DeepSeek V4 Pro 0813 vs Muse Spark 1.2: Benchmark Comparison
DeepSeek V4 Pro 0813 has the higher score on 8 of 16 shared benchmarks; Muse Spark 1.2 leads on 8.
The largest observed score gap is 29.83 pts on IOI , where DeepSeek V4 Pro 0813 leads.
Reported ±1 standard-error ranges overlap on 6 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 | DeepSeek V4 Pro 0813 | Muse Spark 1.2 | Gap | Reported uncertainty |
|---|---|---|---|---|
| Legal Research Bench | 40.87% ±3.42 | 43.75% ±3.45 | 2.88 pts | Reported ±1 SE ranges overlap |
| LegalBench | 82.36% ±0.44 | 85.26% ±0.45 | 2.90 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 26.76% ±3.09 | 32.80% ±2.75 | 6.04 pts | Reported ±1 SE ranges do not overlap |
| TaxEval v2 | 73.06% ±0.87 | 80.38% ±0.76 | 7.32 pts | Reported ±1 SE ranges do not overlap |
| MedCode | 42.47% ±2.16 | 49.35% ±2.19 | 6.88 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 80.17% ±2.00 | 90.06% ±1.96 | 9.89 pts | Reported ±1 SE ranges do not overlap |
| ProofBench v1.1 | 50.00% ±5.03 | 43.00% ±4.98 | 7.00 pts | Reported ±1 SE ranges overlap |
| MMLU Pro | 86.97% ±0.34 | 88.28% ±0.32 | 1.30 pts | Reported ±1 SE ranges do not overlap |
| IOI | 51.61% ±2.40 | 21.78% ±0.87 | 29.83 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 | 53.83% ±4.49 | 53.04% ±4.42 | 0.79 pts | Reported ±1 SE ranges overlap |
| SWE-bench | 96.40% ±0.83 | 86.60% ±1.52 | 9.80 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench 4.0 | 14.14% ±2.02 | 6.06% ±1.51 | 8.08 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 82.30% ±3.15 | 79.10% ±3.31 | 3.20 pts | Reported ±1 SE ranges overlap |
| CyberBench v1.1 | 72.86% ±5.50 | 69.52% ±5.56 | 3.33 pts | Reported ±1 SE ranges overlap |
| SRE Bench | 1.91% ±0.85 | 0.00% ±0.00 | 1.91 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | DeepSeek V4 Pro 0813 average | Muse Spark 1.2 average |
|---|---|---|
| Legal | 61.61% | 64.51% |
| Finance | 49.91% | 56.59% |
| Healthcare | 61.32% | 69.70% |
| Math | 50.00% | 43.00% |
| Academic | 86.97% | 88.28% |
| Coding | 49.71% | 41.18% |
| Cyber | 37.38% | 34.76% |
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 1.2 cost | DeepSeek V4 Pro 0813 latency | Muse Spark 1.2 latency |
|---|---|---|---|---|
| Legal Research Bench | $1.09 | $0.51 | 42m07s | 5m07s |
| LegalBench | N/A | N/A | 20.05s | 30.10s |
| Tax Agent Bench | $0.73 | $0.27 | 26m37s | 119.91s |
| TaxEval v2 | N/A | N/A | 3m46s | 48.31s |
| MedCode | N/A | N/A | 3m01s | 60.17s |
| MedScribe | N/A | N/A | 2m36s | 61.46s |
| ProofBench v1.1 | $0.06 | $0.44 | 12m12s | 7m49s |
| MMLU Pro | N/A | N/A | 59.62s | 44.23s |
| IOI | $2.15 | $2.64 | 1h07m | 25m35s |
| ProgramBench | $0.43 | $2.47 | 1h23m | 26m38s |
| SkillsBench | $0.37 | $0.65 | 11m15s | 13m00s |
| SWE-bench | $0.10 | $0.55 | 4m00s | 8m07s |
| Terminal-Bench 4.0 | $3.31 | $4.14 | 1h32m | 1h18m |
| Vibe Code Bench v1.1 | $0.36 | $1.53 | 1h06m | 19m55s |
| CyberBench v1.1 | $0.59 | $2.15 | 22m33s | 20m21s |
| SRE Bench | $5.58 | $23.43 | 2h20m | 1h40m |
Results available only for DeepSeek V4 Pro 0813
- Vals Finance Index
- Vals Index
- Vals Legal Index
- HLAB-Vals-1.1
- EMB v1.1
- Finance Agent v2.1
- Terminal-Bench-Science
- GPQA Diamond
- Code Migration v1.1
- LiveCodeBench
- Vibe Code Bench 1-100
Results available only for Muse Spark 1.2
- MortgageTax
- BioMysteryBench
- MMMU Pro
- SAGE
- Public Benefits Bench v1.1