Model comparison
GLM-5.2 vs Llama 3-70B
GLM-5.2 is the stronger model overall, scoring 50.9 to 28.5 on the Noometry Index.
Last verified . 22 shared benchmarks.
MetaSummary
- They share 22 benchmarks with published results for both. GLM-5.2 scores higher in 9 categories and Llama 3-70B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.2 leads 55.4 to 12.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 86.4% for GLM-5.2 and 4.3% for Llama 3-70B.
Side by side
| GLM-5.2 | Llama 3-70B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 50.9 | 28.5 |
| Released | 2026-06-13 | 2024-04-18 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 131K | — |
| Input $ / M tokens | $1.40 | — |
| Output $ / M tokens | $4.40 | — |
| Results tracked | 50 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.2 leads
GLM-5.2: 50.9 (#37), Llama 3-70B: 35.3 (#215)
| Benchmark | GLM-5.2 | Llama 3-70B |
|---|---|---|
| LMArena Coding | 1484 | 1206 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| LMArena WebDev | 1604 | — |
| SciCode | 50.5% | — |
| WeirdML | 70.1% | — |
| BigCodeBench Instruct | — | 43.6% |
| BigCodeBench Complete | — | 54.5% |
| ALE-Bench | 1,047 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |
Agentic & Tool Use GLM-5.2 leads
GLM-5.2: 31.6 (#63), Llama 3-70B: 20.9 (#132)
| Benchmark | GLM-5.2 | Llama 3-70B |
|---|---|---|
| τ²-bench Banking | 37.1% | — |
| Cybench | — | 5% |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 8,314 | — |
Reasoning GLM-5.2 leads
GLM-5.2: 42.1 (#46), Llama 3-70B: 17.4 (#284)
| Benchmark | GLM-5.2 | Llama 3-70B |
|---|---|---|
| Kagi LLM Benchmark | 62.6% | 35.1% |
| LMArena Hard Prompts | 1480 | 1195 |
| DTBench | 93.6% | 54.2% |
| Epoch Capabilities Index | 151.76 | 122.91 |
| ARC-AGI-2 | 22.8% | — |
| SimpleBench | 58.8% | — |
| NYT Connections (extended) | 74.3% | — |
| ARC-AGI-1 | 77% | — |
| CritPt | 20.9% | — |
| Chess Puzzles | 21% | — |
| EBR-Bench | 9.5% | — |
| Mystery Game Puzzles | 19% | — |
| LMCA | 45.8% | — |
| Surface Evolver Bench | 55.6% | — |
| ForecastBench | — | 57.1 |
| WinoGrande | — | 83.5% |
Math GLM-5.2 leads
GLM-5.2: 55.4 (#35), Llama 3-70B: 12.0 (#299)
| Benchmark | GLM-5.2 | Llama 3-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.4% | 4.3% |
| LMArena Math | 1482 | 1218 |
| FrontierMath (Tiers 1-3) | 59.2% | — |
| FrontierMath Tier 4 | 29.3% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| ProofBench | 35% | — |
| MATH Level 5 | — | 22.6% |
Knowledge GLM-5.2 leads
GLM-5.2: 57.1 (#36), Llama 3-70B: 20.8 (#272)
| Benchmark | GLM-5.2 | Llama 3-70B |
|---|---|---|
| GPQA Diamond | 91.9% | 40.6% |
| LMArena Expert | 1484 | 1149 |
| SimpleQA Verified | 34.2% | — |
| MMLU | — | 79.3% |
Multilingual GLM-5.2 leads
GLM-5.2: 56.0 (#25), Llama 3-70B: 33.8 (#246)
| Benchmark | GLM-5.2 | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1459 | 1142 |
| LMArena Chinese | 1518 | 1114 |
| LMArena French | 1476 | 1231 |
| LMArena German | 1470 | 1169 |
| LMArena Japanese | 1451 | 1017 |
| LMArena Korean | 1445 | 1017 |
| LMArena Russian | 1467 | 1159 |
| LMArena Spanish | 1477 | 1241 |
Instruction Following GLM-5.2 leads
GLM-5.2: 77.1 (#32), Llama 3-70B: 62.8 (#233)
| Benchmark | GLM-5.2 | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1465 | 1194 |
Long Context GLM-5.2 leads
GLM-5.2: 45.3 (#43), Llama 3-70B: 35.6 (#235)
| Benchmark | GLM-5.2 | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1479 | 1174 |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.7 (#20), Llama 3-70B: 43.0 (#225)
| Benchmark | GLM-5.2 | Llama 3-70B |
|---|---|---|
| LMArena Text | 1470 | 1221 |
| LMArena Creative Writing | 1465 | 1210 |
| LMArena Multi-Turn | 1468 | 1223 |
| EQ-Bench Creative Writing | 1757 | — |
| EQ-Bench 4 | 1222 | — |
Frequently asked questions
Is GLM-5.2 better than Llama 3-70B?
GLM-5.2 is the stronger model overall, scoring 50.9 to 28.5 on the Noometry Index.
Is GLM-5.2 or Llama 3-70B better for coding?
GLM-5.2 scores higher on coding benchmarks: 50.9 versus 35.3 in the Noometry coding category.
How many benchmarks do GLM-5.2 and Llama 3-70B share?
22 benchmarks have published results for both models. GLM-5.2 has 50 scored results on Noometry and Llama 3-70B has 31.