Claude Opus 5.5 vs Muse Spark 1.3 Max: Benchmark Comparison
Claude Opus 5.5 has the higher score on 13 of 18 shared benchmarks; Muse Spark 1.3 Max leads on 5.
The largest observed score gap is 42.00 pts on ProofBench v1.1 , where Claude Opus 5.5 leads.
Reported ±1 standard-error ranges overlap on 3 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 5.5 | Muse Spark 1.3 Max | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Index | 66.97% ±0.89 | 58.16% ±1.19 | 8.81 pts | Reported ±1 SE ranges do not overlap |
| Vals RSI Index | 37.31% | 19.64% | 17.67 pts | Uncertainty comparison unavailable |
| Harvey's Legal Agent Benchmark | 3.75% ±1.47 | 23.75% ±3.55 | 20.00 pts | Reported ±1 SE ranges do not overlap |
| Legal Research Bench | 50.48% ±3.48 | 55.29% ±3.46 | 4.81 pts | Reported ±1 SE ranges overlap |
| EMB | 75.94% ±2.38 | 67.43% ±3.06 | 8.51 pts | Reported ±1 SE ranges do not overlap |
| Finance Agent (v2) | 58.59% ±0.17 | 59.96% ±2.06 | 1.37 pts | Reported ±1 SE ranges overlap |
| Tax Agent Bench | 70.50% ±3.15 | 72.44% ±2.88 | 1.94 pts | Reported ±1 SE ranges overlap |
| ProofBench v1.1 | 100.00% ±0.00 | 58.00% ±4.96 | 42.00 pts | Reported ±1 SE ranges do not overlap |
| MysteryMechanism | 49.55% ±3.36 | 36.04% ±3.23 | 13.51 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench Science | 47.14% ±6.01 | 10.00% ±3.61 | 37.14 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 66.65% ±4.33 | 47.41% ±4.26 | 19.23 pts | Reported ±1 SE ranges do not overlap |
| IOI | 95.06% ±4.94 | 56.56% ±2.52 | 38.50 pts | Reported ±1 SE ranges do not overlap |
| ProgramBench | 18.50% ±2.75 | 2.50% ±1.11 | 16.00 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench 4.0 | 65.15% ±0.00 | 24.75% ±0.51 | 40.41 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench 1-100 | 30.36% ±4.83 | 20.46% ±3.85 | 9.90 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 90.29% ±1.53 | 85.86% ±2.51 | 4.44 pts | Reported ±1 SE ranges do not overlap |
| CyberBench v1.1 | 55.36% ±5.13 | 72.74% ±5.67 | 17.38 pts | Reported ±1 SE ranges do not overlap |
| CUA-bench | 14.00% | 5.83% | 8.17 pts | Uncertainty comparison unavailable |
Performance by category
| Category | Claude Opus 5.5 average | Muse Spark 1.3 Max average |
|---|---|---|
| Legal | 27.12% | 39.52% |
| Finance | 68.34% | 66.61% |
| Math | 100.00% | 58.00% |
| Science | 48.35% | 23.02% |
| Coding | 61.00% | 39.59% |
| Cyber | 55.36% | 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 5.5 cost | Muse Spark 1.3 Max cost | Claude Opus 5.5 latency | Muse Spark 1.3 Max latency |
|---|---|---|---|---|
| Vals Index | $32.14 | $3.79 | 1h19m | 23m33s |
| Vals RSI Index | $411.86 | $48.82 | 90h00m | 90h00m |
| Harvey's Legal Agent Benchmark | $21.38 | $2.26 | 49m00s | 14m35s |
| Legal Research Bench | $25.16 | $0.59 | 1h52m | 5m17s |
| EMB | $11.02 | $2.55 | 35m06s | 13m50s |
| Finance Agent (v2) | $9.22 | $0.76 | 33m08s | 3m19s |
| Tax Agent Bench | $15.09 | $0.39 | 1h07m | 4m09s |
| ProofBench v1.1 | $0.96 | $0.48 | 5m51s | 9m29s |
| MysteryMechanism | $4.62 | $0.85 | 19m38s | 7m32s |
| Terminal-Bench Science | $19.12 | $6.09 | 2h28m | 1h24m |
| Code Migration | $112.97 | $14.21 | 3h19m | 1h24m |
| IOI | $5.26 | $1.73 | 17m15s | 28m58s |
| ProgramBench | $68.05 | $54.29 | 2h24m | 5h28m |
| Terminal-Bench 4.0 | $13.20 | $6.65 | 1h04m | 52m56s |
| Vibe Code Bench 1-100 | $44.12 | $5.60 | 2h28m | 20m02s |
| Vibe Code Bench v1.1 | $57.92 | $2.54 | 1h36m | 16m18s |
| CyberBench v1.1 | $3.48 | $3.34 | 18m11s | 16m18s |
| CUA-bench | $188.04 | $143.48 | 14.71s | 36.39s |
Results available only for Claude Opus 5.5
- MedCode
- MedScribe
- BioMysteryBench
- SAGE
- SRE Bench
- Public Benefits Bench v1.1
- Time Horizon Index: KSP
Results available only for Muse Spark 1.3 Max
None.