# Mistral Medium 3.5 vs Nova 2 Lite

> Mistral Medium 3.5 and Nova 2 Lite score almost the same on the Noometry Index (40.2 vs 39.7), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/mistral-medium-3-5-vs-nova-2-lite
- Last updated: 2026-10-12
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Mistral Medium 3.5 scores higher in 5 categories and Nova 2 Lite in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Nova 2 Lite leads 27.5 to 17.3.
- Nova 2 Lite is cheaper at $0.30 / $2.50 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
- Nova 2 Lite accepts more context: 1M tokens versus 262K.
- Mistral Medium 3.5 has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral Medium 3.5 | Nova 2 Lite |
|---|---|---|
| Provider | Mistral AI | Amazon |
| Noometry Index | 40.2 | 39.7 |
| Rank | 152 | 161 |
| Context | 262K | 1M |
| Input $/M | $1.50 | $0.30 |
| Output $/M | $7.50 | $2.50 |
| Weights | Open | Proprietary |

## Coding

- Mistral Medium 3.5: 36.0 (#213)
- Nova 2 Lite: 40.7 (#134)

| Benchmark | Mistral Medium 3.5 | Nova 2 Lite |
|---|---|---|
| LMArena Coding | 1461 | 1385 |
| LMArena WebDev | 1264 | — |

## Agentic & Tool Use

- Mistral Medium 3.5: —
- Nova 2 Lite: 24.1 (#121)

| Benchmark | Mistral Medium 3.5 | Nova 2 Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.1% |

## Reasoning

- Mistral Medium 3.5: 17.3 (#295)
- Nova 2 Lite: 27.5 (#118)

| Benchmark | Mistral Medium 3.5 | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | 1436 | 1364 |
| Kagi LLM Benchmark | 41.4% | — |
| NYT Connections (extended) | 12.9% | — |
| Epoch Capabilities Index | 141.35 | — |

## Math

- Mistral Medium 3.5: 39.1 (#113)
- Nova 2 Lite: 37.5 (#156)

| Benchmark | Mistral Medium 3.5 | Nova 2 Lite |
|---|---|---|
| LMArena Math | 1431 | 1359 |

## Knowledge

- Mistral Medium 3.5: 40.0 (#126)
- Nova 2 Lite: 43.0 (#94)

| Benchmark | Mistral Medium 3.5 | Nova 2 Lite |
|---|---|---|
| LMArena Expert | 1432 | 1358 |
| Vectara Hallucination Rate | — | 5.1% |

## Multimodal

- Mistral Medium 3.5: 38.3 (#65)
- Nova 2 Lite: —

| Benchmark | Mistral Medium 3.5 | Nova 2 Lite |
|---|---|---|
| LMArena Vision | 1223 | — |

## Multilingual

- Mistral Medium 3.5: 51.9 (#100)
- Nova 2 Lite: 47.1 (#153)

| Benchmark | Mistral Medium 3.5 | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | 1404 | 1337 |
| LMArena Chinese | 1442 | 1364 |
| LMArena French | 1448 | 1381 |
| LMArena German | 1451 | 1343 |
| LMArena Korean | 1385 | 1284 |
| LMArena Russian | 1395 | 1343 |
| LMArena Spanish | 1409 | 1373 |
| LMArena Japanese | — | 1271 |

## Instruction Following

- Mistral Medium 3.5: 74.6 (#90)
- Nova 2 Lite: 70.5 (#161)

| Benchmark | Mistral Medium 3.5 | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | 1415 | 1335 |

## Long Context

- Mistral Medium 3.5: 43.2 (#103)
- Nova 2 Lite: 40.6 (#150)

| Benchmark | Mistral Medium 3.5 | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | 1415 | 1335 |

## Writing & Preference

- Mistral Medium 3.5: 58.5 (#117)
- Nova 2 Lite: 53.9 (#154)

| Benchmark | Mistral Medium 3.5 | Nova 2 Lite |
|---|---|---|
| LMArena Text | 1421 | 1362 |
| LMArena Creative Writing | 1374 | 1291 |
| LMArena Multi-Turn | 1423 | 1338 |
| EQ-Bench 4 | 993 | — |

## FAQ

### Is Mistral Medium 3.5 better than Nova 2 Lite?

Mistral Medium 3.5 and Nova 2 Lite score almost the same on the Noometry Index (40.2 vs 39.7), so choose on price, context window or the category you care about most.

### Which is cheaper, Mistral Medium 3.5 or Nova 2 Lite?

Nova 2 Lite is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

### Is Mistral Medium 3.5 or Nova 2 Lite better for coding?

Nova 2 Lite scores higher on coding benchmarks: 40.7 versus 36.0 in the Noometry coding category.

### Which has the bigger context window?

Nova 2 Lite does, with 1M tokens against 262K.

### How many benchmarks do Mistral Medium 3.5 and Nova 2 Lite share?

16 benchmarks have published results for both models. Mistral Medium 3.5 has 22 scored results on Noometry and Nova 2 Lite has 19.