Model comparison
Gemini 3.6 Flash vs MiMo-V2.5-Pro
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 44.8 on the Noometry Index. MiMo-V2.5-Pro costs 2.8× less per token, which makes it the better buy when Gemini 3.6 Flash's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
GoogleSummary
- They share 26 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 6 categories and MiMo-V2.5-Pro in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.6 Flash leads 58.9 to 25.9.
- The biggest single-benchmark swing is NYT Connections (extended): 89% for Gemini 3.6 Flash and 34.4% for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.6 Flash.
- MiMo-V2.5-Pro has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.6 Flash | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | Xiaomi | |
| Noometry Index | 54.1 | 44.8 |
| Released | 2026-07-21 | 2026-04-22 |
| Weights | Proprietary | Open |
| 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 | 46 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.6 Flash leads
Gemini 3.6 Flash: 49.6 (#45), MiMo-V2.5-Pro: 47.0 (#58)
| Benchmark | Gemini 3.6 Flash | MiMo-V2.5-Pro |
|---|---|---|
| LMArena WebDev | 1536 | 1477 |
| SciCode | 52.7% | 50.2% |
| LMArena Coding | 1492 | 1502 |
| ALE-Bench | 715.52 | 899.8 |
| DeepSWE | 46.7% | — |
| FrontierCode | 34.4% | — |
| WeirdML | 56.1% | — |
Agentic & Tool Use Not comparable
Gemini 3.6 Flash: 32.4 (#56), MiMo-V2.5-Pro: —
| Benchmark | Gemini 3.6 Flash | MiMo-V2.5-Pro |
|---|---|---|
| APEX-Agents | 46.9% | — |
| GDP.pdf | 14% | — |
Reasoning Gemini 3.6 Flash leads
Gemini 3.6 Flash: 58.9 (#20), MiMo-V2.5-Pro: 25.9 (#124)
| Benchmark | Gemini 3.6 Flash | MiMo-V2.5-Pro |
|---|---|---|
| NYT Connections (extended) | 89% | 34.4% |
| CritPt | 10.6% | 4% |
| LMArena Hard Prompts | 1486 | 1487 |
| DTBench | 95.5% | 84.5% |
| LMCA | 44.9% | 29.5% |
| ARC-AGI-2 | 60.4% | — |
| ARC-AGI-1 | 91.2% | — |
| Chess Puzzles | 43% | — |
| Mystery Game Puzzles | 30% | — |
| Epoch Capabilities Index | 154.36 | — |
Math Gemini 3.6 Flash leads
Gemini 3.6 Flash: 57.0 (#33), MiMo-V2.5-Pro: 38.6 (#84)
| Benchmark | Gemini 3.6 Flash | MiMo-V2.5-Pro |
|---|---|---|
| ProofBench | 36% | 22% |
| LMArena Math | 1504 | 1480 |
| FrontierMath (Tiers 1-3) | 58.9% | — |
| FrontierMath Tier 4 | 22% | — |
| MathArena Final-Answer Competitions | 70.8% | — |
| OTIS Mock AIME 2024-2025 | 94.2% | — |
Knowledge Gemini 3.6 Flash leads
Gemini 3.6 Flash: 67.8 (#7), MiMo-V2.5-Pro: 41.5 (#100)
| Benchmark | Gemini 3.6 Flash | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1489 | 1501 |
| GPQA Diamond | 94.1% | — |
| SimpleQA Verified | 66.2% | — |
Multimodal Not comparable
Gemini 3.6 Flash: 38.7 (#55), MiMo-V2.5-Pro: —
| Benchmark | Gemini 3.6 Flash | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Vision | 1297 | — |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 23.3% | — |
| LMArena Document | 1456 | — |
Multilingual Gemini 3.6 Flash leads
Gemini 3.6 Flash: 56.8 (#17), MiMo-V2.5-Pro: 55.3 (#33)
| Benchmark | Gemini 3.6 Flash | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1470 | 1449 |
| LMArena Chinese | 1530 | 1507 |
| LMArena French | 1501 | 1489 |
| LMArena German | 1478 | 1455 |
| LMArena Japanese | 1477 | 1418 |
| LMArena Korean | 1435 | 1436 |
| LMArena Russian | 1490 | 1450 |
| LMArena Spanish | 1477 | 1470 |
Instruction Following Too close to call
Gemini 3.6 Flash: 77.2 (#27), MiMo-V2.5-Pro: 77.6 (#21)
| Benchmark | Gemini 3.6 Flash | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1467 | 1477 |
Long Context Too close to call
Gemini 3.6 Flash: 45.1 (#47), MiMo-V2.5-Pro: 45.4 (#38)
| Benchmark | Gemini 3.6 Flash | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1475 | 1482 |
Writing & Preference Gemini 3.6 Flash leads
Gemini 3.6 Flash: 68.3 (#26), MiMo-V2.5-Pro: 65.5 (#47)
| Benchmark | Gemini 3.6 Flash | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1478 | 1465 |
| LMArena Creative Writing | 1464 | 1440 |
| EQ-Bench Creative Writing | 1604 | 1493 |
| LMArena Multi-Turn | 1481 | 1477 |
| EQ-Bench 4 | — | 1208 |
Frequently asked questions
Is Gemini 3.6 Flash better than MiMo-V2.5-Pro?
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 44.8 on the Noometry Index. MiMo-V2.5-Pro costs 2.8× less per token, which makes it the better buy when Gemini 3.6 Flash's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.6 Flash or MiMo-V2.5-Pro?
MiMo-V2.5-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Gemini 3.6 Flash lists at $0.75 and $3.75.
Is Gemini 3.6 Flash or MiMo-V2.5-Pro better for coding?
Gemini 3.6 Flash scores higher on coding benchmarks: 49.6 versus 47.0 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do Gemini 3.6 Flash and MiMo-V2.5-Pro share?
26 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and MiMo-V2.5-Pro has 27.