# DBRX vs GLM-4.7-Flash

> GLM-4.7-Flash is the stronger model overall, scoring 38.4 to 29.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/dbrx-vs-glm-4-7-flash
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. DBRX scores higher in 1 category and GLM-4.7-Flash in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.7-Flash leads 35.4 to 14.9.
- The biggest single-benchmark swing is GPQA Diamond: 32.9% for DBRX and 60.5% for GLM-4.7-Flash.

## Snapshot

| | DBRX | GLM-4.7-Flash |
|---|---|---|
| Provider | Databricks | Z.ai (Zhipu) |
| Noometry Index | 29.0 | 38.4 |
| Rank | 307 | 175 |
| Context | — | 200K |
| Input $/M | — | $0.06 |
| Output $/M | — | $0.40 |
| Weights | Open | Open |

## Coding

- DBRX: 32.3 (#262)
- GLM-4.7-Flash: 40.0 (#133)

| Benchmark | DBRX | GLM-4.7-Flash |
|---|---|---|
| LMArena Coding | 1132 | 1383 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |

## Reasoning

- DBRX: 20.5 (#218)
- GLM-4.7-Flash: 20.2 (#224)

| Benchmark | DBRX | GLM-4.7-Flash |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1356 |
| Chess Puzzles | — | 0% |

## Math

- DBRX: 22.3 (#265)
- GLM-4.7-Flash: 34.4 (#159)

| Benchmark | DBRX | GLM-4.7-Flash |
|---|---|---|
| LMArena Math | 1145 | 1354 |
| OTIS Mock AIME 2024-2025 | — | 58.3% |
| MATH Level 5 | 11.7% | — |

## Knowledge

- DBRX: 14.9 (#289)
- GLM-4.7-Flash: 35.4 (#177)

| Benchmark | DBRX | GLM-4.7-Flash |
|---|---|---|
| GPQA Diamond | 32.9% | 60.5% |
| LMArena Expert | 1076 | 1357 |
| Vectara Hallucination Rate | — | 9.3% |

## Multilingual

- DBRX: 29.4 (#263)
- GLM-4.7-Flash: 46.8 (#152)

| Benchmark | DBRX | GLM-4.7-Flash |
|---|---|---|
| LMArena Non-English | 1071 | 1331 |
| LMArena Chinese | 1068 | 1403 |
| LMArena French | 1095 | 1332 |
| LMArena German | 1057 | 1336 |
| LMArena Korean | 993 | 1284 |
| LMArena Russian | 1078 | 1333 |
| LMArena Spanish | 1064 | 1351 |
| LMArena Japanese | 990 | — |

## Instruction Following

- DBRX: 57.7 (#265)
- GLM-4.7-Flash: 70.3 (#162)

| Benchmark | DBRX | GLM-4.7-Flash |
|---|---|---|
| LMArena Instruction Following | 1112 | 1327 |

## Long Context

- DBRX: 33.7 (#253)
- GLM-4.7-Flash: 40.9 (#143)

| Benchmark | DBRX | GLM-4.7-Flash |
|---|---|---|
| LMArena Longer Query | 1112 | 1345 |

## Writing & Preference

- DBRX: 33.7 (#271)
- GLM-4.7-Flash: 47.7 (#206)

| Benchmark | DBRX | GLM-4.7-Flash |
|---|---|---|
| LMArena Text | 1119 | 1351 |
| LMArena Creative Writing | 1104 | 1297 |
| LMArena Multi-Turn | 1111 | 1342 |
| EQ-Bench Creative Writing | — | 1125 |

## FAQ

### Is DBRX better than GLM-4.7-Flash?

GLM-4.7-Flash is the stronger model overall, scoring 38.4 to 29.0 on the Noometry Index.

### Is DBRX or GLM-4.7-Flash better for coding?

GLM-4.7-Flash scores higher on coding benchmarks: 40.0 versus 32.3 in the Noometry coding category.

### How many benchmarks do DBRX and GLM-4.7-Flash share?

17 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and GLM-4.7-Flash has 21.