.55 pts | Reported ±1 SE ranges overlap |
| Tax Agent Bench | 26.76% ±3.09 | 26.32% ±2.65 | 0.43 pts | Reported ±1 SE ranges overlap |
| Code Migration v1.1 | 51.99% ±2.23 | 26.89% ±3.23 | 25.09 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench 4.0 | 14.14% ±2.02 | 6.57% ±0.51 | 7.58 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 82.30% ±3.15 | 76.19% ±3.32 | 6.11 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | DeepSeek V4 Pro 0813 average | Muse Spark Open average |
|---|---|---|
| Legal | 25.85% | 31.73% |
| Finance | 49.67% | 49.66% |
| Coding | 49.48% | 36.55% |
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 | DeepSeek V4 Pro 0813 cost | Muse Spark Open cost | DeepSeek V4 Pro 0813 latency | Muse Spark Open latency |
|---|---|---|---|---|
| Vals Finance Index | $0.88 | $3.00 | 24m00s | 41m04s |
| Vals Index | $2.50 | $4.72 | 58m03s | 1h22m |
| Vals Legal Index | $0.87 | $5.36 | 26m33s | 1h33m |
| HLAB-Vals-1.1 | $0.80 | $13.63 | 10m55s | 3h59m |
| Legal Research Bench | $1.09 | $1.56 | 42m07s | 29m23s |
| EMB v1.1 | $1.08 | $5.35 | 37m27s | 1h25m |
| Finance Agent v2.1 | $0.82 | $2.76 | 7m57s | 26m52s |
| Tax Agent Bench | $0.73 | $0.88 | 26m37s | 11m42s |
| Code Migration v1.1 | $12.16 | $3.77 | 2h54m | 1h24m |
| Terminal-Bench 4.0 | $3.31 | $7.26 | 1h32m | 2h04m |
| Vibe Code Bench v1.1 | $0.36 | $1.66 | 1h06m | 31m09s |
Results available only for DeepSeek V4 Pro 0813
- LegalBench
- TaxEval v2
- MedCode
- MedScribe
- ProofBench v1.1
- Terminal-Bench-Science
- GPQA Diamond
- MMLU Pro
- IOI
- LiveCodeBench
- ProgramBench
- SkillsBench
- SWE-bench
- Vibe Code Bench 1-100
- CyberBench v1.1
- SRE Bench
Results available only for Muse Spark Open
None.