Model comparison
Gemma 3 1B vs MiMo-V2.5
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 21.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
GoogleSummary
- The widest gap is in knowledge, where MiMo-V2.5 leads 40.8 to 7.0.
Side by side
| Gemma 3 1B | MiMo-V2.5 | |
|---|---|---|
| Provider | Xiaomi | |
| Noometry Index | 21.1 | 43.4 |
| Released | 2025-03-12 | 2026-04-22 |
| Weights | Open | Open |
| Context window | — | 1.05M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.14 |
| Output $ / M tokens | — | $0.28 |
| Results tracked | 4 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Gemma 3 1B: —, MiMo-V2.5: 43.9 (#81)
| Benchmark | Gemma 3 1B | MiMo-V2.5 |
|---|---|---|
| LMArena WebDev | — | 1438 |
| SciCode | — | 43.1% |
| LMArena Coding | — | 1469 |
| ALE-Bench | — | 513.95 |
Agentic & Tool Use Not comparable
Gemma 3 1B: 13.7 (#152), MiMo-V2.5: —
| Benchmark | Gemma 3 1B | MiMo-V2.5 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 7.2% | — |
Reasoning MiMo-V2.5 leads
Gemma 3 1B: 19.2 (#264), MiMo-V2.5: 28.6 (#101)
| Benchmark | Gemma 3 1B | MiMo-V2.5 |
|---|---|---|
| CritPt | — | 3.7% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | — | 1450 |
Math MiMo-V2.5 leads
Gemma 3 1B: 10.2 (#316), MiMo-V2.5: 36.8 (#163)
| Benchmark | Gemma 3 1B | MiMo-V2.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| ProofBench | — | 16% |
| LMArena Math | — | 1436 |
Knowledge MiMo-V2.5 leads
Gemma 3 1B: 7.0 (#314), MiMo-V2.5: 40.8 (#115)
| Benchmark | Gemma 3 1B | MiMo-V2.5 |
|---|---|---|
| GPQA Diamond | 19.9% | — |
| LMArena Expert | — | 1460 |
Multimodal Not comparable
Gemma 3 1B: —, MiMo-V2.5: 39.8 (#54)
| Benchmark | Gemma 3 1B | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | — | 1247 |
Multilingual Not comparable
Gemma 3 1B: —, MiMo-V2.5: 51.9 (#99)
| Benchmark | Gemma 3 1B | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | — | 1404 |
| LMArena Chinese | — | 1468 |
| LMArena French | — | 1447 |
| LMArena German | — | 1421 |
| LMArena Japanese | — | 1306 |
| LMArena Korean | — | 1363 |
| LMArena Russian | — | 1395 |
| LMArena Spanish | — | 1416 |
Instruction Following Not comparable
Gemma 3 1B: —, MiMo-V2.5: 75.5 (#60)
| Benchmark | Gemma 3 1B | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | — | 1434 |
Long Context Not comparable
Gemma 3 1B: —, MiMo-V2.5: 44.2 (#73)
| Benchmark | Gemma 3 1B | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | — | 1445 |
Writing & Preference Not comparable
Gemma 3 1B: —, MiMo-V2.5: 61.6 (#86)
| Benchmark | Gemma 3 1B | MiMo-V2.5 |
|---|---|---|
| LMArena Text | — | 1428 |
| LMArena Creative Writing | — | 1393 |
| LMArena Multi-Turn | — | 1445 |
Frequently asked questions
Is Gemma 3 1B better than MiMo-V2.5?
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 21.1 on the Noometry Index.
How many benchmarks do Gemma 3 1B and MiMo-V2.5 share?
0 benchmarks have published results for both models. Gemma 3 1B has 4 scored results on Noometry and MiMo-V2.5 has 23.