Model comparison
Codellama 34b Instruct vs GLM-4.5-Air
GLM-4.5-Air is the stronger model overall, scoring 38.7 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-4.5-Air in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.5-Air leads 56.1 to 28.4.
Side by side
| Codellama 34b Instruct | GLM-4.5-Air | |
|---|---|---|
| Provider | Meta | Z.ai (Zhipu) |
| Noometry Index | 30.2 | 38.7 |
| Released | — | 2025-07-20 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 98K |
| Input $ / M tokens | — | $0.20 |
| Output $ / M tokens | — | $1.10 |
| Results tracked | 14 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.5-Air leads
Codellama 34b Instruct: 28.0 (#310), GLM-4.5-Air: 34.5 (#225)
| Benchmark | Codellama 34b Instruct | GLM-4.5-Air |
|---|---|---|
| LMArena Coding | 1046 | 1397 |
| GSO | — | 2.9% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning GLM-4.5-Air leads
Codellama 34b Instruct: 18.8 (#250), GLM-4.5-Air: 23.3 (#166)
| Benchmark | Codellama 34b Instruct | GLM-4.5-Air |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1379 |
| Kagi LLM Benchmark | — | 43% |
| ForecastBench | — | 59.2 |
Math GLM-4.5-Air leads
Codellama 34b Instruct: 28.5 (#227), GLM-4.5-Air: 33.8 (#166)
| Benchmark | Codellama 34b Instruct | GLM-4.5-Air |
|---|---|---|
| LMArena Math | 1056 | 1396 |
| Omni-MATH | — | 39.1% |
Knowledge Not comparable
Codellama 34b Instruct: —, GLM-4.5-Air: 34.6 (#184)
| Benchmark | Codellama 34b Instruct | GLM-4.5-Air |
|---|---|---|
| Humanity's Last Exam | — | 8.1% |
| MMLU-Pro | — | 76.2% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 59.4% |
| LMArena Expert | — | 1370 |
Multilingual GLM-4.5-Air leads
Codellama 34b Instruct: 25.9 (#279), GLM-4.5-Air: 49.4 (#130)
| Benchmark | Codellama 34b Instruct | GLM-4.5-Air |
|---|---|---|
| LMArena Non-English | 1011 | 1366 |
| LMArena Chinese | 976 | 1427 |
| LMArena French | — | 1399 |
| LMArena German | — | 1376 |
| LMArena Japanese | — | 1348 |
| LMArena Korean | — | 1306 |
| LMArena Russian | — | 1373 |
| LMArena Spanish | — | 1385 |
Instruction Following GLM-4.5-Air leads
Codellama 34b Instruct: 52.4 (#286), GLM-4.5-Air: 69.8 (#165)
| Benchmark | Codellama 34b Instruct | GLM-4.5-Air |
|---|---|---|
| LMArena Instruction Following | 1028 | 1353 |
| IFEval | — | 81.2% |
Long Context GLM-4.5-Air leads
Codellama 34b Instruct: 30.8 (#279), GLM-4.5-Air: 41.6 (#130)
| Benchmark | Codellama 34b Instruct | GLM-4.5-Air |
|---|---|---|
| LMArena Longer Query | 1014 | 1367 |
Writing & Preference GLM-4.5-Air leads
Codellama 34b Instruct: 28.4 (#292), GLM-4.5-Air: 56.1 (#134)
| Benchmark | Codellama 34b Instruct | GLM-4.5-Air |
|---|---|---|
| LMArena Text | 1066 | 1384 |
| LMArena Creative Writing | 1032 | 1343 |
| LMArena Multi-Turn | 1015 | 1371 |
| WildBench | — | 78.9% |
Frequently asked questions
Is Codellama 34b Instruct better than GLM-4.5-Air?
GLM-4.5-Air is the stronger model overall, scoring 38.7 to 30.2 on the Noometry Index.
Is Codellama 34b Instruct or GLM-4.5-Air better for coding?
GLM-4.5-Air scores higher on coding benchmarks: 34.5 versus 28.0 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and GLM-4.5-Air share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and GLM-4.5-Air has 27.