Grok 4.5 vs Inkling: Benchmark Comparison
Grok 4.5 has the higher score on 16 of 21 shared benchmarks; Inkling leads on 4.
The largest observed score gap is 49.79 pts on Vibe Code Bench v1.1 , where Grok 4.5 leads.
Reported ±1 standard-error ranges overlap on 6 of 21 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 4.5 | Inkling | Gap | Reported uncertainty |
|---|---|---|---|---|
| Legal Research Bench | 37.98% ±3.37 | 28.36% ±3.13 | 9.62 pts | Reported ±1 SE ranges do not overlap |
| LegalBench | 85.97% ±0.41 | 82.95% ±0.50 | 3.02 pts | Reported ±1 SE ranges do not overlap |
| MortgageTax | 61.80% ±0.97 | 63.99% ±0.94 | 2.19 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 24.86% ±3.12 | 15.29% ±2.42 | 9.56 pts | Reported ±1 SE ranges do not overlap |
| TaxEval v2 | 71.67% ±0.89 | 75.31% ±0.84 | 3.64 pts | Reported ±1 SE ranges do not overlap |
| MedCode | 43.29% ±2.31 | 41.19% ±2.23 | 2.10 pts | Reported ±1 SE ranges overlap |
| MedScribe | 86.88% ±1.94 | 85.41% ±1.84 | 1.48 pts | Reported ±1 SE ranges overlap |
| ProofBench v1.1 | 31.00% ±4.65 | 0.00% ±0.00 | 31.00 pts | Reported ±1 SE ranges do not overlap |
| GPQA Diamond | 92.93% ±1.29 | 87.12% ±1.78 | 5.81 pts | Reported ±1 SE ranges do not overlap |
| MMLU Pro | 89.22% ±0.31 | 86.30% ±0.34 | 2.92 pts | Reported ±1 SE ranges do not overlap |
| MMMU Pro | 61.79% ±1.17 | 78.50% ±0.99 | 16.70 pts | Reported ±1 SE ranges do not overlap |
| SAGE | 34.97% ±3.32 | 36.55% ±3.22 | 1.59 pts | Reported ±1 SE ranges overlap |
| IOI | 40.56% ±3.95 | 14.94% ±5.40 | 25.61 pts | Reported ±1 SE ranges do not overlap |
| LiveCodeBench | 87.35% ±0.96 | 85.52% ±1.00 | 1.83 pts | Reported ±1 SE ranges overlap |
| ProgramBench | 0.00% ±0.00 | 0.00% ±0.00 | 0.00 pts | Reported ±1 SE ranges overlap |
| SkillsBench | 66.03% ±4.60 | 26.09% ±3.86 | 39.94 pts | Reported ±1 SE ranges do not overlap |
| SWE-bench | 86.60% ±1.52 | 77.60% ±1.87 | 9.00 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench 4.0 | 8.59% ±1.34 | 0.51% ±0.51 | 8.08 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 69.00% ±4.48 | 19.21% ±3.66 | 49.79 pts | Reported ±1 SE ranges do not overlap |
| CyberBench v1.1 | 71.01% ±5.79 | 66.79% ±5.95 | 4.23 pts | Reported ±1 SE ranges overlap |
| SRE Bench | 0.76% ±0.54 | 0.00% ±0.00 | 0.76 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Grok 4.5 average | Inkling average |
|---|---|---|
| Legal | 61.97% | 55.66% |
| Finance | 52.78% | 51.53% |
| Healthcare | 65.09% | 63.30% |
| Math | 31.00% | 0.00% |
| Academic | 81.31% | 83.97% |
| Education | 34.97% | 36.55% |
| Coding | 51.16% | 31.98% |
| Cyber | 35.89% | 33.39% |
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 4.5 cost | Inkling cost | Grok 4.5 latency | Inkling latency |
|---|---|---|---|---|
| Legal Research Bench | $1.09 | $0.49 | 15m54s | 14m29s |
| LegalBench | N/A | N/A | 67.88s | 23.14s |
| MortgageTax | N/A | N/A | 117.46s | 69.11s |
| Tax Agent Bench | $0.47 | $0.35 | 4m44s | 13m31s |
| TaxEval v2 | N/A | N/A | 3m15s | 3m18s |
| MedCode | N/A | N/A | 59.64s | 2m47s |
| MedScribe | N/A | N/A | 11m45s | 4m05s |
| ProofBench v1.1 | $0.57 | $0.20 | 11m09s | 7m16s |
| GPQA Diamond | N/A | N/A | 3m38s | 5m09s |
| MMLU Pro | N/A | N/A | 5m58s | 73.26s |
| MMMU Pro | N/A | N/A | 11m55s | 2m04s |
| SAGE | N/A | N/A | 2m50s | 3m18s |
| IOI | $5.64 | $1.71 | 1h27m | 30m12s |
| LiveCodeBench | N/A | N/A | 9m49s | 4m18s |
| ProgramBench | $4.12 | $4.14 | 18m59s | 45m34s |
| SkillsBench | $0.58 | $0.83 | 2m16s | 15m39s |
| SWE-bench | $0.54 | $0.59 | 3m20s | 6m34s |
| Terminal-Bench 4.0 | $5.52 | $2.50 | 33m43s | 22m59s |
| Vibe Code Bench v1.1 | $4.10 | $1.61 | 13m50s | 18m25s |
| CyberBench v1.1 | $2.95 | $1.46 | 14m08s | 13m31s |
| SRE Bench | $13.42 | $2.23 | 1h06m | 28m39s |
Results available only for Grok 4.5
- Time Horizon Index: KSP
Results available only for Inkling
- Vals Finance Index
- Vals Index
- Vals Legal Index
- HLAB-Vals-1.1
- EMB v1.1
- Finance Agent v2.1
- Code Migration v1.1
- Vibe Code Bench 1-100
- Public Benefits Bench v1.1