Model comparison
DeepSeek-V3.1 vs Mistral Small
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 33.4 on the Noometry Index. Mistral Small costs 1.6× less per token, which makes it the better buy when DeepSeek-V3.1's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 21 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 7 categories and Mistral Small in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V3.1 leads 38.9 to 16.4.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 53.2% for DeepSeek-V3.1 and 37.8% for Mistral Small.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.25 / $0.95 for DeepSeek-V3.1.
- Mistral Small accepts more context: 262K tokens versus 164K.
Side by side
| DeepSeek-V3.1 | Mistral Small | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 42.8 | 33.4 |
| Released | 2025-08-21 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 164K | 262K |
| Max output | 8K | 256K |
| Input $ / M tokens | $0.25 | $0.15 |
| Output $ / M tokens | $0.95 | $0.60 |
| Results tracked | 27 | 39 |
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: 34.0 (#247)
| Benchmark | DeepSeek-V3.1 | Mistral Small |
|---|---|---|
| LMArena Coding | 1417 | 1362 |
| SciCode | — | 26.5% |
| WeirdML | 38.4% | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
| ALE-Bench | — | 497.62 |
Agentic & Tool Use Not comparable
DeepSeek-V3.1: —, Mistral Small: 28.1 (#93)
| Benchmark | DeepSeek-V3.1 | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.9 (#110), Mistral Small: 19.8 (#250)
| Benchmark | DeepSeek-V3.1 | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 53.2% | 37.8% |
| LMArena Hard Prompts | 1417 | 1335 |
| DTBench | 82.7% | 70.9% |
| LMCA | 24.3% | 20.6% |
| SimpleBench | 40% | — |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 44.8% |
| LiveBench Data Analysis | — | 53.7% |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
| LiveBench | — | 44% |
Math DeepSeek-V3.1 leads
DeepSeek-V3.1: 38.9 (#122), Mistral Small: 16.4 (#293)
| Benchmark | DeepSeek-V3.1 | Mistral Small |
|---|---|---|
| LMArena Math | 1420 | 1341 |
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.7 (#90), Mistral Small: 31.0 (#222)
| Benchmark | DeepSeek-V3.1 | Mistral Small |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | 5.1% |
| LMArena Expert | 1405 | 1291 |
| GPQA Diamond | — | 47.5% |
| MMLU | — | 68.7% |
Multimodal Not comparable
DeepSeek-V3.1: —, Mistral Small: 33.5 (#96)
| Benchmark | DeepSeek-V3.1 | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.6 (#106), Mistral Small: 45.5 (#169)
| Benchmark | DeepSeek-V3.1 | Mistral Small |
|---|---|---|
| LMArena Non-English | 1400 | 1315 |
| LMArena Chinese | 1469 | 1340 |
| LMArena French | 1447 | 1337 |
| LMArena German | 1411 | 1340 |
| LMArena Japanese | 1378 | 1275 |
| LMArena Korean | 1337 | 1259 |
| LMArena Russian | 1405 | 1324 |
| LMArena Spanish | 1431 | 1346 |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 73.9 (#110), Mistral Small: 66.4 (#209)
| Benchmark | DeepSeek-V3.1 | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1400 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
Long Context Mistral Small leads
DeepSeek-V3.1: 36.3 (#232), Mistral Small: 40.4 (#156)
| Benchmark | DeepSeek-V3.1 | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1422 | 1327 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.3 (#98), Mistral Small: 52.5 (#171)
| Benchmark | DeepSeek-V3.1 | Mistral Small |
|---|---|---|
| LMArena Text | 1420 | 1338 |
| LMArena Creative Writing | 1401 | 1305 |
| LMArena Multi-Turn | 1408 | 1344 |
| EQ-Bench Creative Writing | 1436 | — |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is DeepSeek-V3.1 better than Mistral Small?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 33.4 on the Noometry Index. Mistral Small costs 1.6× 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?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; DeepSeek-V3.1 lists at $0.25 and $0.95.
Is DeepSeek-V3.1 or Mistral Small better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
Mistral Small does, with 262K tokens against 164K.
How many benchmarks do DeepSeek-V3.1 and Mistral Small share?
21 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Mistral Small has 39.