Claude Opus 4.7 vs Muse Spark 1.2: Benchmark Comparison
Claude Opus 4.7 has the higher score on 7 of 17 shared benchmarks; Muse Spark 1.2 leads on 10.
The largest observed score gap is 18.75 pts on Harvey's Legal Agent Benchmark , where Muse Spark 1.2 leads.
Reported ±1 standard-error ranges overlap on 4 of 17 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 | Claude Opus 4.7 | Muse Spark 1.2 | Gap | Reported uncertainty |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | 6.67% ±2.00 | 25.42% ±3.67 | 18.75 pts | Reported ±1 SE ranges do not overlap |
| Legal Research Bench | 38.46% ±3.38 | 43.75% ±3.45 | 5.29 pts | Reported ±1 SE ranges overlap |
| LegalBench | 85.25% ±0.45 | 85.26% ±0.45 | 0.01 pts | Reported ±1 SE ranges overlap |
| EMB | 63.73% ±3.11 | 56.98% ±3.13 | 6.75 pts | Reported ±1 SE ranges do not overlap |
| Finance Agent (v2) | 51.51% ±0.49 | 60.60% ±0.28 | 9.09 pts | Reported ±1 SE ranges do not overlap |
| MortgageTax | 70.27% ±0.90 | 65.42% ±0.93 | 4.85 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 63.86% ±3.14 | 56.86% ±2.32 | 7.00 pts | Reported ±1 SE ranges do not overlap |
| TaxEval v2 | 75.27% ±0.84 | 80.38% ±0.76 | 5.11 pts | Reported ±1 SE ranges do not overlap |
| MedCode | 54.86% ±2.21 | 49.35% ±2.19 | 5.51 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 82.95% ±1.98 | 90.06% ±1.96 | 7.11 pts | Reported ±1 SE ranges do not overlap |
| MMLU Pro | 89.87% ±0.30 | 88.28% ±0.32 | 1.60 pts | Reported ±1 SE ranges do not overlap |
| MMMU Pro | 85.55% ±0.84 | 86.13% ±0.83 | 0.58 pts | Reported ±1 SE ranges overlap |
| SAGE | 56.10% ±3.37 | 47.66% ±3.44 | 8.44 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 43.88% ±4.22 | 29.95% ±4.02 | 13.92 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 |
| SWE-bench | 82.00% ±1.72 | 86.60% ±1.52 | 4.60 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 71.00% ±4.51 | 79.10% ±3.31 | 8.10 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Claude Opus 4.7 average | Muse Spark 1.2 average |
|---|---|---|
| Legal | 43.46% | 51.48% |
| Finance | 64.93% | 64.05% |
| Healthcare | 68.91% | 69.70% |
| Academic | 87.71% | 87.20% |
| Education | 56.10% | 47.66% |
| Coding | 49.22% | 49.04% |
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 | Claude Opus 4.7 cost | Muse Spark 1.2 cost | Claude Opus 4.7 latency | Muse Spark 1.2 latency |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | $10.81 | $2.09 | 24m44s | 24m16s |
| Legal Research Bench | $3.06 | $0.51 | 8m32s | 5m07s |
| LegalBench | N/A | N/A | 26.62s | 30.10s |
| EMB | $12.76 | $2.31 | 38m36s | 17m07s |
| Finance Agent (v2) | $4.03 | $0.77 | 6m00s | 5m04s |
| MortgageTax | N/A | N/A | 16.10s | 44.62s |
| Tax Agent Bench | $1.27 | $0.27 | 4m39s | 119.91s |
| TaxEval v2 | N/A | N/A | 62.07s | 48.31s |
| MedCode | N/A | N/A | 54.25s | 60.17s |
| MedScribe | N/A | N/A | 67.50s | 61.46s |
| MMLU Pro | N/A | N/A | 3m08s | 44.23s |
| MMMU Pro | N/A | N/A | 70.80s | 73.84s |
| SAGE | N/A | N/A | 2m05s | 29.07s |
| Code Migration | $36.39 | $3.78 | 1h12m | 31m07s |
| ProgramBench | N/A | N/A | 54m07s | 26m38s |
| SWE-bench | $2.42 | $0.55 | 7m22s | 8m07s |
| Vibe Code Bench v1.1 | $21.41 | $1.53 | 35m42s | 19m55s |
Results available only for Claude Opus 4.7
- Vals RSI Index
- GPQA Diamond
- LiveCodeBench
Results available only for Muse Spark 1.2
- Vals Index
- ProofBench v1.1
- BioMysteryBench
- IOI
- SkillsBench
- Terminal-Bench 4.0
- CyberBench v1.1
- Public Benefits Bench v1.1