Grok 4.5 vs MiMo V2.5 Pro: Benchmark Comparison
Grok 4.5 has the higher score on 12 of 13 shared benchmarks; MiMo V2.5 Pro leads on 1.
The largest observed score gap is 34.89 pts on Vibe Code Bench v1.1 , where Grok 4.5 leads.
Reported ±1 standard-error ranges overlap on 1 of 13 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 | MiMo V2.5 Pro | Gap | Reported uncertainty |
|---|---|---|---|---|
| Legal Research Bench | 37.98% ±3.37 | 15.87% ±2.54 | 22.12 pts | Reported ±1 SE ranges do not overlap |
| LegalBench | 85.97% ±0.41 | 77.13% ±0.55 | 8.84 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 24.86% ±3.12 | 11.50% ±1.96 | 13.35 pts | Reported ±1 SE ranges do not overlap |
| TaxEval v2 | 71.67% ±0.89 | 73.79% ±0.86 | 2.13 pts | Reported ±1 SE ranges do not overlap |
| MedCode | 43.29% ±2.31 | 32.48% ±1.91 | 10.81 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 86.88% ±1.94 | 83.73% ±2.06 | 3.15 pts | Reported ±1 SE ranges overlap |
| ProofBench v1.1 | 31.00% ±4.65 | 22.00% ±4.16 | 9.00 pts | Reported ±1 SE ranges do not overlap |
| GPQA Diamond | 92.93% ±1.29 | 82.58% ±2.47 | 10.35 pts | Reported ±1 SE ranges do not overlap |
| MMLU Pro | 89.22% ±0.31 | 84.59% ±0.45 | 4.62 pts | Reported ±1 SE ranges do not overlap |
| LiveCodeBench | 87.35% ±0.96 | 81.35% ±1.07 | 6.00 pts | Reported ±1 SE ranges do not overlap |
| SWE-bench | 86.60% ±1.52 | 74.00% ±1.96 | 12.60 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 | 34.11% ±4.53 | 34.89 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Grok 4.5 average | MiMo V2.5 Pro average |
|---|---|---|
| Legal | 61.97% | 46.50% |
| Finance | 48.26% | 42.65% |
| Healthcare | 65.09% | 58.11% |
| Math | 31.00% | 22.00% |
| Academic | 91.07% | 83.59% |
| Coding | 62.88% | 47.49% |
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 | MiMo V2.5 Pro cost | Grok 4.5 latency | MiMo V2.5 Pro latency |
|---|---|---|---|---|
| Legal Research Bench | $1.09 | $0.08 | 15m54s | 6m56s |
| LegalBench | N/A | N/A | 67.88s | 27.14s |
| Tax Agent Bench | $0.47 | $0.04 | 4m44s | 6m17s |
| TaxEval v2 | N/A | N/A | 3m15s | 62.83s |
| MedCode | N/A | N/A | 59.64s | 38.45s |
| MedScribe | N/A | N/A | 11m45s | 90.71s |
| ProofBench v1.1 | $0.57 | $0.09 | 11m09s | 19m37s |
| GPQA Diamond | N/A | N/A | 3m38s | 4m11s |
| MMLU Pro | N/A | N/A | 5m58s | 67.76s |
| LiveCodeBench | N/A | N/A | 9m49s | 4m31s |
| SWE-bench | $0.54 | $0.02 | 3m20s | 7m51s |
| Terminal-Bench 4.0 | $5.52 | $0.23 | 33m43s | 2h07m |
| Vibe Code Bench v1.1 | $4.10 | $0.17 | 13m50s | 40m04s |
Results available only for Grok 4.5
- MortgageTax
- MMMU Pro
- SAGE
- IOI
- ProgramBench
- SkillsBench
- CyberBench v1.1
- SRE Bench
- Time Horizon Index: KSP
Results available only for MiMo V2.5 Pro
None.