Model comparison
MiMo-V2.6-Pro vs StarCoder 2 15B
MiMo-V2.6-Pro has enough public results to be ranked (#49); StarCoder 2 15B does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
NVIDIASummary
- The widest gap is in coding, where MiMo-V2.6-Pro leads 55.5 to 36.6.
Side by side
| MiMo-V2.6-Pro | StarCoder 2 15B | |
|---|---|---|
| Provider | Xiaomi | NVIDIA |
| Noometry Index | 50.3 | 38.1 |
| Released | 2026-09-21 | 2024-02-20 |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.43 | — |
| Output $ / M tokens | $0.87 | — |
| Results tracked | 19 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 55.5 (#23), StarCoder 2 15B: 36.6
| Benchmark | MiMo-V2.6-Pro | StarCoder 2 15B |
|---|---|---|
| LMArena WebDev | 1629 | — |
| SciCode | 60.9% | — |
| LMArena Coding | 1534 | — |
| BigCodeBench Complete | — | 38.4% |
| ALE-Bench | 1,158 | — |
| HumanEval+ | — | 37.8% |
Agentic & Tool Use Not comparable
MiMo-V2.6-Pro: 37.5 (#35), StarCoder 2 15B: —
| Benchmark | MiMo-V2.6-Pro | StarCoder 2 15B |
|---|---|---|
| APEX-Agents | 59.5% | — |
Reasoning Not comparable
MiMo-V2.6-Pro: 43.1 (#50), StarCoder 2 15B: —
| Benchmark | MiMo-V2.6-Pro | StarCoder 2 15B |
|---|---|---|
| CritPt | 26.6% | — |
| LMArena Hard Prompts | 1512 | — |
| Epoch Capabilities Index | — | 105 |
| WinoGrande | — | 64.3% |
Math Not comparable
MiMo-V2.6-Pro: 54.5 (#45), StarCoder 2 15B: —
| Benchmark | MiMo-V2.6-Pro | StarCoder 2 15B |
|---|---|---|
| ProofBench | 70% | — |
| LMArena Math | 1494 | — |
| GSM8K | — | 57.7% |
Knowledge Not comparable
MiMo-V2.6-Pro: 43.5 (#92), StarCoder 2 15B: —
| Benchmark | MiMo-V2.6-Pro | StarCoder 2 15B |
|---|---|---|
| LMArena Expert | 1543 | — |
| ARC (AI2) Challenge | — | 47.2% |
| MMLU | — | 64.1% |
Multimodal Not comparable
MiMo-V2.6-Pro: 40.8 (#43), StarCoder 2 15B: —
| Benchmark | MiMo-V2.6-Pro | StarCoder 2 15B |
|---|---|---|
| LMArena Vision | 1264 | — |
Multilingual Not comparable
MiMo-V2.6-Pro: 56.9 (#14), StarCoder 2 15B: —
| Benchmark | MiMo-V2.6-Pro | StarCoder 2 15B |
|---|---|---|
| LMArena Non-English | 1474 | — |
| LMArena Chinese | 1529 | — |
| LMArena Russian | 1480 | — |
Instruction Following Not comparable
MiMo-V2.6-Pro: 78.2 (#12), StarCoder 2 15B: —
| Benchmark | MiMo-V2.6-Pro | StarCoder 2 15B |
|---|---|---|
| LMArena Instruction Following | 1493 | — |
Long Context Not comparable
MiMo-V2.6-Pro: 46.0 (#27), StarCoder 2 15B: —
| Benchmark | MiMo-V2.6-Pro | StarCoder 2 15B |
|---|---|---|
| LMArena Longer Query | 1501 | — |
Writing & Preference Not comparable
MiMo-V2.6-Pro: 66.8 (#33), StarCoder 2 15B: —
| Benchmark | MiMo-V2.6-Pro | StarCoder 2 15B |
|---|---|---|
| LMArena Text | 1492 | — |
| LMArena Creative Writing | 1468 | — |
| LMArena Multi-Turn | 1464 | — |
Frequently asked questions
Is MiMo-V2.6-Pro better than StarCoder 2 15B?
MiMo-V2.6-Pro has enough public results to be ranked (#49); StarCoder 2 15B does not yet, so treat this comparison as directional.
Is MiMo-V2.6-Pro or StarCoder 2 15B better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 36.6 in the Noometry coding category.
How many benchmarks do MiMo-V2.6-Pro and StarCoder 2 15B share?
0 benchmarks have published results for both models. MiMo-V2.6-Pro has 19 scored results on Noometry and StarCoder 2 15B has 7.