Claude Opus 5 vs Muse Spark 1.3: Benchmark Comparison
Claude Opus 5 has the higher score on 11 of 14 shared benchmarks; Muse Spark 1.3 leads on 3.
The largest observed score gap is 44.00 pts on ProofBench v1.1 , where Claude Opus 5 leads.
Reported ±1 standard-error ranges overlap on 4 of 14 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 | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Index | 63.67% ±0.96 | 53.20% ±1.07 | 10.48 pts | Reported ±1 SE ranges do not overlap |
| Harvey's Legal Agent Benchmark | 6.67% ±1.65 | 22.92% ±3.42 | 16.25 pts | Reported ±1 SE ranges do not overlap |
| Legal Research Bench | 55.29% ±3.46 | 40.87% ±3.42 | 14.42 pts | Reported ±1 SE ranges do not overlap |
| EMB | 73.56% ±2.24 | 62.71% ±2.96 | 10.84 pts | Reported ±1 SE ranges do not overlap |
| Finance Agent (v2) | 58.63% ±0.08 | 58.90% ±0.44 | 0.27 pts | Reported ±1 SE ranges overlap |
| Tax Agent Bench | 75.06% ±2.96 | 71.93% ±2.92 | 3.13 pts | Reported ±1 SE ranges overlap |
| ProofBench v1.1 | 99.00% ±1.00 | 55.00% ±5.00 | 44.00 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench Science | 27.14% ±5.35 | 4.29% ±2.44 | 22.86 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 57.47% ±4.37 | 27.58% ±4.07 | 29.89 pts | Reported ±1 SE ranges do not overlap |
| IOI | 84.33% ±9.96 | 43.94% ±1.45 | 40.39 pts | Reported ±1 SE ranges do not overlap |
| ProgramBench | 3.00% ±1.21 | 0.50% ±0.50 | 2.50 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench 4.0 | 53.53% ±1.34 | 10.61% ±1.75 | 42.93 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 88.40% ±3.00 | 82.86% ±2.90 | 5.55 pts | Reported ±1 SE ranges overlap |
| CyberBench v1.1 | 65.36% ±5.55 | 69.41% ±5.76 | 4.05 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | Claude Opus 5 average | Muse Spark 1.3 average |
|---|---|---|
| Legal | 30.98% | 31.89% |
| Finance | 69.08% | 64.52% |
| Math | 99.00% | 55.00% |
| Science | 27.14% | 4.29% |
| Coding | 57.35% | 33.10% |
| Cyber | 65.36% | 69.41% |
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 cost | Claude Opus 5 latency | Muse Spark 1.3 latency |
|---|---|---|---|---|
| Vals Index | $19.31 | $3.38 | 57m41s | 32m42s |
| Harvey's Legal Agent Benchmark | $23.67 | $2.76 | 55m37s | 16m39s |
| Legal Research Bench | $6.76 | $0.65 | 31m01s | 8m51s |
| EMB | $6.07 | $3.55 | 25m59s | 22m55s |
| Finance Agent (v2) | $5.12 | $0.74 | 9m58s | 5m42s |
| Tax Agent Bench | $5.14 | $0.32 | 16m48s | 8m25s |
| ProofBench v1.1 | $2.11 | $0.43 | 9m51s | 8m54s |
| Terminal-Bench Science | $32.54 | $4.41 | 2h12m | 1h08m |
| Code Migration | $60.51 | $4.62 | 2h51m | 1h08m |
| IOI | $16.48 | $2.36 | 56m42s | 29m51s |
| ProgramBench | $60.29 | $11.56 | 2h55m | 1h09m |
| Terminal-Bench 4.0 | $18.60 | $7.04 | 1h07m | 1h59m |
| Vibe Code Bench v1.1 | $33.88 | $2.10 | 1h28m | 12m54s |
| CyberBench v1.1 | $2.87 | $4.26 | 19m25s | 24m53s |
Results available only for Claude Opus 5
- Vals RSI Index
- LegalBench
- MortgageTax
- TaxEval v2
- MedCode
- MedScribe
- BioMysteryBench
- MysteryMechanism
- GPQA Diamond
- MMLU Pro
- MMMU Pro
- SAGE
- LiveCodeBench
- SkillsBench
- SWE-bench
- Vibe Code Bench 1-100
- SRE Bench
- Public Benefits Bench v1.1
- CUA-bench
- Time Horizon Index: KSP
Results available only for Muse Spark 1.3
None.