Model comparison
GLM-4.5-Air vs Llama 2-70B
GLM-4.5-Air is the stronger model overall, scoring 38.7 to 24.1 on the Noometry Index.
Last verified . 18 shared benchmarks.
MetaSummary
- They share 18 benchmarks with published results for both. GLM-4.5-Air scores higher in 8 categories and Llama 2-70B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.5-Air leads 34.6 to 7.4.
Side by side
| GLM-4.5-Air | Llama 2-70B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 38.7 | 24.1 |
| Released | 2025-07-20 | 2023-07-18 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 98K | — |
| Input $ / M tokens | $0.20 | — |
| Output $ / M tokens | $1.10 | — |
| Results tracked | 27 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.5-Air leads
GLM-4.5-Air: 34.5 (#225), Llama 2-70B: 30.8 (#281)
| Benchmark | GLM-4.5-Air | Llama 2-70B |
|---|---|---|
| LMArena Coding | 1397 | 1079 |
| GSO | 2.9% | — |
Reasoning GLM-4.5-Air leads
GLM-4.5-Air: 23.3 (#166), Llama 2-70B: 13.7 (#324)
| Benchmark | GLM-4.5-Air | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1073 |
| ForecastBench | 59.2 | 51.4 |
| Kagi LLM Benchmark | 43% | — |
| DTBench | — | 41.6% |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| Epoch Capabilities Index | — | 113.59 |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| PIQA | — | 82.8% |
| WinoGrande | — | 80.2% |
Math GLM-4.5-Air leads
GLM-4.5-Air: 33.8 (#166), Llama 2-70B: 7.5 (#320)
| Benchmark | GLM-4.5-Air | Llama 2-70B |
|---|---|---|
| LMArena Math | 1396 | 1091 |
| OTIS Mock AIME 2024-2025 | — | 0% |
| Omni-MATH | 39.1% | — |
| MATH Level 5 | — | 3.3% |
| GSM8K | — | 69.6% |
Knowledge GLM-4.5-Air leads
GLM-4.5-Air: 34.6 (#184), Llama 2-70B: 7.4 (#305)
| Benchmark | GLM-4.5-Air | Llama 2-70B |
|---|---|---|
| LMArena Expert | 1370 | 1039 |
| GPQA Diamond | — | 26.3% |
| Humanity's Last Exam | 8.1% | — |
| MMLU-Pro | 76.2% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 59.4% | — |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| MMLU | — | 69.9% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |
Multilingual GLM-4.5-Air leads
GLM-4.5-Air: 49.4 (#130), Llama 2-70B: 27.9 (#269)
| Benchmark | GLM-4.5-Air | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 1366 | 1045 |
| LMArena Chinese | 1427 | 994 |
| LMArena French | 1399 | 1089 |
| LMArena German | 1376 | 1041 |
| LMArena Japanese | 1348 | 927 |
| LMArena Korean | 1306 | 964 |
| LMArena Russian | 1373 | 1083 |
| LMArena Spanish | 1385 | 1142 |
Instruction Following GLM-4.5-Air leads
GLM-4.5-Air: 69.8 (#165), Llama 2-70B: 55.1 (#273)
| Benchmark | GLM-4.5-Air | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 1353 | 1071 |
| IFEval | 81.2% | — |
Long Context GLM-4.5-Air leads
GLM-4.5-Air: 41.6 (#130), Llama 2-70B: 32.2 (#265)
| Benchmark | GLM-4.5-Air | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | 1367 | 1062 |
Writing & Preference GLM-4.5-Air leads
GLM-4.5-Air: 56.1 (#134), Llama 2-70B: 32.5 (#274)
| Benchmark | GLM-4.5-Air | Llama 2-70B |
|---|---|---|
| LMArena Text | 1384 | 1115 |
| LMArena Creative Writing | 1343 | 1075 |
| LMArena Multi-Turn | 1371 | 1088 |
| WildBench | 78.9% | — |
Frequently asked questions
Is GLM-4.5-Air better than Llama 2-70B?
GLM-4.5-Air is the stronger model overall, scoring 38.7 to 24.1 on the Noometry Index.
Is GLM-4.5-Air or Llama 2-70B better for coding?
GLM-4.5-Air scores higher on coding benchmarks: 34.5 versus 30.8 in the Noometry coding category.
How many benchmarks do GLM-4.5-Air and Llama 2-70B share?
18 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Llama 2-70B has 35.