Model comparison
DBRX vs Mistral Small
Mistral Small is the stronger model overall, scoring 33.4 to 29.4 on the Noometry Index.
Last verified . 19 shared benchmarks.
Databricks
Mistral AISummary
- They share 19 benchmarks with published results for both. DBRX scores higher in 2 categories and Mistral Small in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Small leads 52.5 to 33.6.
- The biggest single-benchmark swing is MATH Level 5: 11.7% for DBRX and 46.8% for Mistral Small.
Side by side
| DBRX | Mistral Small | |
|---|---|---|
| Provider | Databricks | Mistral AI |
| Noometry Index | 29.4 | 33.4 |
| Released | 2024-03-27 | 2024-02-26 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.60 |
| Results tracked | 21 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small leads
DBRX: 32.9 (#266), Mistral Small: 34.0 (#247)
| Benchmark | DBRX | Mistral Small |
|---|---|---|
| LMArena Coding | 1132 | 1362 |
| SciCode | — | 26.5% |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
| ALE-Bench | — | 497.62 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Agentic & Tool Use Not comparable
DBRX: —, Mistral Small: 28.1 (#93)
| Benchmark | DBRX | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
Reasoning DBRX leads
DBRX: 21.4 (#222), Mistral Small: 19.8 (#250)
| Benchmark | DBRX | Mistral Small |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1335 |
| Kagi LLM Benchmark | — | 37.8% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 44.8% |
| DTBench | — | 70.9% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| LiveBench | — | 44% |
Math DBRX leads
DBRX: 24.3 (#269), Mistral Small: 16.4 (#293)
| Benchmark | DBRX | Mistral Small |
|---|---|---|
| LMArena Math | 1145 | 1341 |
| MATH Level 5 | 11.7% | 46.8% |
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| LiveBench Math | — | 39.9% |
Knowledge Mistral Small leads
DBRX: 14.9 (#294), Mistral Small: 31.0 (#222)
| Benchmark | DBRX | Mistral Small |
|---|---|---|
| GPQA Diamond | 32.9% | 47.5% |
| LMArena Expert | 1076 | 1291 |
| Vectara Hallucination Rate | — | 5.1% |
| MMLU | — | 68.7% |
Multimodal Not comparable
DBRX: —, Mistral Small: 33.5 (#96)
| Benchmark | DBRX | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual Mistral Small leads
DBRX: 29.3 (#268), Mistral Small: 45.5 (#169)
| Benchmark | DBRX | Mistral Small |
|---|---|---|
| LMArena Non-English | 1071 | 1315 |
| LMArena Chinese | 1068 | 1340 |
| LMArena French | 1096 | 1337 |
| LMArena German | 1057 | 1340 |
| LMArena Japanese | 990 | 1275 |
| LMArena Korean | 993 | 1259 |
| LMArena Russian | 1078 | 1324 |
| LMArena Spanish | 1064 | 1346 |
Instruction Following Mistral Small leads
DBRX: 57.5 (#270), Mistral Small: 66.4 (#209)
| Benchmark | DBRX | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1112 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
Long Context Mistral Small leads
DBRX: 33.7 (#258), Mistral Small: 40.4 (#156)
| Benchmark | DBRX | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1112 | 1327 |
Writing & Preference Mistral Small leads
DBRX: 33.6 (#275), Mistral Small: 52.5 (#171)
| Benchmark | DBRX | Mistral Small |
|---|---|---|
| LMArena Text | 1119 | 1338 |
| LMArena Creative Writing | 1104 | 1305 |
| LMArena Multi-Turn | 1111 | 1344 |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is DBRX better than Mistral Small?
Mistral Small is the stronger model overall, scoring 33.4 to 29.4 on the Noometry Index.
Is DBRX or Mistral Small better for coding?
Mistral Small scores higher on coding benchmarks: 34.0 versus 32.9 in the Noometry coding category.
How many benchmarks do DBRX and Mistral Small share?
19 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Mistral Small has 39.