# DeepSeek-V2.5 (Sep 2024) vs Mistral Small 3

> DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.0 to 30.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v2-5-vs-mistral-small-3
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 7 categories and Mistral Small 3 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V2.5 (Sep 2024) leads 33.3 to 15.3.

## Snapshot

| | DeepSeek-V2.5 (Sep 2024) | Mistral Small 3 |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 37.0 | 30.9 |
| Rank | 197 | 268 |
| Context | — | 33K |
| Input $/M | — | $0.05 |
| Output $/M | — | $0.08 |
| Weights | Open | Open |

## Coding

- DeepSeek-V2.5 (Sep 2024): 31.3 (#274)
- Mistral Small 3: 36.0 (#203)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Small 3 |
|---|---|---|
| BigCodeBench Instruct | 48.6% | 45.3% |
| LMArena Coding | 1310 | 1246 |
| BigCodeBench Complete | 53.2% | 50.4% |
| Aider Polyglot | 17.8% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |

## Reasoning

- DeepSeek-V2.5 (Sep 2024): 24.5 (#145)
- Mistral Small 3: 18.2 (#269)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1233 |
| Chess Puzzles | — | 0% |
| Epoch Capabilities Index | — | 127.06 |

## Math

- DeepSeek-V2.5 (Sep 2024): 33.3 (#177)
- Mistral Small 3: 15.3 (#290)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Small 3 |
|---|---|---|
| LMArena Math | 1289 | 1240 |
| OTIS Mock AIME 2024-2025 | — | 6.7% |

## Knowledge

- DeepSeek-V2.5 (Sep 2024): 34.2 (#190)
- Mistral Small 3: 25.0 (#258)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Small 3 |
|---|---|---|
| LMArena Expert | 1266 | 1202 |
| GPQA Diamond | — | 47.3% |
| Confabulations | — | 25.2% |

## Multilingual

- DeepSeek-V2.5 (Sep 2024): 42.7 (#188)
- Mistral Small 3: 37.5 (#231)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1273 | 1198 |
| LMArena Chinese | 1317 | 1204 |
| LMArena French | 1288 | 1202 |
| LMArena German | 1258 | 1211 |
| LMArena Japanese | 1228 | 1111 |
| LMArena Korean | 1209 | 1188 |
| LMArena Russian | 1289 | 1216 |
| LMArena Spanish | 1248 | — |

## Instruction Following

- DeepSeek-V2.5 (Sep 2024): 67.7 (#189)
- Mistral Small 3: 63.9 (#224)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1214 |

## Long Context

- DeepSeek-V2.5 (Sep 2024): 39.5 (#169)
- Mistral Small 3: 37.8 (#206)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1301 | 1246 |

## Writing & Preference

- DeepSeek-V2.5 (Sep 2024): 50.0 (#182)
- Mistral Small 3: 32.4 (#275)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1294 | 1234 |
| LMArena Creative Writing | 1285 | 1195 |
| LMArena Multi-Turn | 1297 | 1217 |
| EQ-Bench Creative Writing | — | 707 |

## FAQ

### Is DeepSeek-V2.5 (Sep 2024) better than Mistral Small 3?

DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.0 to 30.9 on the Noometry Index.

### Is DeepSeek-V2.5 (Sep 2024) or Mistral Small 3 better for coding?

Mistral Small 3 scores higher on coding benchmarks: 36.0 versus 31.3 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Mistral Small 3 share?

18 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Mistral Small 3 has 24.