Model comparison
Codellama 70b Instruct vs GLM-4.5-Air
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 33.7 on the Noometry Index.
Last verified . 4 shared benchmarks.
MetaSummary
- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 1 category and GLM-4.5-Air in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GLM-4.5-Air leads 49.1 to 24.8.
Side by side
| Codellama 70b Instruct | GLM-4.5-Air | |
|---|---|---|
| Provider | Meta | Z.ai (Zhipu) |
| Noometry Index | 33.7 | 38.9 |
| 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 | 7 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 70b Instruct leads
Codellama 70b Instruct: 37.6 (#193), GLM-4.5-Air: 33.3 (#259)
| Benchmark | Codellama 70b Instruct | GLM-4.5-Air |
|---|---|---|
| GSO | — | 2.9% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1397 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Reasoning GLM-4.5-Air leads
Codellama 70b Instruct: 20.1 (#242), GLM-4.5-Air: 24.1 (#166)
| Benchmark | Codellama 70b Instruct | GLM-4.5-Air |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1379 |
| Kagi LLM Benchmark | — | 43% |
| ForecastBench | — | 59.2 |
Math Not comparable
Codellama 70b Instruct: —, GLM-4.5-Air: 36.2 (#170)
| Benchmark | Codellama 70b Instruct | GLM-4.5-Air |
|---|---|---|
| Omni-MATH | — | 39.1% |
| LMArena Math | — | 1396 |
Knowledge Not comparable
Codellama 70b Instruct: —, GLM-4.5-Air: 35.0 (#191)
| Benchmark | Codellama 70b 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 70b Instruct: 24.8 (#288), GLM-4.5-Air: 49.1 (#135)
| Benchmark | Codellama 70b Instruct | GLM-4.5-Air |
|---|---|---|
| LMArena Non-English | 992 | 1366 |
| LMArena Chinese | — | 1426 |
| LMArena French | — | 1399 |
| LMArena German | — | 1377 |
| LMArena Japanese | — | 1348 |
| LMArena Korean | — | 1308 |
| LMArena Russian | — | 1373 |
| LMArena Spanish | — | 1386 |
Instruction Following GLM-4.5-Air leads
Codellama 70b Instruct: 51.9 (#293), GLM-4.5-Air: 69.6 (#171)
| Benchmark | Codellama 70b Instruct | GLM-4.5-Air |
|---|---|---|
| LMArena Instruction Following | 1024 | 1354 |
| IFEval | — | 81.2% |
Long Context Not comparable
Codellama 70b Instruct: —, GLM-4.5-Air: 41.6 (#135)
| Benchmark | Codellama 70b Instruct | GLM-4.5-Air |
|---|---|---|
| LMArena Longer Query | — | 1366 |
Writing & Preference GLM-4.5-Air leads
Codellama 70b Instruct: 33.4 (#277), GLM-4.5-Air: 55.9 (#139)
| Benchmark | Codellama 70b Instruct | GLM-4.5-Air |
|---|---|---|
| LMArena Text | 1057 | 1384 |
| LMArena Creative Writing | — | 1343 |
| WildBench | — | 78.9% |
| LMArena Multi-Turn | — | 1371 |
Frequently asked questions
Is Codellama 70b Instruct better than GLM-4.5-Air?
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 33.7 on the Noometry Index.
Is Codellama 70b Instruct or GLM-4.5-Air better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 33.3 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and GLM-4.5-Air share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and GLM-4.5-Air has 27.