Gemini 3.8 Flash vs MiMo V2.6 Flash: Benchmark Comparison
Gemini 3.8 Flash has the higher score on 14 of 24 shared benchmarks; MiMo V2.6 Flash leads on 10.
The largest observed score gap is 31.61 pts on CyberBench v1.1 , where MiMo V2.6 Flash leads.
Reported ±1 standard-error ranges overlap on 13 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 | Gemini 3.8 Flash | MiMo V2.6 Flash | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Finance Index | 60.46% ±1.45 | 57.15% ±1.39 | 3.31 pts | Reported ±1 SE ranges do not overlap |
| Vals Index | 55.95% ±1.14 | 54.83% ±1.11 | 1.13 pts | Reported ±1 SE ranges overlap |
| Vals Legal Index | 69.78% ±1.78 | 68.99% ±1.77 | 0.79 pts | Reported ±1 SE ranges overlap |
| Vals Science Index | 35.76% ±1.66 | 31.72% ±1.27 | 4.04 pts | Reported ±1 SE ranges do not overlap |
| HLAB-Vals-1.1 | 12.08% ±2.58 | 13.33% ±2.82 | 1.25 pts | Reported ±1 SE ranges overlap |
| Legal Research Bench | 38.94% ±3.39 | 37.98% ±3.37 | 0.96 pts | Reported ±1 SE ranges overlap |
| EMB v1.1 | 72.87% ±2.42 | 68.88% ±2.27 | 3.99 pts | Reported ±1 SE ranges overlap |
| Finance Agent v2.1 | 65.76% ±2.04 | 63.32% ±2.08 | 2.44 pts | Reported ±1 SE ranges overlap |
| Tax Agent Bench | 32.12% ±3.37 | 28.51% ±3.14 | 3.62 pts | Reported ±1 SE ranges overlap |
| MedCode | 48.13% ±2.18 | 41.06% ±2.03 | 7.08 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 84.50% ±1.94 | 85.28% ±1.99 | 0.78 pts | Reported ±1 SE ranges overlap |
| ProofBench v1.1 | 48.00% ±5.02 | 63.00% ±4.85 | 15.00 pts | Reported ±1 SE ranges do not overlap |
| BioMysteryBench | 62.22% ±1.70 | 69.26% ±0.98 | 7.04 pts | Reported ±1 SE ranges do not overlap |
| MysteryMechanism | 36.49% ±3.24 | 21.62% ±2.77 | 14.86 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench-Science | 8.57% ±3.37 | 4.29% ±2.44 | 4.29 pts | Reported ±1 SE ranges overlap |
| SAGE | 35.06% ±3.36 | 43.53% ±3.43 | 8.47 pts | Reported ±1 SE ranges do not overlap |
| Code Migration v1.1 | 38.65% ±3.65 | 39.55% ±3.54 | 0.91 pts | Reported ±1 SE ranges overlap |
| IOI | 56.94% ±2.26 | 47.67% ±4.79 | 9.28 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 |
| Terminal-Bench 4.0 | 19.70% ±2.31 | 24.24% ±1.51 | 4.55 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 78.65% ±3.88 | 78.96% ±4.04 | 0.31 pts | Reported ±1 SE ranges overlap |
| CyberBench v1.1 | 43.75% ±2.21 | 75.36% ±5.42 | 31.61 pts | Reported ±1 SE ranges do not overlap |
| SRE Bench | 11.07% ±1.94 | 4.20% ±1.24 | 6.87 pts | Reported ±1 SE ranges do not overlap |
| Public Benefits Bench v1.1 | 65.29% ±1.24 | 67.59% ±1.22 | 2.30 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | Gemini 3.8 Flash average | MiMo V2.6 Flash average |
|---|---|---|
| Legal | 25.51% | 25.66% |
| Finance | 56.92% | 53.57% |
| Healthcare | 66.32% | 63.17% |
| Math | 48.00% | 63.00% |
| Science | 35.76% | 31.72% |
| Education | 35.06% | 43.53% |
| Coding | 38.99% | 38.18% |
| Cyber | 27.41% | 39.78% |
| Social Mobility | 65.29% | 67.59% |
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 3.8 Flash cost | MiMo V2.6 Flash cost | Gemini 3.8 Flash latency | MiMo V2.6 Flash latency |
|---|---|---|---|---|
| Vals Finance Index | $3.70 | $0.07 | 7m44s | 19m26s |
| Vals Index | $6.06 | $0.22 | 35m58s | 1h07m |
| Vals Legal Index | $2.05 | $0.07 | 9m15s | 18m20s |
| Vals Science Index | $2.98 | $0.12 | 22m00s | 1h41m |
| HLAB-Vals-1.1 | $3.66 | $0.09 | 19m22s | 22m23s |
| Legal Research Bench | $1.63 | $0.07 | 5m24s | 15m20s |
| EMB v1.1 | $8.24 | $0.11 | 12m49s | 25m22s |
| Finance Agent v2.1 | $1.99 | $0.07 | 7m24s | 15m36s |
| Tax Agent Bench | $0.86 | $0.05 | 2m58s | 17m19s |
| MedCode | N/A | N/A | 42.89s | 93.37s |
| MedScribe | N/A | N/A | 21.14s | 74.48s |
| ProofBench v1.1 | $0.60 | $0.12 | 6m09s | 1h03m |
| BioMysteryBench | $1.55 | $0.05 | 5m27s | 28m28s |
| MysteryMechanism | $1.73 | $0.06 | 5m22s | 35m08s |
| Terminal-Bench-Science | $5.64 | $0.24 | 55m11s | 3h59m |
| SAGE | N/A | N/A | 28.64s | 2m16s |
| Code Migration v1.1 | $15.79 | $0.53 | 2h35m | 4h10m |
| IOI | $3.98 | $0.22 | 14m20s | 1h49m |
| ProgramBench | $10.93 | $0.47 | 46m39s | 3h22m |
| Terminal-Bench 4.0 | $8.65 | $0.22 | 1h47m | 2h25m |
| Vibe Code Bench v1.1 | $6.87 | $0.56 | 8m39s | 50m13s |
| CyberBench v1.1 | $1.31 | $0.05 | 9m49s | 28m22s |
| SRE Bench | $27.46 | $0.40 | 2h28m | 3h22m |
| Public Benefits Bench v1.1 | $1.01 | $0.03 | 3m21s | 20m56s |
Results available only for Gemini 3.8 Flash
- Vals RSI Index
- LegalBench
- MortgageTax
- TaxEval v2
- GPQA Diamond
- MMLU Pro
- MMMU Pro
- LiveCodeBench
- SkillsBench
- SWE-bench
- SWE-bench Multimodal
- Vibe Code Bench 1-100
- CUA-bench
- Time Horizon Index: KSP
Results available only for MiMo V2.6 Flash
None.