Model comparison
GPT-4.5 vs MiMo-V2.6-Pro
MiMo-V2.6-Pro is the stronger model overall, scoring 46.7 to 36.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
Summary
- They share 13 benchmarks with published results for both. GPT-4.5 scores higher in 0 categories and MiMo-V2.6-Pro in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.6-Pro leads 30.4 to 14.1.
- MiMo-V2.6-Pro has downloadable open weights; the other is API-only.
Side by side
| GPT-4.5 | MiMo-V2.6-Pro | |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 36.9 | 46.7 |
| Released | 2025-02-27 | 2026-09-22 |
| Weights | Proprietary | Open |
| Context window | — | 1.05M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.43 |
| Output $ / M tokens | — | $0.87 |
| Results tracked | 42 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Pro leads
GPT-4.5: 41.8 (#102), MiMo-V2.6-Pro: 53.2 (#27)
| Benchmark | GPT-4.5 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Coding | 1397 | 1538 |
| Aider Polyglot | 44.9% | — |
| LMArena WebDev | — | 1618 |
| WeirdML | 39.4% | — |
| LiveBench Coding | 75.2% | — |
Agentic & Tool Use Not comparable
GPT-4.5: 27.6 (#92), MiMo-V2.6-Pro: —
| Benchmark | GPT-4.5 | MiMo-V2.6-Pro |
|---|---|---|
| Cybench | 17.5% | — |
Reasoning MiMo-V2.6-Pro leads
GPT-4.5: 14.1 (#320), MiMo-V2.6-Pro: 30.4 (#76)
| Benchmark | GPT-4.5 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Hard Prompts | 1404 | 1511 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 34.5% | — |
| ARC-AGI-1 | 10.3% | — |
| EnigmaEval | 3.2% | — |
| LiveBench Reasoning | 71.1% | — |
| LiveBench Data Analysis | 64.3% | — |
| Epoch Capabilities Index | 136.74 | — |
| ForecastBench | 61.7 | — |
| LiveBench | 69% | — |
Math MiMo-V2.6-Pro leads
GPT-4.5: 31.0 (#200), MiMo-V2.6-Pro: 37.9 (#91)
| Benchmark | GPT-4.5 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Math | 1412 | 1497 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| LiveBench Math | 69.3% | — |
| MATH Level 5 | 78.6% | — |
Knowledge MiMo-V2.6-Pro leads
GPT-4.5: 32.4 (#205), MiMo-V2.6-Pro: 43.0 (#85)
| Benchmark | GPT-4.5 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1394 | 1548 |
| GPQA Diamond | 68.7% | — |
| Humanity's Last Exam | 5.4% | — |
| Confabulations | 13.6% | — |
Multimodal MiMo-V2.6-Pro leads
GPT-4.5: 37.0 (#68), MiMo-V2.6-Pro: 40.2 (#40)
| Benchmark | GPT-4.5 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | 1195 | 1265 |
| VPCT | 45% | — |
Multilingual MiMo-V2.6-Pro leads
GPT-4.5: 52.7 (#78), MiMo-V2.6-Pro: 57.0 (#15)
| Benchmark | GPT-4.5 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1413 | 1474 |
| LMArena Chinese | 1421 | 1532 |
| LMArena Russian | 1419 | 1481 |
| LMArena French | 1417 | — |
| LMArena German | 1457 | — |
| LMArena Japanese | 1416 | — |
| LMArena Korean | 1392 | — |
Instruction Following MiMo-V2.6-Pro leads
GPT-4.5: 72.8 (#129), MiMo-V2.6-Pro: 78.2 (#10)
| Benchmark | GPT-4.5 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1404 | 1490 |
| LiveBench Instruction Following | 72.3% | — |
Long Context MiMo-V2.6-Pro leads
GPT-4.5: 40.4 (#150), MiMo-V2.6-Pro: 46.0 (#26)
| Benchmark | GPT-4.5 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1406 | 1500 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference MiMo-V2.6-Pro leads
GPT-4.5: 57.1 (#129), MiMo-V2.6-Pro: 66.9 (#32)
| Benchmark | GPT-4.5 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1417 | 1491 |
| LMArena Creative Writing | 1394 | 1465 |
| LMArena Multi-Turn | 1444 | 1463 |
| Short-Story Creative Writing | 75.6% | — |
| EQ-Bench Creative Writing | 1258 | — |
| LiveBench Language | 61.5% | — |
Frequently asked questions
Is GPT-4.5 better than MiMo-V2.6-Pro?
MiMo-V2.6-Pro is the stronger model overall, scoring 46.7 to 36.9 on the Noometry Index.
Is GPT-4.5 or MiMo-V2.6-Pro better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 53.2 versus 41.8 in the Noometry coding category.
How many benchmarks do GPT-4.5 and MiMo-V2.6-Pro share?
13 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and MiMo-V2.6-Pro has 14.