Claude Opus 5 vs Muse Spark 1.3 Max: Benchmark Comparison
Claude Opus 5 has the higher score on 14 of 18 shared benchmarks; Muse Spark 1.3 Max leads on 3.
The largest observed score gap is 41.00 pts on ProofBench v1.1 , where Claude Opus 5 leads.
Reported ±1 standard-error ranges overlap on 8 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 | Claude Opus 5 | Muse Spark 1.3 Max | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Index | 63.67% ±0.96 | 58.16% ±1.19 | 5.51 pts | Reported ±1 SE ranges do not overlap |
| Vals RSI Index | 33.02% | 19.64% | 13.38 pts | Uncertainty comparison unavailable |
| Harvey's Legal Agent Benchmark | 6.67% ±1.65 | 23.75% ±3.55 | 17.08 pts | Reported ±1 SE ranges do not overlap |
| Legal Research Bench | 55.29% ±3.46 | 55.29% ±3.46 | 0.00 pts | Reported ±1 SE ranges overlap |
| EMB | 73.56% ±2.24 | 67.43% ±3.06 | 6.13 pts | Reported ±1 SE ranges do not overlap |
| Finance Agent (v2) | 58.63% ±0.08 | 59.96% ±2.06 | 1.32 pts | Reported ±1 SE ranges overlap |
| Tax Agent Bench | 75.06% ±2.96 | 72.44% ±2.88 | 2.62 pts | Reported ±1 SE ranges overlap |
| ProofBench v1.1 | 99.00% ±1.00 | 58.00% ±4.96 | 41.00 pts | Reported ±1 SE ranges do not overlap |
| MysteryMechanism | 37.39% ±3.25 | 36.04% ±3.23 | 1.35 pts | Reported ±1 SE ranges overlap |
| Terminal-Bench Science | 27.14% ±5.35 | 10.00% ±3.61 | 17.14 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 57.47% ±4.37 | 47.41% ±4.26 | 10.06 pts | Reported ±1 SE ranges do not overlap |
| IOI | 84.33% ±9.96 | 56.56% ±2.52 | 27.78 pts | Reported ±1 SE ranges do not overlap |
| ProgramBench | 3.00% ±1.21 | 2.50% ±1.11 | 0.50 pts | Reported ±1 SE ranges overlap |
| Terminal-Bench 4.0 | 53.53% ±1.34 | 24.75% ±0.51 | 28.79 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench 1-100 | 28.53% ±4.33 | 20.46% ±3.85 | 8.07 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench v1.1 | 88.40% ±3.00 | 85.86% ±2.51 | 2.55 pts | Reported ±1 SE ranges overlap |
| CyberBench v1.1 | 65.36% ±5.55 | 72.74% ±5.67 | 7.38 pts | Reported ±1 SE ranges overlap |
| CUA-bench | 9.00% | 5.83% | 3.17 pts | Uncertainty comparison unavailable |
Performance by category
| Category | Claude Opus 5 average | Muse Spark 1.3 Max average |
|---|---|---|
| Legal | 30.98% | 39.52% |
| Finance | 69.08% | 66.61% |
| Math | 99.00% | 58.00% |
| Science | 32.27% | 23.02% |
| Coding | 52.55% | 39.59% |
| Cyber | 65.36% | 72.74% |
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 | Claude Opus 5 cost | Muse Spark 1.3 Max cost | Claude Opus 5 latency | Muse Spark 1.3 Max latency |
|---|---|---|---|---|
| Vals Index | $19.31 | $3.79 | 57m41s | 23m33s |
| Vals RSI Index | $418.69 | $48.82 | 90h00m | 90h00m |
| Harvey's Legal Agent Benchmark | $23.67 | $2.26 | 55m37s | 14m35s |
| Legal Research Bench | $6.76 | $0.59 | 31m01s | 5m17s |
| EMB | $6.07 | $2.55 | 25m59s | 13m50s |
| Finance Agent (v2) | $5.12 | $0.76 | 9m58s | 3m19s |
| Tax Agent Bench | $5.14 | $0.39 | 16m48s | 4m09s |
| ProofBench v1.1 | $2.11 | $0.48 | 9m51s | 9m29s |
| MysteryMechanism | $3.28 | $0.85 | 16m53s | 7m32s |
| Terminal-Bench Science | $32.54 | $6.09 | 2h12m | 1h24m |
| Code Migration | $60.51 | $14.21 | 2h51m | 1h24m |
| IOI | $16.48 | $1.73 | 56m42s | 28m58s |
| ProgramBench | $60.29 | $54.29 | 2h55m | 5h28m |
| Terminal-Bench 4.0 | $18.60 | $6.65 | 1h07m | 52m56s |
| Vibe Code Bench 1-100 | $41.49 | $5.60 | 1h22m | 20m02s |
| Vibe Code Bench v1.1 | $33.88 | $2.54 | 1h28m | 16m18s |
| CyberBench v1.1 | $2.87 | $3.34 | 19m25s | 16m18s |
| CUA-bench | $232.23 | $143.48 | 25.29s | 36.39s |
Results available only for Claude Opus 5
- LegalBench
- MortgageTax
- TaxEval v2
- MedCode
- MedScribe
- BioMysteryBench
- GPQA Diamond
- MMLU Pro
- MMMU Pro
- SAGE
- LiveCodeBench
- SkillsBench
- SWE-bench
- SRE Bench
- Public Benefits Bench v1.1
- Time Horizon Index: KSP
Results available only for Muse Spark 1.3 Max
None.