# Mistral Small vs Nova 2 Lite

> Nova 2 Lite is the stronger model overall, scoring 39.0 to 33.1 on the Noometry Index. Mistral Small costs 3.2× less per token, which makes it the better buy when Nova 2 Lite's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mistral-small-vs-nova-2-lite
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Mistral Small scores higher in 1 category and Nova 2 Lite in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Nova 2 Lite leads 34.8 to 15.4.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 37.1% for Mistral Small and 27.1% for Nova 2 Lite.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.30 / $2.50 for Nova 2 Lite.
- Nova 2 Lite accepts more context: 1M tokens versus 256K.
- Mistral Small has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral Small | Nova 2 Lite |
|---|---|---|
| Provider | Mistral AI | Amazon |
| Noometry Index | 33.1 | 39.0 |
| Rank | 238 | 161 |
| Context | 256K | 1M |
| Input $/M | $0.15 | $0.30 |
| Output $/M | $0.60 | $2.50 |
| Weights | Open | Proprietary |

## Coding

- Mistral Small: 33.5 (#242)
- Nova 2 Lite: 40.1 (#131)

| Benchmark | Mistral Small | Nova 2 Lite |
|---|---|---|
| LMArena Coding | 1363 | 1386 |
| SciCode | 26.5% | — |
| BigCodeBench Instruct | 36.1% | — |
| LiveBench Coding | 36.2% | — |
| BigCodeBench Complete | 46.6% | — |
| ALE-Bench | 497.62 | — |

## Agentic & Tool Use

- Mistral Small: 27.9 (#87)
- Nova 2 Lite: 23.9 (#114)

| Benchmark | Mistral Small | Nova 2 Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | 27.1% |

## Reasoning

- Mistral Small: 19.3 (#238)
- Nova 2 Lite: 26.4 (#120)

| Benchmark | Mistral Small | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | 1336 | 1364 |
| Kagi LLM Benchmark | 37.8% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 44.8% | — |
| DTBench | 70.9% | — |
| LiveBench Data Analysis | 53.7% | — |
| LMCA | 20.6% | — |
| LiveBench | 44% | — |

## Math

- Mistral Small: 15.4 (#287)
- Nova 2 Lite: 34.8 (#154)

| Benchmark | Mistral Small | Nova 2 Lite |
|---|---|---|
| LMArena Math | 1341 | 1359 |
| OTIS Mock AIME 2024-2025 | 5.8% | — |
| LiveBench Math | 39.9% | — |
| MATH Level 5 | 46.8% | — |

## Knowledge

- Mistral Small: 30.9 (#214)
- Nova 2 Lite: 42.5 (#88)

| Benchmark | Mistral Small | Nova 2 Lite |
|---|---|---|
| Vectara Hallucination Rate | 5.1% | 5.1% |
| LMArena Expert | 1293 | 1360 |
| GPQA Diamond | 47.5% | — |
| MMLU | 68.7% | — |

## Multimodal

- Mistral Small: 32.9 (#91)
- Nova 2 Lite: —

| Benchmark | Mistral Small | Nova 2 Lite |
|---|---|---|
| LMArena Vision | 1142 | — |

## Multilingual

- Mistral Small: 45.7 (#164)
- Nova 2 Lite: 47.3 (#148)

| Benchmark | Mistral Small | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | 1315 | 1337 |
| LMArena Chinese | 1342 | 1364 |
| LMArena French | 1337 | 1381 |
| LMArena German | 1341 | 1343 |
| LMArena Japanese | 1275 | 1273 |
| LMArena Korean | 1260 | 1284 |
| LMArena Russian | 1324 | 1343 |
| LMArena Spanish | 1346 | 1372 |

## Instruction Following

- Mistral Small: 66.6 (#204)
- Nova 2 Lite: 70.7 (#156)

| Benchmark | Mistral Small | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | 1310 | 1335 |
| LiveBench Instruction Following | 63.7% | — |

## Long Context

- Mistral Small: 40.4 (#151)
- Nova 2 Lite: 40.6 (#145)

| Benchmark | Mistral Small | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | 1327 | 1335 |

## Writing & Preference

- Mistral Small: 52.6 (#165)
- Nova 2 Lite: 54.1 (#150)

| Benchmark | Mistral Small | Nova 2 Lite |
|---|---|---|
| LMArena Text | 1338 | 1362 |
| LMArena Creative Writing | 1304 | 1291 |
| LMArena Multi-Turn | 1344 | 1338 |
| LiveBench Language | 30.5% | — |

## FAQ

### Is Mistral Small better than Nova 2 Lite?

Nova 2 Lite is the stronger model overall, scoring 39.0 to 33.1 on the Noometry Index. Mistral Small costs 3.2× less per token, which makes it the better buy when Nova 2 Lite's lead doesn't matter for your workload.

### Which is cheaper, Mistral Small or Nova 2 Lite?

Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Nova 2 Lite lists at $0.30 and $2.50.

### Is Mistral Small or Nova 2 Lite better for coding?

Nova 2 Lite scores higher on coding benchmarks: 40.1 versus 33.5 in the Noometry coding category.

### Which has the bigger context window?

Nova 2 Lite does, with 1M tokens against 256K.

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

19 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Nova 2 Lite has 19.