Model comparison
DeepSeek Coder 33B vs Mistral Small
Mistral Small has enough public results to be ranked (#243); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Last verified . 3 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 3 benchmarks with published results for both. DeepSeek Coder 33B scores higher in 1 category and Mistral Small in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek Coder 33B leads 38.0 to 34.0.
- The biggest single-benchmark swing is BigCodeBench Instruct: 42% for DeepSeek Coder 33B and 36.1% for Mistral Small.
Side by side
| DeepSeek Coder 33B | Mistral Small | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 38.9 | 33.4 |
| Released | 2023-11-02 | 2024-02-26 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.60 |
| Results tracked | 9 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek Coder 33B leads
DeepSeek Coder 33B: 38.0 (#184), Mistral Small: 34.0 (#247)
| Benchmark | DeepSeek Coder 33B | Mistral Small |
|---|---|---|
| BigCodeBench Instruct | 42% | 36.1% |
| BigCodeBench Complete | 51.1% | 46.6% |
| SciCode | — | 26.5% |
| LiveBench Coding | — | 36.2% |
| LMArena Coding | — | 1362 |
| ALE-Bench | — | 497.62 |
| HumanEval+ | 75% | — |
| MBPP+ | 70.1% | — |
Agentic & Tool Use Not comparable
DeepSeek Coder 33B: —, Mistral Small: 28.1 (#93)
| Benchmark | DeepSeek Coder 33B | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
Reasoning Not comparable
DeepSeek Coder 33B: —, Mistral Small: 19.8 (#250)
| Benchmark | DeepSeek Coder 33B | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | — | 37.8% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 44.8% |
| LMArena Hard Prompts | — | 1335 |
| DTBench | — | 70.9% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| Epoch Capabilities Index | 96.32 | — |
| LiveBench | — | 44% |
| WinoGrande | 62% | — |
Math Not comparable
DeepSeek Coder 33B: —, Mistral Small: 16.4 (#293)
| Benchmark | DeepSeek Coder 33B | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| LiveBench Math | — | 39.9% |
| LMArena Math | — | 1341 |
| MATH Level 5 | — | 46.8% |
| GSM8K | 35.4% | — |
Knowledge Not comparable
DeepSeek Coder 33B: —, Mistral Small: 31.0 (#222)
| Benchmark | DeepSeek Coder 33B | Mistral Small |
|---|---|---|
| MMLU | 39.4% | 68.7% |
| GPQA Diamond | — | 47.5% |
| Vectara Hallucination Rate | — | 5.1% |
| LMArena Expert | — | 1291 |
| ARC (AI2) Challenge | 42.2% | — |
Multimodal Not comparable
DeepSeek Coder 33B: —, Mistral Small: 33.5 (#96)
| Benchmark | DeepSeek Coder 33B | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual Not comparable
DeepSeek Coder 33B: —, Mistral Small: 45.5 (#169)
| Benchmark | DeepSeek Coder 33B | Mistral Small |
|---|---|---|
| LMArena Non-English | — | 1315 |
| LMArena Chinese | — | 1340 |
| LMArena French | — | 1337 |
| LMArena German | — | 1340 |
| LMArena Japanese | — | 1275 |
| LMArena Korean | — | 1259 |
| LMArena Russian | — | 1324 |
| LMArena Spanish | — | 1346 |
Instruction Following Not comparable
DeepSeek Coder 33B: —, Mistral Small: 66.4 (#209)
| Benchmark | DeepSeek Coder 33B | Mistral Small |
|---|---|---|
| LiveBench Instruction Following | — | 63.7% |
| LMArena Instruction Following | — | 1310 |
Long Context Not comparable
DeepSeek Coder 33B: —, Mistral Small: 40.4 (#156)
| Benchmark | DeepSeek Coder 33B | Mistral Small |
|---|---|---|
| LMArena Longer Query | — | 1327 |
Writing & Preference Not comparable
DeepSeek Coder 33B: —, Mistral Small: 52.5 (#171)
| Benchmark | DeepSeek Coder 33B | Mistral Small |
|---|---|---|
| LMArena Text | — | 1338 |
| LMArena Creative Writing | — | 1305 |
| LMArena Multi-Turn | — | 1344 |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is DeepSeek Coder 33B better than Mistral Small?
Mistral Small has enough public results to be ranked (#243); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 33B or Mistral Small better for coding?
DeepSeek Coder 33B scores higher on coding benchmarks: 38.0 versus 34.0 in the Noometry coding category.
How many benchmarks do DeepSeek Coder 33B and Mistral Small share?
3 benchmarks have published results for both models. DeepSeek Coder 33B has 9 scored results on Noometry and Mistral Small has 39.