Model comparison
Gemma 2 9B vs MiMo-V2.6-Pro
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 25.9 on the Noometry Index.
Last verified . 12 shared benchmarks.
GoogleSummary
- They share 12 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and MiMo-V2.6-Pro in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2.6-Pro leads 54.5 to 9.9.
Side by side
| Gemma 2 9B | MiMo-V2.6-Pro | |
|---|---|---|
| Provider | Xiaomi | |
| Noometry Index | 25.9 | 50.3 |
| Released | 2024-06-24 | 2026-09-21 |
| Weights | Open | Open |
| Context window | — | 1.05M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.43 |
| Output $ / M tokens | — | $0.87 |
| Results tracked | 35 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Pro leads
Gemma 2 9B: 29.4 (#304), MiMo-V2.6-Pro: 55.5 (#23)
| Benchmark | Gemma 2 9B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Coding | 1173 | 1534 |
| LMArena WebDev | — | 1629 |
| SciCode | — | 60.9% |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
| ALE-Bench | — | 1,158 |
Agentic & Tool Use Not comparable
Gemma 2 9B: —, MiMo-V2.6-Pro: 37.5 (#35)
| Benchmark | Gemma 2 9B | MiMo-V2.6-Pro |
|---|---|---|
| APEX-Agents | — | 59.5% |
Reasoning MiMo-V2.6-Pro leads
Gemma 2 9B: 15.9 (#309), MiMo-V2.6-Pro: 43.1 (#50)
| Benchmark | Gemma 2 9B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1512 |
| CritPt | — | 26.6% |
| LiveBench Reasoning | 15.2% | — |
| LiveBench Data Analysis | 36.4% | — |
| Epoch Capabilities Index | 119.83 | — |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |
Math MiMo-V2.6-Pro leads
Gemma 2 9B: 9.9 (#318), MiMo-V2.6-Pro: 54.5 (#45)
| Benchmark | Gemma 2 9B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Math | 1183 | 1494 |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| ProofBench | — | 70% |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
| GSM8K | 84.9% | — |
Knowledge MiMo-V2.6-Pro leads
Gemma 2 9B: 9.7 (#305), MiMo-V2.6-Pro: 43.5 (#92)
| Benchmark | Gemma 2 9B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1147 | 1543 |
| GPQA Diamond | 27.5% | — |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |
Multimodal Not comparable
Gemma 2 9B: —, MiMo-V2.6-Pro: 40.8 (#43)
| Benchmark | Gemma 2 9B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | — | 1264 |
Multilingual MiMo-V2.6-Pro leads
Gemma 2 9B: 36.6 (#238), MiMo-V2.6-Pro: 56.9 (#14)
| Benchmark | Gemma 2 9B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1188 | 1474 |
| LMArena Chinese | 1185 | 1529 |
| LMArena Russian | 1200 | 1480 |
| LMArena French | 1190 | — |
| LMArena German | 1186 | — |
| LMArena Japanese | 1144 | — |
| LMArena Korean | 1137 | — |
| LMArena Spanish | 1200 | — |
Instruction Following MiMo-V2.6-Pro leads
Gemma 2 9B: 57.6 (#269), MiMo-V2.6-Pro: 78.2 (#12)
| Benchmark | Gemma 2 9B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1178 | 1493 |
| LiveBench Instruction Following | 52.6% | — |
Long Context MiMo-V2.6-Pro leads
Gemma 2 9B: 36.3 (#233), MiMo-V2.6-Pro: 46.0 (#27)
| Benchmark | Gemma 2 9B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1197 | 1501 |
Writing & Preference MiMo-V2.6-Pro leads
Gemma 2 9B: 32.1 (#281), MiMo-V2.6-Pro: 66.8 (#33)
| Benchmark | Gemma 2 9B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1207 | 1492 |
| LMArena Creative Writing | 1206 | 1468 |
| LMArena Multi-Turn | 1193 | 1464 |
| EQ-Bench Creative Writing | 841 | — |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than MiMo-V2.6-Pro?
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 25.9 on the Noometry Index.
Is Gemma 2 9B or MiMo-V2.6-Pro better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and MiMo-V2.6-Pro share?
12 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and MiMo-V2.6-Pro has 19.