Model comparison
DBRX vs DeepSeek-V3.1-Terminus
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 29.4 on the Noometry Index.
Last verified . 10 shared benchmarks.
Databricks
DeepSeekSummary
- They share 10 benchmarks with published results for both. DBRX scores higher in 0 categories and DeepSeek-V3.1-Terminus in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.0 to 33.6.
Side by side
| DBRX | DeepSeek-V3.1-Terminus | |
|---|---|---|
| Provider | Databricks | DeepSeek |
| Noometry Index | 29.4 | 43.1 |
| Released | 2024-03-27 | 2025-09-22 |
| Weights | Open | Open |
| Context window | — | 164K |
| Max output | — | 147K |
| Input $ / M tokens | — | $0.27 |
| Output $ / M tokens | — | $1 |
| Results tracked | 21 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DBRX: 32.9 (#266), DeepSeek-V3.1-Terminus: 42.0 (#113)
| Benchmark | DBRX | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Coding | 1132 | 1426 |
| SciCode | — | 40.6% |
| ALE-Bench | — | 745.17 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning DeepSeek-V3.1-Terminus leads
DBRX: 21.4 (#222), DeepSeek-V3.1-Terminus: 26.4 (#133)
| Benchmark | DBRX | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1426 |
| Kagi LLM Benchmark | — | 57.4% |
| CritPt | — | 1.7% |
| DTBench | — | 81.3% |
| LMCA | — | 28.6% |
Math DeepSeek-V3.1-Terminus leads
DBRX: 24.3 (#269), DeepSeek-V3.1-Terminus: 38.5 (#137)
| Benchmark | DBRX | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Math | 1145 | 1402 |
| MATH Level 5 | 11.7% | — |
Knowledge Not comparable
DBRX: 14.9 (#294), DeepSeek-V3.1-Terminus: —
| Benchmark | DBRX | DeepSeek-V3.1-Terminus |
|---|---|---|
| GPQA Diamond | 32.9% | — |
| LMArena Expert | 1076 | — |
Multilingual DeepSeek-V3.1-Terminus leads
DBRX: 29.3 (#268), DeepSeek-V3.1-Terminus: 52.1 (#92)
| Benchmark | DBRX | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Non-English | 1071 | 1407 |
| LMArena Russian | 1078 | 1436 |
| LMArena Chinese | 1068 | — |
| LMArena French | 1096 | — |
| LMArena German | 1057 | — |
| LMArena Japanese | 990 | — |
| LMArena Korean | 993 | — |
| LMArena Spanish | 1064 | — |
Instruction Following DeepSeek-V3.1-Terminus leads
DBRX: 57.5 (#270), DeepSeek-V3.1-Terminus: 74.0 (#106)
| Benchmark | DBRX | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Instruction Following | 1112 | 1404 |
Long Context DeepSeek-V3.1-Terminus leads
DBRX: 33.7 (#258), DeepSeek-V3.1-Terminus: 43.4 (#97)
| Benchmark | DBRX | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Longer Query | 1112 | 1421 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DBRX: 33.6 (#275), DeepSeek-V3.1-Terminus: 61.0 (#92)
| Benchmark | DBRX | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Text | 1119 | 1419 |
| LMArena Creative Writing | 1104 | 1403 |
| LMArena Multi-Turn | 1111 | 1411 |
Frequently asked questions
Is DBRX better than DeepSeek-V3.1-Terminus?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 29.4 on the Noometry Index.
Is DBRX or DeepSeek-V3.1-Terminus better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 32.9 in the Noometry coding category.
How many benchmarks do DBRX and DeepSeek-V3.1-Terminus share?
10 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and DeepSeek-V3.1-Terminus has 16.