Grok 4.6 vs Muse Spark 1.3: Benchmark Comparison
Grok 4.6 has the higher score on 7 of 14 shared benchmarks; Muse Spark 1.3 leads on 7.
The largest observed score gap is 16.99 pts on Code Migration , where Grok 4.6 leads.
Reported ±1 standard-error ranges overlap on 7 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 | Grok 4.6 | Muse Spark 1.3 | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Index | 52.09% ±1.15 | 53.20% ±1.07 | 1.11 pts | Reported ±1 SE ranges overlap |
| Harvey's Legal Agent Benchmark | 15.83% ±2.65 | 22.92% ±3.42 | 7.08 pts | Reported ±1 SE ranges do not overlap |
| Legal Research Bench | 48.08% ±3.47 | 40.87% ±3.42 | 7.21 pts | Reported ±1 SE ranges do not overlap |
| EMB | 62.73% ±3.08 | 62.71% ±2.96 | 0.01 pts | Reported ±1 SE ranges overlap |
| Finance Agent (v2) | 53.68% ±0.67 | 58.90% ±0.44 | 5.22 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 33.14% ±3.40 | 35.97% ±3.42 | 2.83 pts | Reported ±1 SE ranges overlap |
| ProofBench v1.1 | 51.00% ±5.02 | 55.00% ±5.00 | 4.00 pts | Reported ±1 SE ranges overlap |
| Terminal-Bench-Science | 11.43% ±3.83 | 4.29% ±2.44 | 7.14 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 44.57% ±4.48 | 27.58% ±4.07 | 16.99 pts | Reported ±1 SE ranges do not overlap |
| IOI | 47.61% ±2.09 | 43.94% ±1.45 | 3.67 pts | Reported ±1 SE ranges do not overlap |
| ProgramBench | 1.00% ±0.70 | 0.50% ±0.50 | 0.50 pts | Reported ±1 SE ranges overlap |
| Terminal-Bench 4.0 | 17.17% ±1.34 | 10.61% ±1.75 | 6.57 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 76.24% ±3.82 | 82.86% ±2.90 | 6.62 pts | Reported ±1 SE ranges overlap |
| CyberBench v1.1 | 67.68% ±5.87 | 69.41% ±5.76 | 1.73 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | Grok 4.6 average | Muse Spark 1.3 average |
|---|---|---|
| Legal | 31.95% | 31.89% |
| Finance | 49.85% | 52.53% |
| Math | 51.00% | 55.00% |
| Science | 11.43% | 4.29% |
| Coding | 37.32% | 33.10% |
| Cyber | 67.68% | 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 | Grok 4.6 cost | Muse Spark 1.3 cost | Grok 4.6 latency | Muse Spark 1.3 latency |
|---|---|---|---|---|
| Vals Index | $4.49 | $3.38 | 37m01s | 32m46s |
| Harvey's Legal Agent Benchmark | $4.01 | $2.76 | 45m05s | 17m04s |
| Legal Research Bench | $1.53 | $0.65 | 25m04s | 8m51s |
| EMB | $3.06 | $3.55 | 52m59s | 22m55s |
| Finance Agent (v2) | $1.66 | $0.74 | 16m41s | 5m42s |
| Tax Agent Bench | $0.98 | $0.32 | 10m58s | 8m25s |
| ProofBench v1.1 | $0.76 | $0.43 | 14m22s | 8m54s |
| Terminal-Bench-Science | $4.82 | $4.41 | 1h18m | 1h08m |
| Code Migration | $14.58 | $4.62 | 1h30m | 1h08m |
| IOI | $8.18 | $2.36 | 3h57m | 29m51s |
| ProgramBench | $16.76 | $11.56 | 4h27m | 1h09m |
| Terminal-Bench 4.0 | $5.06 | $7.04 | 29m25s | 1h59m |
| Vibe Code Bench v1.1 | $4.88 | $2.10 | 25m30s | 12m54s |
| CyberBench v1.1 | $4.07 | $4.26 | 36m52s | 24m53s |
Results available only for Grok 4.6
- Vals RSI Index
- Vals Science Index
- LegalBench
- MortgageTax
- TaxEval v2
- MedCode
- MedScribe
- BioMysteryBench
- MysteryMechanism
- GPQA Diamond
- MMLU Pro
- SAGE
- LiveCodeBench
- SkillsBench
- SWE-bench
- Vibe Code Bench 1-100
- Public Benefits Bench v1.1
- Time Horizon Index: KSP
Results available only for Muse Spark 1.3
None.