Model comparison
Gemini 3.8 Flash vs MiMo-V2-Pro
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 43.0 on the Noometry Index. MiMo-V2-Pro costs 2.8× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
GoogleSummary
- They share 20 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 8 categories and MiMo-V2-Pro in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 22.1.
- The biggest single-benchmark swing is NYT Connections (extended): 97.4% for Gemini 3.8 Flash and 25.8% for MiMo-V2-Pro.
- MiMo-V2-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.8 Flash.
Side by side
| Gemini 3.8 Flash | MiMo-V2-Pro | |
|---|---|---|
| Provider | Xiaomi | |
| Noometry Index | 61.8 | 43.0 |
| Released | 2026-09-02 | 2026-03-18 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.75 | $0.43 |
| Output $ / M tokens | $3.75 | $0.87 |
| Results tracked | 50 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.8 Flash leads
Gemini 3.8 Flash: 59.2 (#15), MiMo-V2-Pro: 43.8 (#83)
| Benchmark | Gemini 3.8 Flash | MiMo-V2-Pro |
|---|---|---|
| LMArena WebDev | 1584 | 1433 |
| LMArena Coding | 1510 | 1476 |
| ALE-Bench | 1,270 | 785.17 |
| DeepSWE | 73.8% | — |
| FrontierCode | 41.2% | — |
| CursorBench | 39.6% | — |
| FrontierSWE | 19.6% | — |
| SciCode | 56.6% | — |
| WeirdML | 84.8% | — |
Agentic & Tool Use Not comparable
Gemini 3.8 Flash: 41.8 (#21), MiMo-V2-Pro: —
| Benchmark | Gemini 3.8 Flash | MiMo-V2-Pro |
|---|---|---|
| APEX-Agents | 64.3% | — |
| Remote Labor Index | 5.8% | — |
| GDP.pdf | 23.4% | — |
| Vending-Bench 2 | 5,094 | — |
Reasoning Gemini 3.8 Flash leads
Gemini 3.8 Flash: 76.9 (#5), MiMo-V2-Pro: 22.1 (#206)
| Benchmark | Gemini 3.8 Flash | MiMo-V2-Pro |
|---|---|---|
| NYT Connections (extended) | 97.4% | 25.8% |
| LMArena Hard Prompts | 1508 | 1457 |
| ARC-AGI-2 | 89.2% | — |
| ARC-AGI-1 | 98.5% | — |
| CritPt | 18.3% | — |
| Chess Puzzles | 61% | — |
| Thematic Generalization | — | 45.9% |
| Mystery Game Puzzles | 47% | — |
| DTBench | 95.7% | — |
| LMCA | 52.9% | — |
| Surface Evolver Bench | 76.9% | — |
| Epoch Capabilities Index | 156.71 | — |
Math Gemini 3.8 Flash leads
Gemini 3.8 Flash: 65.3 (#28), MiMo-V2-Pro: 39.5 (#102)
| Benchmark | Gemini 3.8 Flash | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1528 | 1447 |
| FrontierMath (Tiers 1-3) | 68.4% | — |
| FrontierMath Tier 4 | 22% | — |
| OTIS Mock AIME 2024-2025 | 98.9% | — |
| ProofBench | 48% | — |
Knowledge Gemini 3.8 Flash leads
Gemini 3.8 Flash: 74.8 (#2), MiMo-V2-Pro: 41.4 (#111)
| Benchmark | Gemini 3.8 Flash | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1524 | 1478 |
| GPQA Diamond | 95.4% | — |
| Humanity's Last Exam | 44.5% | — |
| SimpleQA Verified | 69.7% | — |
Multimodal Not comparable
Gemini 3.8 Flash: 40.7 (#45), MiMo-V2-Pro: —
| Benchmark | Gemini 3.8 Flash | MiMo-V2-Pro |
|---|---|---|
| LMArena Vision | 1314 | — |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 31.7% | — |
Multilingual Gemini 3.8 Flash leads
Gemini 3.8 Flash: 58.0 (#5), MiMo-V2-Pro: 52.7 (#81)
| Benchmark | Gemini 3.8 Flash | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1491 | 1416 |
| LMArena Chinese | 1554 | 1456 |
| LMArena French | 1498 | 1469 |
| LMArena German | 1493 | 1417 |
| LMArena Japanese | 1502 | 1366 |
| LMArena Korean | 1459 | 1400 |
| LMArena Russian | 1515 | 1427 |
| LMArena Spanish | 1485 | 1457 |
Instruction Following Gemini 3.8 Flash leads
Gemini 3.8 Flash: 78.0 (#13), MiMo-V2-Pro: 76.0 (#49)
| Benchmark | Gemini 3.8 Flash | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1490 | 1445 |
Long Context Gemini 3.8 Flash leads
Gemini 3.8 Flash: 46.3 (#24), MiMo-V2-Pro: 41.5 (#138)
| Benchmark | Gemini 3.8 Flash | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1508 | 1455 |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |
Writing & Preference Gemini 3.8 Flash leads
Gemini 3.8 Flash: 72.2 (#15), MiMo-V2-Pro: 62.8 (#70)
| Benchmark | Gemini 3.8 Flash | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1499 | 1436 |
| LMArena Creative Writing | 1492 | 1415 |
| LMArena Multi-Turn | 1501 | 1456 |
| EQ-Bench Creative Writing | 1748 | — |
Frequently asked questions
Is Gemini 3.8 Flash better than MiMo-V2-Pro?
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 43.0 on the Noometry Index. MiMo-V2-Pro costs 2.8× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.8 Flash or MiMo-V2-Pro?
MiMo-V2-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Gemini 3.8 Flash lists at $0.75 and $3.75.
Is Gemini 3.8 Flash or MiMo-V2-Pro better for coding?
Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 43.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do Gemini 3.8 Flash and MiMo-V2-Pro share?
20 benchmarks have published results for both models. Gemini 3.8 Flash has 50 scored results on Noometry and MiMo-V2-Pro has 23.