Model comparison
GLM-4.5 vs Llama 3-70B
GLM-4.5 is the stronger model overall, scoring 42.0 to 28.8 on the Noometry Index.
Last verified . 18 shared benchmarks.
MetaSummary
- They share 18 benchmarks with published results for both. GLM-4.5 scores higher in 8 categories and Llama 3-70B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.5 leads 39.0 to 12.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 57.9% for GLM-4.5 and 35.1% for Llama 3-70B.
Side by side
| GLM-4.5 | Llama 3-70B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 42.0 | 28.8 |
| Released | 2025-07-27 | 2024-04-18 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 98K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $2.20 | — |
| Results tracked | 27 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.5 leads
GLM-4.5: 41.4 (#125), Llama 3-70B: 35.8 (#218)
| Benchmark | GLM-4.5 | Llama 3-70B |
|---|---|---|
| LMArena Coding | 1434 | 1206 |
| SWE-bench Verified (bash only) | 54.2% | — |
| WeirdML | 40.6% | — |
| BigCodeBench Instruct | — | 43.6% |
| BigCodeBench Complete | — | 54.5% |
| ALE-Bench | 344.82 | — |
| AlgoTune | 1.52 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |
Agentic & Tool Use Not comparable
GLM-4.5: —, Llama 3-70B: 21.1 (#139)
| Benchmark | GLM-4.5 | Llama 3-70B |
|---|---|---|
| Cybench | — | 5% |
Reasoning GLM-4.5 leads
GLM-4.5: 28.6 (#100), Llama 3-70B: 18.0 (#288)
| Benchmark | GLM-4.5 | Llama 3-70B |
|---|---|---|
| Kagi LLM Benchmark | 57.9% | 35.1% |
| LMArena Hard Prompts | 1429 | 1195 |
| DTBench | — | 54.2% |
| Epoch Capabilities Index | — | 122.93 |
| ForecastBench | — | 57.1 |
| WinoGrande | — | 83.5% |
Math GLM-4.5 leads
GLM-4.5: 39.0 (#116), Llama 3-70B: 12.8 (#305)
| Benchmark | GLM-4.5 | Llama 3-70B |
|---|---|---|
| LMArena Math | 1427 | 1218 |
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| MATH Level 5 | — | 22.6% |
Knowledge GLM-4.5 leads
GLM-4.5: 35.9 (#179), Llama 3-70B: 20.8 (#277)
| Benchmark | GLM-4.5 | Llama 3-70B |
|---|---|---|
| LMArena Expert | 1433 | 1149 |
| GPQA Diamond | — | 40.6% |
| Humanity's Last Exam | 8.3% | — |
| Confabulations | 11.3% | — |
| MMLU | — | 79.3% |
Multilingual GLM-4.5 leads
GLM-4.5: 52.8 (#77), Llama 3-70B: 33.6 (#251)
| Benchmark | GLM-4.5 | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1417 | 1142 |
| LMArena Chinese | 1465 | 1114 |
| LMArena French | 1418 | 1232 |
| LMArena German | 1407 | 1169 |
| LMArena Japanese | 1415 | 1017 |
| LMArena Korean | 1380 | 1017 |
| LMArena Russian | 1414 | 1159 |
| LMArena Spanish | 1454 | 1241 |
Instruction Following GLM-4.5 leads
GLM-4.5: 74.1 (#104), Llama 3-70B: 62.5 (#238)
| Benchmark | GLM-4.5 | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1404 | 1194 |
Long Context GLM-4.5 leads
GLM-4.5: 38.2 (#201), Llama 3-70B: 35.6 (#240)
| Benchmark | GLM-4.5 | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1412 | 1174 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference GLM-4.5 leads
GLM-4.5: 57.5 (#127), Llama 3-70B: 42.8 (#231)
| Benchmark | GLM-4.5 | Llama 3-70B |
|---|---|---|
| LMArena Text | 1430 | 1221 |
| LMArena Creative Writing | 1395 | 1210 |
| LMArena Multi-Turn | 1415 | 1223 |
| Short-Story Creative Writing | 73.4% | — |
| EQ-Bench Creative Writing | 1343 | — |
Frequently asked questions
Is GLM-4.5 better than Llama 3-70B?
GLM-4.5 is the stronger model overall, scoring 42.0 to 28.8 on the Noometry Index.
Is GLM-4.5 or Llama 3-70B better for coding?
GLM-4.5 scores higher on coding benchmarks: 41.4 versus 35.8 in the Noometry coding category.
How many benchmarks do GLM-4.5 and Llama 3-70B share?
18 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Llama 3-70B has 31.