Inkling vs MiMo V2.5 Pro: Benchmark Comparison
Inkling has the higher score on 11 of 18 shared benchmarks; MiMo V2.5 Pro leads on 5.
The largest observed score gap is 22.00 pts on ProofBench v1.1 , where MiMo V2.5 Pro leads.
Reported ±1 standard-error ranges overlap on 5 of 18 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 | Inkling | MiMo V2.5 Pro | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Index | 28.67% ±1.10 | 33.84% ±1.17 | 5.17 pts | Reported ±1 SE ranges do not overlap |
| Harvey's Legal Agent Benchmark | 2.08% ±0.83 | 2.08% ±0.83 | 0.00 pts | Reported ±1 SE ranges overlap |
| Legal Research Bench | 28.36% ±3.13 | 15.87% ±2.54 | 12.50 pts | Reported ±1 SE ranges do not overlap |
| LegalBench | 82.95% ±0.50 | 77.13% ±0.55 | 5.82 pts | Reported ±1 SE ranges do not overlap |
| EMB | 38.36% ±3.27 | 55.23% ±3.11 | 16.87 pts | Reported ±1 SE ranges do not overlap |
| Finance Agent (v2) | 46.60% ±0.93 | 41.50% ±1.19 | 5.09 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 43.52% ±2.95 | 34.79% ±2.62 | 8.73 pts | Reported ±1 SE ranges do not overlap |
| TaxEval v2 | 75.31% ±0.84 | 73.79% ±0.86 | 1.51 pts | Reported ±1 SE ranges overlap |
| MedCode | 41.19% ±2.23 | 32.48% ±1.91 | 8.71 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 85.41% ±1.84 | 83.73% ±2.06 | 1.67 pts | Reported ±1 SE ranges overlap |
| ProofBench v1.1 | 0.00% ±0.00 | 22.00% ±4.16 | 22.00 pts | Reported ±1 SE ranges do not overlap |
| GPQA Diamond | 87.12% ±1.78 | 82.58% ±2.47 | 4.55 pts | Reported ±1 SE ranges do not overlap |
| MMLU Pro | 86.30% ±0.34 | 84.59% ±0.45 | 1.70 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 11.79% ±3.40 | 21.56% ±4.13 | 9.77 pts | Reported ±1 SE ranges do not overlap |
| LiveCodeBench | 85.52% ±1.00 | 81.35% ±1.07 | 4.16 pts | Reported ±1 SE ranges do not overlap |
| SWE-bench | 77.60% ±1.87 | 74.00% ±1.96 | 3.60 pts | Reported ±1 SE ranges overlap |
| Terminal-Bench 4.0 | 0.51% ±0.51 | 0.51% ±0.51 | 0.00 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench v1.1 | 19.21% ±3.66 | 34.11% ±4.53 | 14.90 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Inkling average | MiMo V2.5 Pro average |
|---|---|---|
| Legal | 37.80% | 31.69% |
| Finance | 50.95% | 51.33% |
| Healthcare | 63.30% | 58.11% |
| Math | 0.00% | 22.00% |
| Academic | 86.71% | 83.59% |
| Coding | 38.93% | 42.31% |
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 | Inkling cost | MiMo V2.5 Pro cost | Inkling latency | MiMo V2.5 Pro latency |
|---|---|---|---|---|
| Vals Index | $1.46 | $0.16 | 20m06s | 34m33s |
| Harvey's Legal Agent Benchmark | $1.25 | $0.11 | 18m24s | 9m04s |
| Legal Research Bench | $0.49 | $0.08 | 14m29s | 6m56s |
| LegalBench | N/A | N/A | 23.14s | 27.14s |
| EMB | $1.67 | $0.22 | 26m22s | 29m08s |
| Finance Agent (v2) | $1.00 | $0.21 | 18m02s | 8m17s |
| Tax Agent Bench | $0.35 | $0.04 | 13m31s | 6m17s |
| TaxEval v2 | N/A | N/A | 3m18s | 62.83s |
| MedCode | N/A | N/A | 2m47s | 38.45s |
| MedScribe | N/A | N/A | 4m05s | 90.71s |
| ProofBench v1.1 | $0.20 | $0.09 | 7m16s | 19m37s |
| GPQA Diamond | N/A | N/A | 5m09s | 4m11s |
| MMLU Pro | N/A | N/A | 73.26s | 67.76s |
| Code Migration | $3.01 | $0.24 | 29m34s | 48m53s |
| LiveCodeBench | N/A | N/A | 4m18s | 4m31s |
| SWE-bench | $0.59 | $0.02 | 6m34s | 7m51s |
| Terminal-Bench 4.0 | $2.51 | $0.23 | 22m52s | 2h07m |
| Vibe Code Bench v1.1 | $1.61 | $0.17 | 18m25s | 40m04s |
Results available only for Inkling
- MortgageTax
- MMMU Pro
- SAGE
- IOI
- ProgramBench
- SkillsBench
- Vibe Code Bench 1-100
- CyberBench v1.1
- Public Benefits Bench v1.1
Results available only for MiMo V2.5 Pro
None.