Model comparison
Codellama 34b Instruct vs GLM-5V-Turbo
GLM-5V-Turbo is the stronger model overall, scoring 43.1 to 30.2 on the Noometry Index.
Last verified . 10 shared benchmarks.
MetaSummary
- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 0 categories and GLM-5V-Turbo in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5V-Turbo leads 62.6 to 28.4.
- Codellama 34b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 34b Instruct | GLM-5V-Turbo | |
|---|---|---|
| Provider | Meta | Z.ai (Zhipu) |
| Noometry Index | 30.2 | 43.1 |
| Released | — | 2026-04-01 |
| Weights | Open | Proprietary |
| Context window | — | 200K |
| Max output | — | 131K |
| Input $ / M tokens | — | $1.20 |
| Output $ / M tokens | — | $4 |
| Results tracked | 14 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5V-Turbo leads
Codellama 34b Instruct: 28.0 (#310), GLM-5V-Turbo: 41.8 (#105)
| Benchmark | Codellama 34b Instruct | GLM-5V-Turbo |
|---|---|---|
| LMArena Coding | 1046 | 1467 |
| LMArena WebDev | — | 1400 |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning GLM-5V-Turbo leads
Codellama 34b Instruct: 18.8 (#250), GLM-5V-Turbo: 28.5 (#87)
| Benchmark | Codellama 34b Instruct | GLM-5V-Turbo |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1443 |
Math GLM-5V-Turbo leads
Codellama 34b Instruct: 28.5 (#227), GLM-5V-Turbo: 36.6 (#109)
| Benchmark | Codellama 34b Instruct | GLM-5V-Turbo |
|---|---|---|
| LMArena Math | 1056 | 1440 |
Knowledge Not comparable
Codellama 34b Instruct: —, GLM-5V-Turbo: 39.9 (#113)
| Benchmark | Codellama 34b Instruct | GLM-5V-Turbo |
|---|---|---|
| LMArena Expert | — | 1451 |
Multimodal Not comparable
Codellama 34b Instruct: —, GLM-5V-Turbo: 40.1 (#41)
| Benchmark | Codellama 34b Instruct | GLM-5V-Turbo |
|---|---|---|
| LMArena Vision | — | 1264 |
| LMArena Document | — | 1416 |
Multilingual GLM-5V-Turbo leads
Codellama 34b Instruct: 25.9 (#279), GLM-5V-Turbo: 53.2 (#69)
| Benchmark | Codellama 34b Instruct | GLM-5V-Turbo |
|---|---|---|
| LMArena Non-English | 1011 | 1420 |
| LMArena Chinese | 976 | 1488 |
| LMArena French | — | 1443 |
| LMArena German | — | 1422 |
| LMArena Korean | — | 1399 |
| LMArena Russian | — | 1432 |
| LMArena Spanish | — | 1446 |
Instruction Following GLM-5V-Turbo leads
Codellama 34b Instruct: 52.4 (#286), GLM-5V-Turbo: 75.1 (#75)
| Benchmark | Codellama 34b Instruct | GLM-5V-Turbo |
|---|---|---|
| LMArena Instruction Following | 1028 | 1422 |
Long Context GLM-5V-Turbo leads
Codellama 34b Instruct: 30.8 (#279), GLM-5V-Turbo: 44.0 (#76)
| Benchmark | Codellama 34b Instruct | GLM-5V-Turbo |
|---|---|---|
| LMArena Longer Query | 1014 | 1439 |
Writing & Preference GLM-5V-Turbo leads
Codellama 34b Instruct: 28.4 (#292), GLM-5V-Turbo: 62.6 (#69)
| Benchmark | Codellama 34b Instruct | GLM-5V-Turbo |
|---|---|---|
| LMArena Text | 1066 | 1437 |
| LMArena Creative Writing | 1032 | 1414 |
| LMArena Multi-Turn | 1015 | 1432 |
Frequently asked questions
Is Codellama 34b Instruct better than GLM-5V-Turbo?
GLM-5V-Turbo is the stronger model overall, scoring 43.1 to 30.2 on the Noometry Index.
Is Codellama 34b Instruct or GLM-5V-Turbo better for coding?
GLM-5V-Turbo scores higher on coding benchmarks: 41.8 versus 28.0 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and GLM-5V-Turbo share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and GLM-5V-Turbo has 19.