Model comparison
DBRX vs GLM-4.5-Air
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 29.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
DatabricksSummary
- They share 17 benchmarks with published results for both. DBRX scores higher in 0 categories and GLM-4.5-Air in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.5-Air leads 55.9 to 33.6.
Side by side
| DBRX | GLM-4.5-Air | |
|---|---|---|
| Provider | Databricks | Z.ai (Zhipu) |
| Noometry Index | 29.4 | 38.9 |
| Released | 2024-03-27 | 2025-07-20 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 98K |
| Input $ / M tokens | — | $0.20 |
| Output $ / M tokens | — | $1.10 |
| Results tracked | 21 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DBRX: 32.9 (#266), GLM-4.5-Air: 33.3 (#259)
| Benchmark | DBRX | GLM-4.5-Air |
|---|---|---|
| LMArena Coding | 1132 | 1397 |
| GSO | — | 2.9% |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning GLM-4.5-Air leads
DBRX: 21.4 (#222), GLM-4.5-Air: 24.1 (#166)
| Benchmark | DBRX | GLM-4.5-Air |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1379 |
| Kagi LLM Benchmark | — | 43% |
| ForecastBench | — | 59.2 |
Math GLM-4.5-Air leads
DBRX: 24.3 (#269), GLM-4.5-Air: 36.2 (#170)
| Benchmark | DBRX | GLM-4.5-Air |
|---|---|---|
| LMArena Math | 1145 | 1396 |
| Omni-MATH | — | 39.1% |
| MATH Level 5 | 11.7% | — |
Knowledge GLM-4.5-Air leads
DBRX: 14.9 (#294), GLM-4.5-Air: 35.0 (#191)
| Benchmark | DBRX | GLM-4.5-Air |
|---|---|---|
| LMArena Expert | 1076 | 1370 |
| GPQA Diamond | 32.9% | — |
| Humanity's Last Exam | — | 8.1% |
| MMLU-Pro | — | 76.2% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 59.4% |
Multilingual GLM-4.5-Air leads
DBRX: 29.3 (#268), GLM-4.5-Air: 49.1 (#135)
| Benchmark | DBRX | GLM-4.5-Air |
|---|---|---|
| LMArena Non-English | 1071 | 1366 |
| LMArena Chinese | 1068 | 1426 |
| LMArena French | 1096 | 1399 |
| LMArena German | 1057 | 1377 |
| LMArena Japanese | 990 | 1348 |
| LMArena Korean | 993 | 1308 |
| LMArena Russian | 1078 | 1373 |
| LMArena Spanish | 1064 | 1386 |
Instruction Following GLM-4.5-Air leads
DBRX: 57.5 (#270), GLM-4.5-Air: 69.6 (#171)
| Benchmark | DBRX | GLM-4.5-Air |
|---|---|---|
| LMArena Instruction Following | 1112 | 1354 |
| IFEval | — | 81.2% |
Long Context GLM-4.5-Air leads
DBRX: 33.7 (#258), GLM-4.5-Air: 41.6 (#135)
| Benchmark | DBRX | GLM-4.5-Air |
|---|---|---|
| LMArena Longer Query | 1112 | 1366 |
Writing & Preference GLM-4.5-Air leads
DBRX: 33.6 (#275), GLM-4.5-Air: 55.9 (#139)
| Benchmark | DBRX | GLM-4.5-Air |
|---|---|---|
| LMArena Text | 1119 | 1384 |
| LMArena Creative Writing | 1104 | 1343 |
| LMArena Multi-Turn | 1111 | 1371 |
| WildBench | — | 78.9% |
Frequently asked questions
Is DBRX better than GLM-4.5-Air?
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 29.4 on the Noometry Index.
Is DBRX or GLM-4.5-Air better for coding?
They score almost the same on coding (32.9 vs 33.3); test both on your own repository before choosing.
How many benchmarks do DBRX and GLM-4.5-Air share?
17 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and GLM-4.5-Air has 27.