# GPT-4 Turbo vs MiMo-V2.6-Pro

> MiMo-V2.6-Pro is the stronger model overall, scoring 46.7 to 30.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-turbo-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 Turbo 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 math, where MiMo-V2.6-Pro leads 37.9 to 8.6.
- MiMo-V2.6-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 128K.
- MiMo-V2.6-Pro has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4 Turbo | MiMo-V2.6-Pro |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 30.3 | 46.7 |
| Rank | 281 | 55 |
| Context | 128K | 1.05M |
| Input $/M | $10 | $0.43 |
| Output $/M | $30 | $0.87 |
| Weights | Proprietary | Open |

## Coding

- GPT-4 Turbo: 33.4 (#247)
- MiMo-V2.6-Pro: 53.2 (#27)

| Benchmark | GPT-4 Turbo | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Coding | 1268 | 1538 |
| LMArena WebDev | — | 1618 |
| WeirdML | 18% | — |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 58.2% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |

## Agentic & Tool Use

- GPT-4 Turbo: —
- MiMo-V2.6-Pro: —

| Benchmark | GPT-4 Turbo | MiMo-V2.6-Pro |
|---|---|---|
| METR Time Horizons | 36.7% | — |

## Reasoning

- GPT-4 Turbo: 14.9 (#311)
- MiMo-V2.6-Pro: 30.4 (#76)

| Benchmark | GPT-4 Turbo | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1511 |
| SimpleBench | 25.1% | — |
| Chess Puzzles | 6% | — |
| DTBench | 61.6% | — |
| LMCA | 9.8% | — |
| Epoch Capabilities Index | 127.25 | — |
| ForecastBench | 59.4 | — |

## Math

- GPT-4 Turbo: 8.6 (#316)
- MiMo-V2.6-Pro: 37.9 (#91)

| Benchmark | GPT-4 Turbo | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Math | 1272 | 1497 |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| MATH Level 5 | 46.7% | — |

## Knowledge

- GPT-4 Turbo: 24.3 (#263)
- MiMo-V2.6-Pro: 43.0 (#85)

| Benchmark | GPT-4 Turbo | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1223 | 1548 |
| GPQA Diamond | 46.6% | — |
| Confabulations | 28.4% | — |
| MMLU | 81.3% | — |

## Multimodal

- GPT-4 Turbo: 30.0 (#104)
- MiMo-V2.6-Pro: 40.2 (#40)

| Benchmark | GPT-4 Turbo | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | 1090 | 1265 |

## Multilingual

- GPT-4 Turbo: 40.7 (#211)
- MiMo-V2.6-Pro: 57.0 (#15)

| Benchmark | GPT-4 Turbo | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1245 | 1474 |
| LMArena Chinese | 1242 | 1532 |
| LMArena Russian | 1259 | 1481 |
| LMArena French | 1275 | — |
| LMArena German | 1259 | — |
| LMArena Japanese | 1194 | — |
| LMArena Korean | 1187 | — |
| LMArena Spanish | 1260 | — |

## Instruction Following

- GPT-4 Turbo: 66.0 (#211)
- MiMo-V2.6-Pro: 78.2 (#10)

| Benchmark | GPT-4 Turbo | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1250 | 1490 |

## Long Context

- GPT-4 Turbo: 38.0 (#200)
- MiMo-V2.6-Pro: 46.0 (#26)

| Benchmark | GPT-4 Turbo | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1254 | 1500 |

## Writing & Preference

- GPT-4 Turbo: 47.9 (#201)
- MiMo-V2.6-Pro: 66.9 (#32)

| Benchmark | GPT-4 Turbo | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1272 | 1491 |
| LMArena Creative Writing | 1269 | 1465 |
| LMArena Multi-Turn | 1267 | 1463 |

## FAQ

### Is GPT-4 Turbo better than MiMo-V2.6-Pro?

MiMo-V2.6-Pro is the stronger model overall, scoring 46.7 to 30.3 on the Noometry Index.

### Which is cheaper, GPT-4 Turbo or MiMo-V2.6-Pro?

MiMo-V2.6-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; GPT-4 Turbo lists at $10 and $30.

### Is GPT-4 Turbo or MiMo-V2.6-Pro better for coding?

MiMo-V2.6-Pro scores higher on coding benchmarks: 53.2 versus 33.4 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.6-Pro does, with 1.05M tokens against 128K.

### How many benchmarks do GPT-4 Turbo and MiMo-V2.6-Pro share?

13 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and MiMo-V2.6-Pro has 14.