Grok 4.6 vs Muse Spark 1.2: Benchmark Comparison
Grok 4.6 has the higher score on 14 of 24 shared benchmarks; Muse Spark 1.2 leads on 10.
The largest observed score gap is 25.83 pts on IOI , where Grok 4.6 leads.
Reported ±1 standard-error ranges overlap on 10 of 24 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 1.2 | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Index | 52.09% ±1.15 | 49.29% ±1.10 | 2.80 pts | Reported ±1 SE ranges do not overlap |
| Harvey's Legal Agent Benchmark | 15.83% ±2.65 | 25.42% ±3.67 | 9.58 pts | Reported ±1 SE ranges do not overlap |
| Legal Research Bench | 48.08% ±3.47 | 43.75% ±3.45 | 4.33 pts | Reported ±1 SE ranges overlap |
| LegalBench | 86.31% ±0.42 | 85.26% ±0.45 | 1.05 pts | Reported ±1 SE ranges do not overlap |
| EMB | 62.73% ±3.08 | 56.98% ±3.13 | 5.75 pts | Reported ±1 SE ranges overlap |
| Finance Agent (v2) | 53.68% ±0.67 | 60.60% ±0.28 | 6.92 pts | Reported ±1 SE ranges do not overlap |
| MortgageTax | 64.19% ±0.95 | 65.42% ±0.93 | 1.23 pts | Reported ±1 SE ranges overlap |
| Tax Agent Bench | 70.79% ±3.00 | 56.86% ±2.32 | 13.93 pts | Reported ±1 SE ranges do not overlap |
| TaxEval v2 | 71.10% ±0.90 | 80.38% ±0.76 | 9.28 pts | Reported ±1 SE ranges do not overlap |
| MedCode | 44.71% ±2.26 | 49.35% ±2.19 | 4.63 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 86.53% ±1.96 | 90.06% ±1.96 | 3.53 pts | Reported ±1 SE ranges overlap |
| ProofBench v1.1 | 51.00% ±5.02 | 43.00% ±4.98 | 8.00 pts | Reported ±1 SE ranges overlap |
| BioMysteryBench | 72.22% ±0.00 | 64.81% ±1.33 | 7.41 pts | Reported ±1 SE ranges do not overlap |
| MMLU Pro | 89.40% ±0.30 | 88.28% ±0.32 | 1.13 pts | Reported ±1 SE ranges do not overlap |
| SAGE | 28.90% ±3.08 | 47.66% ±3.44 | 18.76 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 44.57% ±4.48 | 29.95% ±4.02 | 14.62 pts | Reported ±1 SE ranges do not overlap |
| IOI | 47.61% ±2.09 | 21.78% ±0.87 | 25.83 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 |
| SkillsBench | 55.77% ±4.84 | 53.04% ±4.42 | 2.73 pts | Reported ±1 SE ranges overlap |
| SWE-bench | 95.60% ±0.92 | 86.60% ±1.52 | 9.00 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench 4.0 | 17.17% ±1.34 | 6.06% ±1.51 | 11.11 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 76.24% ±3.82 | 79.10% ±3.31 | 2.86 pts | Reported ±1 SE ranges overlap |
| CyberBench v1.1 | 67.68% ±5.87 | 69.52% ±5.56 | 1.85 pts | Reported ±1 SE ranges overlap |
| Public Benefits Bench v1.1 | 66.85% ±1.23 | 68.47% ±1.21 | 1.62 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | Grok 4.6 average | Muse Spark 1.2 average |
|---|---|---|
| Legal | 50.07% | 51.48% |
| Finance | 64.50% | 64.05% |
| Healthcare | 65.62% | 69.70% |
| Math | 51.00% | 43.00% |
| Science | 72.22% | 64.81% |
| Academic | 89.40% | 88.28% |
| Education | 28.90% | 47.66% |
| Coding | 48.28% | 39.58% |
| Cyber | 67.68% | 69.52% |
| Social Mobility | 66.85% | 68.47% |
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 1.2 cost | Grok 4.6 latency | Muse Spark 1.2 latency |
|---|---|---|---|---|
| Vals Index | $4.49 | $1.94 | 37m01s | 22m56s |
| Harvey's Legal Agent Benchmark | $4.01 | $2.09 | 45m05s | 24m16s |
| Legal Research Bench | $1.53 | $0.51 | 25m04s | 5m07s |
| LegalBench | N/A | N/A | 27.42s | 30.10s |
| EMB | $3.06 | $2.31 | 52m59s | 17m07s |
| Finance Agent (v2) | $1.66 | $0.77 | 16m41s | 5m04s |
| MortgageTax | N/A | N/A | 8.55s | 44.62s |
| Tax Agent Bench | $0.98 | $0.27 | 10m58s | 119.91s |
| TaxEval v2 | N/A | N/A | 47.57s | 48.31s |
| MedCode | N/A | N/A | 2m07s | 60.17s |
| MedScribe | N/A | N/A | 70.94s | 61.46s |
| ProofBench v1.1 | $0.76 | $0.44 | 14m22s | 7m49s |
| BioMysteryBench | $1.23 | $0.99 | 14m18s | 23m37s |
| MMLU Pro | N/A | N/A | 54.98s | 44.23s |
| SAGE | N/A | N/A | 3m22s | 29.07s |
| Code Migration | $14.58 | $3.78 | 1h30m | 31m07s |
| IOI | $8.18 | $2.64 | 3h57m | 25m35s |
| ProgramBench | $16.76 | $2.47 | 4h27m | 26m38s |
| SkillsBench | $0.92 | $0.65 | 13m28s | 13m00s |
| SWE-bench | $0.78 | $0.55 | 10m04s | 8m07s |
| Terminal-Bench 4.0 | $5.07 | $4.14 | 29m27s | 1h18m |
| Vibe Code Bench v1.1 | $4.88 | $1.53 | 25m30s | 19m55s |
| CyberBench v1.1 | $4.07 | $2.15 | 36m52s | 20m21s |
| Public Benefits Bench v1.1 | $0.92 | $0.59 | 25m53s | 8m55s |
Results available only for Grok 4.6
- Vals RSI Index
- MysteryMechanism
- Terminal-Bench Science
- GPQA Diamond
- LiveCodeBench
- Vibe Code Bench 1-100
- Time Horizon Index: KSP
Results available only for Muse Spark 1.2
- MMMU Pro