# GPT-4 vs MiMo-V2.5-Pro

> MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 28.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-vs-mimo-v2-5-pro
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. GPT-4 scores higher in 0 categories and MiMo-V2.5-Pro in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5-Pro leads 65.5 to 35.0.
- The biggest single-benchmark swing is DTBench: 62.7% for GPT-4 and 84.5% for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $30 / $60 for GPT-4.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 8K.
- MiMo-V2.5-Pro has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4 | MiMo-V2.5-Pro |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 28.9 | 44.8 |
| Rank | 308 | 70 |
| Context | 8K | 1.05M |
| Input $/M | $30 | $0.43 |
| Output $/M | $60 | $0.87 |
| Weights | Proprietary | Open |

## Coding

- GPT-4: 31.2 (#277)
- MiMo-V2.5-Pro: 47.0 (#58)

| Benchmark | GPT-4 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Coding | 1254 | 1502 |
| LMArena WebDev | — | 1477 |
| SciCode | — | 50.2% |
| WeirdML | 12.4% | — |
| BigCodeBench Instruct | 46% | — |
| BigCodeBench Complete | 57.2% | — |
| ALE-Bench | — | 899.8 |
| HumanEval+ | 79.3% | — |

## Agentic & Tool Use

- GPT-4: —
- MiMo-V2.5-Pro: —

| Benchmark | GPT-4 | MiMo-V2.5-Pro |
|---|---|---|
| METR Time Horizons | 36.1% | — |

## Reasoning

- GPT-4: 17.3 (#285)
- MiMo-V2.5-Pro: 25.9 (#124)

| Benchmark | GPT-4 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1487 |
| DTBench | 62.7% | 84.5% |
| LMCA | 17.1% | 29.5% |
| NYT Connections (extended) | — | 34.4% |
| CritPt | — | 4% |
| Chess Puzzles | 4% | — |
| Mystery Game Puzzles | 12% | — |
| BIG-Bench Hard | 75.1% | — |
| Epoch Capabilities Index | 125.88 | — |
| ForecastBench | 57.8 | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |

## Math

- GPT-4: 10.1 (#304)
- MiMo-V2.5-Pro: 38.6 (#84)

| Benchmark | GPT-4 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1269 | 1480 |
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| ProofBench | — | 22% |
| MATH Level 5 | 23% | — |
| GSM8K | 92% | — |

## Knowledge

- GPT-4: 18.4 (#277)
- MiMo-V2.5-Pro: 41.5 (#100)

| Benchmark | GPT-4 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1211 | 1501 |
| GPQA Diamond | 35.7% | — |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |

## Multilingual

- GPT-4: 40.8 (#210)
- MiMo-V2.5-Pro: 55.3 (#33)

| Benchmark | GPT-4 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1246 | 1449 |
| LMArena Chinese | 1242 | 1507 |
| LMArena French | 1282 | 1489 |
| LMArena German | 1251 | 1455 |
| LMArena Japanese | 1209 | 1418 |
| LMArena Korean | 1184 | 1436 |
| LMArena Russian | 1251 | 1450 |
| LMArena Spanish | 1261 | 1470 |

## Instruction Following

- GPT-4: 65.5 (#217)
- MiMo-V2.5-Pro: 77.6 (#21)

| Benchmark | GPT-4 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1241 | 1477 |

## Long Context

- GPT-4: 37.7 (#207)
- MiMo-V2.5-Pro: 45.4 (#38)

| Benchmark | GPT-4 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1244 | 1482 |

## Writing & Preference

- GPT-4: 35.0 (#263)
- MiMo-V2.5-Pro: 65.5 (#47)

| Benchmark | GPT-4 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1263 | 1465 |
| LMArena Creative Writing | 1244 | 1440 |
| EQ-Bench Creative Writing | 752 | 1493 |
| LMArena Multi-Turn | 1257 | 1477 |
| EQ-Bench 4 | — | 1208 |

## FAQ

### Is GPT-4 better than MiMo-V2.5-Pro?

MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 28.9 on the Noometry Index.

### Which is cheaper, GPT-4 or MiMo-V2.5-Pro?

MiMo-V2.5-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; GPT-4 lists at $30 and $60.

### Is GPT-4 or MiMo-V2.5-Pro better for coding?

MiMo-V2.5-Pro scores higher on coding benchmarks: 47.0 versus 31.2 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.5-Pro does, with 1.05M tokens against 8K.

### How many benchmarks do GPT-4 and MiMo-V2.5-Pro share?

20 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and MiMo-V2.5-Pro has 27.