# GPT-4.5 vs MiMo-V2.6-Pro

> MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 37.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-5-vs-mimo-v2-6-pro
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. GPT-4.5 scores higher in 0 categories and MiMo-V2.6-Pro in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.6-Pro leads 43.1 to 13.9.
- MiMo-V2.6-Pro has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4.5 | MiMo-V2.6-Pro |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 37.2 | 50.3 |
| Rank | 208 | 49 |
| Context | — | 1.05M |
| Input $/M | — | $0.43 |
| Output $/M | — | $0.87 |
| Weights | Proprietary | Open |

## Coding

- GPT-4.5: 42.2 (#109)
- MiMo-V2.6-Pro: 55.5 (#23)

| Benchmark | GPT-4.5 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Coding | 1396 | 1534 |
| Aider Polyglot | 44.9% | — |
| LMArena WebDev | — | 1629 |
| SciCode | — | 60.9% |
| WeirdML | 39.4% | — |
| LiveBench Coding | 75.2% | — |
| ALE-Bench | — | 1,158 |

## Agentic & Tool Use

- GPT-4.5: 27.9 (#97)
- MiMo-V2.6-Pro: 37.5 (#35)

| Benchmark | GPT-4.5 | MiMo-V2.6-Pro |
|---|---|---|
| APEX-Agents | — | 59.5% |
| Cybench | 17.5% | — |

## Reasoning

- GPT-4.5: 13.9 (#330)
- MiMo-V2.6-Pro: 43.1 (#50)

| Benchmark | GPT-4.5 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Hard Prompts | 1403 | 1512 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 34.5% | — |
| ARC-AGI-1 | 10.3% | — |
| CritPt | — | 26.6% |
| EnigmaEval | 3.2% | — |
| LiveBench Reasoning | 71.1% | — |
| LiveBench Data Analysis | 64.3% | — |
| Epoch Capabilities Index | 136.74 | — |
| ForecastBench | 61.7 | — |
| LiveBench | 69% | — |

## Math

- GPT-4.5: 32.6 (#211)
- MiMo-V2.6-Pro: 54.5 (#45)

| Benchmark | GPT-4.5 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Math | 1412 | 1494 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| ProofBench | — | 70% |
| LiveBench Math | 69.3% | — |
| MATH Level 5 | 78.6% | — |

## Knowledge

- GPT-4.5: 32.5 (#211)
- MiMo-V2.6-Pro: 43.5 (#92)

| Benchmark | GPT-4.5 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1394 | 1543 |
| GPQA Diamond | 68.7% | — |
| Humanity's Last Exam | 5.4% | — |
| Confabulations | 13.6% | — |

## Multimodal

- GPT-4.5: 37.6 (#71)
- MiMo-V2.6-Pro: 40.8 (#43)

| Benchmark | GPT-4.5 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | 1195 | 1264 |
| VPCT | 45% | — |

## Multilingual

- GPT-4.5: 52.5 (#83)
- MiMo-V2.6-Pro: 56.9 (#14)

| Benchmark | GPT-4.5 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1413 | 1474 |
| LMArena Chinese | 1421 | 1529 |
| LMArena Russian | 1419 | 1480 |
| LMArena French | 1418 | — |
| LMArena German | 1457 | — |
| LMArena Japanese | 1416 | — |
| LMArena Korean | 1392 | — |

## Instruction Following

- GPT-4.5: 72.6 (#134)
- MiMo-V2.6-Pro: 78.2 (#12)

| Benchmark | GPT-4.5 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1404 | 1493 |
| LiveBench Instruction Following | 72.3% | — |

## Long Context

- GPT-4.5: 40.4 (#155)
- MiMo-V2.6-Pro: 46.0 (#27)

| Benchmark | GPT-4.5 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1406 | 1501 |
| Fiction.LiveBench | 63.9% | — |

## Writing & Preference

- GPT-4.5: 56.9 (#134)
- MiMo-V2.6-Pro: 66.8 (#33)

| Benchmark | GPT-4.5 | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1417 | 1492 |
| LMArena Creative Writing | 1394 | 1468 |
| LMArena Multi-Turn | 1444 | 1464 |
| Short-Story Creative Writing | 75.6% | — |
| EQ-Bench Creative Writing | 1258 | — |
| LiveBench Language | 61.5% | — |

## FAQ

### Is GPT-4.5 better than MiMo-V2.6-Pro?

MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 37.2 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: 55.5 versus 42.2 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 19.