Model comparison
DeepSeek-R1 vs Mistral Small
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 33.4 on the Noometry Index. Mistral Small costs 3.5× less per token, which makes it the better buy when DeepSeek-R1's lead doesn't matter for your workload.
Last verified . 32 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 32 benchmarks with published results for both. DeepSeek-R1 scores higher in 8 categories and Mistral Small in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-R1 leads 43.8 to 16.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 66.4% for DeepSeek-R1 and 5.8% for Mistral Small.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.50 / $2.15 for DeepSeek-R1.
- Mistral Small accepts more context: 262K tokens versus 164K.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-R1 | Mistral Small | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 42.3 | 33.4 |
| Released | 2025-01-20 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 164K | 262K |
| Max output | 64K | 256K |
| Input $ / M tokens | $0.50 | $0.15 |
| Output $ / M tokens | $2.15 | $0.60 |
| Results tracked | 52 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1 leads
DeepSeek-R1: 46.3 (#68), Mistral Small: 34.0 (#247)
| Benchmark | DeepSeek-R1 | Mistral Small |
|---|---|---|
| SciCode | 35.7% | 26.5% |
| LiveBench Coding | 66.7% | 36.2% |
| LMArena Coding | 1427 | 1362 |
| ALE-Bench | 804.12 | 497.62 |
| Aider Polyglot | 71.4% | — |
| WeirdML | 41.6% | — |
| BigCodeBench Instruct | — | 36.1% |
| BigCodeBench Complete | — | 46.6% |
| AlgoTune | 1.7 | — |
Agentic & Tool Use DeepSeek-R1 leads
DeepSeek-R1: 30.7 (#75), Mistral Small: 28.1 (#93)
| Benchmark | DeepSeek-R1 | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |
Reasoning Mistral Small leads
DeepSeek-R1: 18.6 (#278), Mistral Small: 19.8 (#250)
| Benchmark | DeepSeek-R1 | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 69.4% | 37.8% |
| CritPt | 1.1% | 0% |
| LiveBench Reasoning | 83.2% | 44.8% |
| LMArena Hard Prompts | 1416 | 1335 |
| LiveBench Data Analysis | 69.8% | 53.7% |
| LiveBench | 71.6% | 44% |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 40.8% | — |
| ARC-AGI-1 | 21.2% | — |
| DTBench | — | 70.9% |
| LMCA | — | 20.6% |
| Epoch Capabilities Index | 141.29 | — |
| ForecastBench | 60 | — |
Math DeepSeek-R1 leads
DeepSeek-R1: 43.8 (#79), Mistral Small: 16.4 (#293)
| Benchmark | DeepSeek-R1 | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.4% | 5.8% |
| LiveBench Math | 80.7% | 39.9% |
| LMArena Math | 1400 | 1341 |
| MATH Level 5 | 96.6% | 46.8% |
| Omni-MATH | 42.4% | — |
Knowledge DeepSeek-R1 leads
DeepSeek-R1: 44.5 (#87), Mistral Small: 31.0 (#222)
| Benchmark | DeepSeek-R1 | Mistral Small |
|---|---|---|
| GPQA Diamond | 76.3% | 47.5% |
| Vectara Hallucination Rate | 11.3% | 5.1% |
| LMArena Expert | 1394 | 1291 |
| MMLU-Pro | 79.3% | — |
| Confabulations | 12.7% | — |
| GPQA (HELM) | 66.6% | — |
| MMLU | — | 68.7% |
Multimodal Not comparable
DeepSeek-R1: —, Mistral Small: 33.5 (#96)
| Benchmark | DeepSeek-R1 | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual DeepSeek-R1 leads
DeepSeek-R1: 52.4 (#85), Mistral Small: 45.5 (#169)
| Benchmark | DeepSeek-R1 | Mistral Small |
|---|---|---|
| LMArena Non-English | 1412 | 1315 |
| LMArena Chinese | 1442 | 1340 |
| LMArena French | 1417 | 1337 |
| LMArena German | 1404 | 1340 |
| LMArena Japanese | 1391 | 1275 |
| LMArena Korean | 1360 | 1259 |
| LMArena Russian | 1423 | 1324 |
| LMArena Spanish | 1411 | 1346 |
Instruction Following DeepSeek-R1 leads
DeepSeek-R1: 72.0 (#143), Mistral Small: 66.4 (#209)
| Benchmark | DeepSeek-R1 | Mistral Small |
|---|---|---|
| LiveBench Instruction Following | 80.5% | 63.7% |
| LMArena Instruction Following | 1382 | 1310 |
| IFEval | 78.4% | — |
Long Context DeepSeek-R1 leads
DeepSeek-R1: 45.4 (#36), Mistral Small: 40.4 (#156)
| Benchmark | DeepSeek-R1 | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1391 | 1327 |
| Fiction.LiveBench | 75% | — |
Writing & Preference DeepSeek-R1 leads
DeepSeek-R1: 61.4 (#88), Mistral Small: 52.5 (#171)
| Benchmark | DeepSeek-R1 | Mistral Small |
|---|---|---|
| LMArena Text | 1428 | 1338 |
| LMArena Creative Writing | 1405 | 1305 |
| LMArena Multi-Turn | 1405 | 1344 |
| LiveBench Language | 48.5% | 30.5% |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1500 | — |
| WildBench | 82.8% | — |
Frequently asked questions
Is DeepSeek-R1 better than Mistral Small?
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 33.4 on the Noometry Index. Mistral Small costs 3.5× 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?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; DeepSeek-R1 lists at $0.50 and $2.15.
Is DeepSeek-R1 or Mistral Small better for coding?
DeepSeek-R1 scores higher on coding benchmarks: 46.3 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-R1 and Mistral Small share?
32 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Mistral Small has 39.