Model comparison
DeepSeek-V3.1 vs Mistral Small 3
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 31.2 on the Noometry Index. Mistral Small 3 costs 7.4× less per token, which makes it the better buy when DeepSeek-V3.1's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 18 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 7 categories and Mistral Small 3 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.3 to 32.2.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.25 / $0.95 for DeepSeek-V3.1.
- DeepSeek-V3.1 accepts more context: 164K tokens versus 33K.
Side by side
| DeepSeek-V3.1 | Mistral Small 3 | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 42.8 | 31.2 |
| Released | 2025-08-21 | 2025-01-30 |
| Weights | Open | Open |
| Context window | 164K | 33K |
| Max output | 8K | 16K |
| Input $ / M tokens | $0.25 | $0.05 |
| Output $ / M tokens | $0.95 | $0.08 |
| Results tracked | 27 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1 leads
DeepSeek-V3.1: 40.3 (#144), Mistral Small 3: 36.5 (#207)
| Benchmark | DeepSeek-V3.1 | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1417 | 1246 |
| WeirdML | 38.4% | — |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.9 (#110), Mistral Small 3: 18.9 (#273)
| Benchmark | DeepSeek-V3.1 | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1233 |
| Epoch Capabilities Index | 139.92 | 127.07 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| Chess Puzzles | — | 0% |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| ForecastBench | 58 | — |
Math DeepSeek-V3.1 leads
DeepSeek-V3.1: 38.9 (#122), Mistral Small 3: 16.3 (#295)
| Benchmark | DeepSeek-V3.1 | Mistral Small 3 |
|---|---|---|
| LMArena Math | 1420 | 1240 |
| OTIS Mock AIME 2024-2025 | — | 6.7% |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.7 (#90), Mistral Small 3: 25.1 (#263)
| Benchmark | DeepSeek-V3.1 | Mistral Small 3 |
|---|---|---|
| LMArena Expert | 1405 | 1202 |
| GPQA Diamond | — | 47.3% |
| Confabulations | — | 25.2% |
| Vectara Hallucination Rate | 5.5% | — |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.6 (#106), Mistral Small 3: 37.3 (#236)
| Benchmark | DeepSeek-V3.1 | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1400 | 1198 |
| LMArena Chinese | 1469 | 1204 |
| LMArena French | 1447 | 1203 |
| LMArena German | 1411 | 1211 |
| LMArena Japanese | 1378 | 1111 |
| LMArena Korean | 1337 | 1188 |
| LMArena Russian | 1405 | 1216 |
| LMArena Spanish | 1431 | — |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 73.9 (#110), Mistral Small 3: 63.7 (#229)
| Benchmark | DeepSeek-V3.1 | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1400 | 1214 |
Long Context Mistral Small 3 leads
DeepSeek-V3.1: 36.3 (#232), Mistral Small 3: 37.8 (#211)
| Benchmark | DeepSeek-V3.1 | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1422 | 1246 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.3 (#98), Mistral Small 3: 32.2 (#280)
| Benchmark | DeepSeek-V3.1 | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1420 | 1234 |
| LMArena Creative Writing | 1401 | 1195 |
| EQ-Bench Creative Writing | 1436 | 707 |
| LMArena Multi-Turn | 1408 | 1217 |
Frequently asked questions
Is DeepSeek-V3.1 better than Mistral Small 3?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 31.2 on the Noometry Index. Mistral Small 3 costs 7.4× less per token, which makes it the better buy when DeepSeek-V3.1's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.1 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-V3.1 lists at $0.25 and $0.95.
Is DeepSeek-V3.1 or Mistral Small 3 better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 36.5 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-V3.1 does, with 164K tokens against 33K.
How many benchmarks do DeepSeek-V3.1 and Mistral Small 3 share?
18 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Mistral Small 3 has 24.