Muse Spark 1.3 vs GPT-5.6 Sol: Benchmark Comparison
Muse Spark 1.3 has the higher score on 4 of 14 shared benchmarks; GPT-5.6 Sol leads on 10.
The largest observed score gap is 47.22 pts on IOI , where GPT-5.6 Sol 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 | Muse Spark 1.3 | GPT-5.6 Sol | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Index | 53.20% ±1.07 | 58.01% ±1.02 | 4.81 pts | Reported ±1 SE ranges do not overlap |
| Harvey's Legal Agent Benchmark | 22.92% ±3.42 | 2.50% ±0.83 | 20.42 pts | Reported ±1 SE ranges do not overlap |
| Legal Research Bench | 40.87% ±3.42 | 48.08% ±3.47 | 7.21 pts | Reported ±1 SE ranges do not overlap |
| EMB | 62.71% ±2.96 | 72.34% ±2.37 | 9.63 pts | Reported ±1 SE ranges do not overlap |
| Finance Agent (v2) | 58.90% ±0.44 | 53.76% ±0.85 | 5.15 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 71.93% ±2.92 | 67.95% ±3.12 | 3.98 pts | Reported ±1 SE ranges overlap |
| ProofBench v1.1 | 55.00% ±5.00 | 83.00% ±3.77 | 28.00 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench Science | 4.29% ±2.44 | 20.00% ±4.82 | 15.71 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 27.58% ±4.07 | 52.92% ±4.35 | 25.34 pts | Reported ±1 SE ranges do not overlap |
| IOI | 43.94% ±1.45 | 91.17% ±4.51 | 47.22 pts | Reported ±1 SE ranges do not overlap |
| ProgramBench | 0.50% ±0.50 | 1.50% ±0.86 | 1.00 pts | Reported ±1 SE ranges overlap |
| Terminal-Bench 4.0 | 10.61% ±1.75 | 37.88% ±0.00 | 27.27 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 82.86% ±2.90 | 80.50% ±3.72 | 2.36 pts | Reported ±1 SE ranges overlap |
| CyberBench v1.1 | 69.41% ±5.76 | 76.31% ±5.18 | 6.91 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | Muse Spark 1.3 average | GPT-5.6 Sol average |
|---|---|---|
| Legal | 31.89% | 25.29% |
| Finance | 64.52% | 64.68% |
| Math | 55.00% | 83.00% |
| Science | 4.29% | 20.00% |
| Coding | 33.10% | 52.79% |
| Cyber | 69.41% | 76.31% |
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 | Muse Spark 1.3 cost | GPT-5.6 Sol cost | Muse Spark 1.3 latency | GPT-5.6 Sol latency |
|---|---|---|---|---|
| Vals Index | $3.38 | $14.24 | 32m42s | 37m23s |
| Harvey's Legal Agent Benchmark | $2.76 | $10.37 | 16m39s | 22m50s |
| Legal Research Bench | $0.65 | $21.61 | 8m51s | 1h17m |
| EMB | $3.55 | $6.01 | 22m55s | 9m50s |
| Finance Agent (v2) | $0.74 | $1.25 | 5m42s | 19m25s |
| Tax Agent Bench | $0.32 | $7.51 | 8m25s | 44m41s |
| ProofBench v1.1 | $0.43 | $1.44 | 8m54s | 8m40s |
| Terminal-Bench Science | $4.41 | $7.32 | 1h08m | 1h44m |
| Code Migration | $4.62 | $24.54 | 1h08m | 59m12s |
| IOI | $2.36 | $7.98 | 29m51s | 1h02m |
| ProgramBench | $11.56 | $15.29 | 1h09m | 29m24s |
| Terminal-Bench 4.0 | $7.04 | $7.98 | 1h59m | 33m46s |
| Vibe Code Bench v1.1 | $2.10 | $33.40 | 12m54s | 33m53s |
| CyberBench v1.1 | $4.26 | $3.05 | 24m53s | 10m47s |
Results available only for Muse Spark 1.3
None.
Results available only for GPT-5.6 Sol
- 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