# DeepSeek-R1 vs Mistral Small 3

> DeepSeek-R1 is the stronger model overall, scoring 42.3 to 31.2 on the Noometry Index. Mistral Small 3 costs 16× less per token, which makes it the better buy when DeepSeek-R1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/deepseek-r1-vs-mistral-small-3
- Last updated: 2026-10-11
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. DeepSeek-R1 scores higher in 7 categories and Mistral Small 3 in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-R1 leads 61.4 to 32.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 66.4% for DeepSeek-R1 and 6.7% for Mistral Small 3.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.50 / $2.15 for DeepSeek-R1.
- DeepSeek-R1 accepts more context: 164K tokens versus 33K.
- Mistral Small 3 has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-R1 | Mistral Small 3 |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 42.3 | 31.2 |
| Rank | 115 | 278 |
| Context | 164K | 33K |
| Input $/M | $0.50 | $0.05 |
| Output $/M | $2.15 | $0.08 |
| Weights | Proprietary | Open |

## Coding

- DeepSeek-R1: 46.3 (#68)
- Mistral Small 3: 36.5 (#207)

| Benchmark | DeepSeek-R1 | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1427 | 1246 |
| Aider Polyglot | 71.4% | — |
| SciCode | 35.7% | — |
| WeirdML | 41.6% | — |
| BigCodeBench Instruct | — | 45.3% |
| LiveBench Coding | 66.7% | — |
| BigCodeBench Complete | — | 50.4% |
| ALE-Bench | 804.12 | — |
| AlgoTune | 1.7 | — |

## Agentic & Tool Use

- DeepSeek-R1: 30.7 (#75)
- Mistral Small 3: —

| Benchmark | DeepSeek-R1 | Mistral Small 3 |
|---|---|---|
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |

## Reasoning

- DeepSeek-R1: 18.6 (#278)
- Mistral Small 3: 18.9 (#273)

| Benchmark | DeepSeek-R1 | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1416 | 1233 |
| Epoch Capabilities Index | 141.29 | 127.07 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 40.8% | — |
| Kagi LLM Benchmark | 69.4% | — |
| ARC-AGI-1 | 21.2% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 83.2% | — |
| LiveBench Data Analysis | 69.8% | — |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |

## Math

- DeepSeek-R1: 43.8 (#79)
- Mistral Small 3: 16.3 (#295)

| Benchmark | DeepSeek-R1 | Mistral Small 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.4% | 6.7% |
| LMArena Math | 1400 | 1240 |
| Omni-MATH | 42.4% | — |
| LiveBench Math | 80.7% | — |
| MATH Level 5 | 96.6% | — |

## Knowledge

- DeepSeek-R1: 44.5 (#87)
- Mistral Small 3: 25.1 (#263)

| Benchmark | DeepSeek-R1 | Mistral Small 3 |
|---|---|---|
| GPQA Diamond | 76.3% | 47.3% |
| Confabulations | 12.7% | 25.2% |
| LMArena Expert | 1394 | 1202 |
| MMLU-Pro | 79.3% | — |
| Vectara Hallucination Rate | 11.3% | — |
| GPQA (HELM) | 66.6% | — |

## Multilingual

- DeepSeek-R1: 52.4 (#85)
- Mistral Small 3: 37.3 (#236)

| Benchmark | DeepSeek-R1 | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1412 | 1198 |
| LMArena Chinese | 1442 | 1204 |
| LMArena French | 1417 | 1203 |
| LMArena German | 1404 | 1211 |
| LMArena Japanese | 1391 | 1111 |
| LMArena Korean | 1360 | 1188 |
| LMArena Russian | 1423 | 1216 |
| LMArena Spanish | 1411 | — |

## Instruction Following

- DeepSeek-R1: 72.0 (#143)
- Mistral Small 3: 63.7 (#229)

| Benchmark | DeepSeek-R1 | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1382 | 1214 |
| LiveBench Instruction Following | 80.5% | — |
| IFEval | 78.4% | — |

## Long Context

- DeepSeek-R1: 45.4 (#36)
- Mistral Small 3: 37.8 (#211)

| Benchmark | DeepSeek-R1 | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1391 | 1246 |
| Fiction.LiveBench | 75% | — |

## Writing & Preference

- DeepSeek-R1: 61.4 (#88)
- Mistral Small 3: 32.2 (#280)

| Benchmark | DeepSeek-R1 | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1428 | 1234 |
| LMArena Creative Writing | 1405 | 1195 |
| EQ-Bench Creative Writing | 1500 | 707 |
| LMArena Multi-Turn | 1405 | 1217 |
| Short-Story Creative Writing | 83% | — |
| WildBench | 82.8% | — |
| LiveBench Language | 48.5% | — |

## FAQ

### Is DeepSeek-R1 better than Mistral Small 3?

DeepSeek-R1 is the stronger model overall, scoring 42.3 to 31.2 on the Noometry Index. Mistral Small 3 costs 16× less per token, which makes it the better buy when DeepSeek-R1's lead doesn't matter for your workload.

### Which is cheaper, DeepSeek-R1 or Mistral Small 3?

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; DeepSeek-R1 lists at $0.50 and $2.15.

### Is DeepSeek-R1 or Mistral Small 3 better for coding?

DeepSeek-R1 scores higher on coding benchmarks: 46.3 versus 36.5 in the Noometry coding category.

### Which has the bigger context window?

DeepSeek-R1 does, with 164K tokens against 33K.

### How many benchmarks do DeepSeek-R1 and Mistral Small 3 share?

21 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Mistral Small 3 has 24.