Gemini 3.5 Flash Lite vs MiMo V2.5 Pro: Benchmark Comparison
Gemini 3.5 Flash Lite has the higher score on 8 of 15 shared benchmarks; MiMo V2.5 Pro leads on 7.
The largest observed score gap is 15.41 pts on Code Migration , where MiMo V2.5 Pro leads.
Reported ±1 standard-error ranges overlap on 6 of 15 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 | Gemini 3.5 Flash Lite | MiMo V2.5 Pro | Gap | Reported uncertainty |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | 0.00% ±0.00 | 2.08% ±0.83 | 2.08 pts | Reported ±1 SE ranges do not overlap |
| Legal Research Bench | 13.94% ±2.41 | 15.87% ±2.54 | 1.92 pts | Reported ±1 SE ranges overlap |
| LegalBench | 84.07% ±0.44 | 77.13% ±0.55 | 6.94 pts | Reported ±1 SE ranges do not overlap |
| EMB | 43.23% ±3.10 | 55.23% ±3.11 | 12.00 pts | Reported ±1 SE ranges do not overlap |
| Finance Agent (v2) | 47.44% ±0.51 | 41.50% ±1.19 | 5.94 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 37.45% ±3.12 | 34.79% ±2.62 | 2.66 pts | Reported ±1 SE ranges overlap |
| TaxEval v2 | 72.61% ±0.88 | 73.79% ±0.86 | 1.19 pts | Reported ±1 SE ranges overlap |
| MedCode | 43.49% ±1.95 | 32.48% ±1.91 | 11.00 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 70.89% ±2.03 | 83.73% ±2.06 | 12.84 pts | Reported ±1 SE ranges do not overlap |
| GPQA Diamond | 83.84% ±1.85 | 82.58% ±2.47 | 1.26 pts | Reported ±1 SE ranges overlap |
| MMLU Pro | 85.84% ±0.34 | 84.59% ±0.45 | 1.24 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 6.15% ±1.71 | 21.56% ±4.13 | 15.41 pts | Reported ±1 SE ranges do not overlap |
| LiveCodeBench | 79.01% ±1.10 | 81.35% ±1.07 | 2.34 pts | Reported ±1 SE ranges do not overlap |
| SWE-bench | 75.00% ±1.94 | 74.00% ±1.96 | 1.00 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench v1.1 | 37.16% ±4.63 | 34.11% ±4.53 | 3.05 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | Gemini 3.5 Flash Lite average | MiMo V2.5 Pro average |
|---|---|---|
| Legal | 32.67% | 31.69% |
| Finance | 50.18% | 51.33% |
| Healthcare | 57.19% | 58.11% |
| Academic | 84.84% | 83.59% |
| Coding | 49.33% | 52.76% |
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 | Gemini 3.5 Flash Lite cost | MiMo V2.5 Pro cost | Gemini 3.5 Flash Lite latency | MiMo V2.5 Pro latency |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | $0.33 | $0.11 | 3m53s | 9m04s |
| Legal Research Bench | $0.12 | $0.08 | 59.20s | 6m56s |
| LegalBench | N/A | N/A | 1.67s | 27.14s |
| EMB | $1.23 | $0.22 | 8m14s | 29m08s |
| Finance Agent (v2) | $0.39 | $0.21 | 2m23s | 8m17s |
| Tax Agent Bench | $0.08 | $0.04 | 47.46s | 6m17s |
| TaxEval v2 | N/A | N/A | 8.81s | 62.83s |
| MedCode | N/A | N/A | 6.02s | 38.45s |
| MedScribe | N/A | N/A | 18.99s | 90.71s |
| GPQA Diamond | N/A | N/A | 13.85s | 4m11s |
| MMLU Pro | N/A | N/A | 4.82s | 67.76s |
| Code Migration | $0.53 | $0.24 | 22m02s | 48m53s |
| LiveCodeBench | N/A | N/A | 21.08s | 4m31s |
| SWE-bench | $0.31 | $0.02 | 7m20s | 7m51s |
| Vibe Code Bench v1.1 | $0.83 | $0.17 | 8m22s | 40m04s |
Results available only for Gemini 3.5 Flash Lite
- MortgageTax
- MMMU Pro
- SAGE
- ProgramBench
- CyberBench v1.1
- Public Benefits Bench v1.1
Results available only for MiMo V2.5 Pro
- Vals Index
- ProofBench v1.1
- Terminal-Bench 4.0