Model comparison
GPT-4.5 vs MiMo-V2.5
MiMo-V2.5 is the stronger model overall, scoring 43.0 to 36.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. GPT-4.5 scores higher in 1 category and MiMo-V2.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.5 leads 27.8 to 14.1.
- MiMo-V2.5 has downloadable open weights; the other is API-only.
Side by side
| GPT-4.5 | MiMo-V2.5 | |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 36.9 | 43.0 |
| Released | 2025-02-27 | 2026-04-22 |
| Weights | Proprietary | Open |
| Context window | — | 1.05M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.14 |
| Output $ / M tokens | — | $0.28 |
| Results tracked | 42 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
GPT-4.5: 41.8 (#102), MiMo-V2.5: 43.6 (#75)
| Benchmark | GPT-4.5 | MiMo-V2.5 |
|---|---|---|
| LMArena Coding | 1397 | 1469 |
| Aider Polyglot | 44.9% | — |
| LMArena WebDev | — | 1438 |
| SciCode | — | 43.1% |
| WeirdML | 39.4% | — |
| LiveBench Coding | 75.2% | — |
| ALE-Bench | — | 513.95 |
Agentic & Tool Use Not comparable
GPT-4.5: 27.6 (#92), MiMo-V2.5: —
| Benchmark | GPT-4.5 | MiMo-V2.5 |
|---|---|---|
| Cybench | 17.5% | — |
Reasoning MiMo-V2.5 leads
GPT-4.5: 14.1 (#320), MiMo-V2.5: 27.8 (#98)
| Benchmark | GPT-4.5 | MiMo-V2.5 |
|---|---|---|
| LMArena Hard Prompts | 1404 | 1450 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 34.5% | — |
| ARC-AGI-1 | 10.3% | — |
| CritPt | — | 3.7% |
| EnigmaEval | 3.2% | — |
| LiveBench Reasoning | 71.1% | — |
| LiveBench Data Analysis | 64.3% | — |
| Epoch Capabilities Index | 136.74 | — |
| ForecastBench | 61.7 | — |
| LiveBench | 69% | — |
Math MiMo-V2.5 leads
GPT-4.5: 31.0 (#200), MiMo-V2.5: 35.4 (#145)
| Benchmark | GPT-4.5 | MiMo-V2.5 |
|---|---|---|
| LMArena Math | 1412 | 1436 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| ProofBench | — | 16% |
| LiveBench Math | 69.3% | — |
| MATH Level 5 | 78.6% | — |
Knowledge MiMo-V2.5 leads
GPT-4.5: 32.4 (#205), MiMo-V2.5: 40.2 (#109)
| Benchmark | GPT-4.5 | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1394 | 1459 |
| GPQA Diamond | 68.7% | — |
| Humanity's Last Exam | 5.4% | — |
| Confabulations | 13.6% | — |
Multimodal MiMo-V2.5 leads
GPT-4.5: 37.0 (#68), MiMo-V2.5: 39.0 (#53)
| Benchmark | GPT-4.5 | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | 1195 | 1245 |
| VPCT | 45% | — |
Multilingual Too close to call
GPT-4.5: 52.7 (#78), MiMo-V2.5: 52.0 (#96)
| Benchmark | GPT-4.5 | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1413 | 1404 |
| LMArena Chinese | 1421 | 1467 |
| LMArena French | 1417 | 1447 |
| LMArena German | 1457 | 1421 |
| LMArena Japanese | 1416 | 1304 |
| LMArena Korean | 1392 | 1363 |
| LMArena Russian | 1419 | 1395 |
| LMArena Spanish | — | 1412 |
Instruction Following MiMo-V2.5 leads
GPT-4.5: 72.8 (#129), MiMo-V2.5: 75.7 (#55)
| Benchmark | GPT-4.5 | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1404 | 1433 |
| LiveBench Instruction Following | 72.3% | — |
Long Context MiMo-V2.5 leads
GPT-4.5: 40.4 (#150), MiMo-V2.5: 44.1 (#69)
| Benchmark | GPT-4.5 | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1406 | 1444 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference MiMo-V2.5 leads
GPT-4.5: 57.1 (#129), MiMo-V2.5: 61.8 (#82)
| Benchmark | GPT-4.5 | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1417 | 1427 |
| LMArena Creative Writing | 1394 | 1392 |
| LMArena Multi-Turn | 1444 | 1445 |
| 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-V2.5?
MiMo-V2.5 is the stronger model overall, scoring 43.0 to 36.9 on the Noometry Index.
Is GPT-4.5 or MiMo-V2.5 better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.6 versus 41.8 in the Noometry coding category.
How many benchmarks do GPT-4.5 and MiMo-V2.5 share?
17 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and MiMo-V2.5 has 23.