# Llama-3.3-70B-Instruct vs MiMo-V2.5

> MiMo-V2.5 is the stronger model overall, scoring 43.0 to 30.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-3-70b-instruct-vs-mimo-v2-5
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 0 categories and MiMo-V2.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2.5 leads 35.4 to 14.3.
- The biggest single-benchmark swing is SciCode: 26% for Llama-3.3-70B-Instruct and 43.1% for MiMo-V2.5.
- Llama-3.3-70B-Instruct is cheaper at $0.10 / $0.32 per million input/output tokens, against $0.14 / $0.28 for MiMo-V2.5.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 128K.

## Snapshot

| | Llama-3.3-70B-Instruct | MiMo-V2.5 |
|---|---|---|
| Provider | Meta | Xiaomi |
| Noometry Index | 30.3 | 43.0 |
| Rank | 283 | 89 |
| Context | 128K | 1.05M |
| Input $/M | $0.10 | $0.14 |
| Output $/M | $0.32 | $0.28 |
| Weights | Open | Open |

## Coding

- Llama-3.3-70B-Instruct: 30.6 (#284)
- MiMo-V2.5: 43.6 (#75)

| Benchmark | Llama-3.3-70B-Instruct | MiMo-V2.5 |
|---|---|---|
| SciCode | 26% | 43.1% |
| LMArena Coding | 1268 | 1469 |
| LMArena WebDev | — | 1438 |
| WeirdML | 14.4% | — |
| BigCodeBench Instruct | 46.9% | — |
| LiveBench Coding | 36.6% | — |
| BigCodeBench Complete | 57.5% | — |
| ALE-Bench | — | 513.95 |

## Agentic & Tool Use

- Llama-3.3-70B-Instruct: 25.6 (#100)
- MiMo-V2.5: —

| Benchmark | Llama-3.3-70B-Instruct | MiMo-V2.5 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 31.9% | — |
| BALROG | 23% | — |

## Reasoning

- Llama-3.3-70B-Instruct: 13.7 (#325)
- MiMo-V2.5: 27.8 (#98)

| Benchmark | Llama-3.3-70B-Instruct | MiMo-V2.5 |
|---|---|---|
| CritPt | 0% | 3.7% |
| LMArena Hard Prompts | 1257 | 1450 |
| SimpleBench | 19.9% | — |
| LiveBench Reasoning | 50.8% | — |
| DTBench | 59.5% | — |
| LiveBench Data Analysis | 49.5% | — |
| LMCA | 17.5% | — |
| Epoch Capabilities Index | 127.32 | — |
| ForecastBench | 58.6 | — |
| LiveBench | 50.2% | — |

## Math

- Llama-3.3-70B-Instruct: 14.3 (#292)
- MiMo-V2.5: 35.4 (#145)

| Benchmark | Llama-3.3-70B-Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Math | 1268 | 1436 |
| OTIS Mock AIME 2024-2025 | 5.1% | — |
| ProofBench | — | 16% |
| LiveBench Math | 42.2% | — |
| MATH Level 5 | 41.6% | — |

## Knowledge

- Llama-3.3-70B-Instruct: 30.5 (#220)
- MiMo-V2.5: 40.2 (#109)

| Benchmark | Llama-3.3-70B-Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1225 | 1459 |
| GPQA Diamond | 47.4% | — |
| Confabulations | 22.8% | — |
| Vectara Hallucination Rate | 4.1% | — |
| MMLU | 86.3% | — |

## Multimodal

- Llama-3.3-70B-Instruct: —
- MiMo-V2.5: 39.0 (#53)

| Benchmark | Llama-3.3-70B-Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | — | 1245 |

## Multilingual

- Llama-3.3-70B-Instruct: 40.1 (#215)
- MiMo-V2.5: 52.0 (#96)

| Benchmark | Llama-3.3-70B-Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1236 | 1404 |
| LMArena Chinese | 1217 | 1467 |
| LMArena French | 1280 | 1447 |
| LMArena German | 1251 | 1421 |
| LMArena Japanese | 1149 | 1304 |
| LMArena Korean | 1142 | 1363 |
| LMArena Russian | 1252 | 1395 |
| LMArena Spanish | 1269 | 1412 |

## Instruction Following

- Llama-3.3-70B-Instruct: 71.3 (#152)
- MiMo-V2.5: 75.7 (#55)

| Benchmark | Llama-3.3-70B-Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1242 | 1433 |
| LiveBench Instruction Following | 82.7% | — |

## Long Context

- Llama-3.3-70B-Instruct: 26.4 (#290)
- MiMo-V2.5: 44.1 (#69)

| Benchmark | Llama-3.3-70B-Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1256 | 1444 |
| Fiction.LiveBench | 33.3% | — |

## Writing & Preference

- Llama-3.3-70B-Instruct: 47.8 (#203)
- MiMo-V2.5: 61.8 (#82)

| Benchmark | Llama-3.3-70B-Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1274 | 1427 |
| LMArena Creative Writing | 1250 | 1392 |
| LMArena Multi-Turn | 1279 | 1445 |
| LiveBench Language | 39.2% | — |

## FAQ

### Is Llama-3.3-70B-Instruct better than MiMo-V2.5?

MiMo-V2.5 is the stronger model overall, scoring 43.0 to 30.3 on the Noometry Index.

### Which is cheaper, Llama-3.3-70B-Instruct or MiMo-V2.5?

Llama-3.3-70B-Instruct is cheaper. It lists at $0.10 per million input tokens and $0.32 per million output tokens; MiMo-V2.5 lists at $0.14 and $0.28.

### Is Llama-3.3-70B-Instruct or MiMo-V2.5 better for coding?

MiMo-V2.5 scores higher on coding benchmarks: 43.6 versus 30.6 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.5 does, with 1.05M tokens against 128K.

### How many benchmarks do Llama-3.3-70B-Instruct and MiMo-V2.5 share?

19 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and MiMo-V2.5 has 23.