Model comparison
GLM-5.2 vs Llama 3.1-405B
GLM-5.2 is the stronger model overall, scoring 50.9 to 30.4 on the Noometry Index.
Last verified . 25 shared benchmarks.
MetaSummary
- They share 25 benchmarks with published results for both. GLM-5.2 scores higher in 9 categories and Llama 3.1-405B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.2 leads 55.4 to 17.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 86.4% for GLM-5.2 and 9.7% for Llama 3.1-405B.
Side by side
| GLM-5.2 | Llama 3.1-405B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 50.9 | 30.4 |
| Released | 2026-06-13 | 2024-07-23 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 131K | — |
| Input $ / M tokens | $1.40 | — |
| Output $ / M tokens | $4.40 | — |
| Results tracked | 50 | 42 |
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 3.1-405B: 32.7 (#257)
| Benchmark | GLM-5.2 | Llama 3.1-405B |
|---|---|---|
| WeirdML | 70.1% | 21.4% |
| LMArena Coding | 1484 | 1291 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| LMArena WebDev | 1604 | — |
| SciCode | 50.5% | — |
| ALE-Bench | 1,047 | — |
Agentic & Tool Use GLM-5.2 leads
GLM-5.2: 31.6 (#63), Llama 3.1-405B: 20.9 (#131)
| Benchmark | GLM-5.2 | Llama 3.1-405B |
|---|---|---|
| TheAgentCompany | — | 7.4% |
| τ²-bench Banking | 37.1% | — |
| Cybench | — | 7.5% |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 8,314 | — |
Reasoning GLM-5.2 leads
GLM-5.2: 42.1 (#46), Llama 3.1-405B: 16.4 (#293)
| Benchmark | GLM-5.2 | Llama 3.1-405B |
|---|---|---|
| SimpleBench | 58.8% | 23% |
| Kagi LLM Benchmark | 62.6% | 45% |
| LMArena Hard Prompts | 1480 | 1270 |
| DTBench | 93.6% | 61.4% |
| Epoch Capabilities Index | 151.76 | 128.76 |
| ARC-AGI-2 | 22.8% | — |
| 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% | — |
| BIG-Bench Hard | — | 82.9% |
| ForecastBench | — | 59.9 |
| HellaSwag | — | 89.2% |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |
Math GLM-5.2 leads
GLM-5.2: 55.4 (#35), Llama 3.1-405B: 17.3 (#283)
| Benchmark | GLM-5.2 | Llama 3.1-405B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.4% | 9.7% |
| LMArena Math | 1482 | 1281 |
| FrontierMath (Tiers 1-3) | 59.2% | — |
| FrontierMath Tier 4 | 29.3% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| ProofBench | 35% | — |
| Omni-MATH | — | 24.9% |
| MATH Level 5 | — | 49.8% |
Knowledge GLM-5.2 leads
GLM-5.2: 57.1 (#36), Llama 3.1-405B: 30.4 (#221)
| Benchmark | GLM-5.2 | Llama 3.1-405B |
|---|---|---|
| GPQA Diamond | 91.9% | 50.9% |
| LMArena Expert | 1484 | 1243 |
| SimpleQA Verified | 34.2% | — |
| MMLU-Pro | — | 72.3% |
| Confabulations | — | 17.6% |
| GPQA (HELM) | — | 52.2% |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 84.5% |
| TriviaQA | — | 82.7% |
Multilingual GLM-5.2 leads
GLM-5.2: 56.0 (#25), Llama 3.1-405B: 40.9 (#209)
| Benchmark | GLM-5.2 | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1459 | 1248 |
| LMArena Chinese | 1518 | 1242 |
| LMArena French | 1476 | 1278 |
| LMArena German | 1470 | 1252 |
| LMArena Japanese | 1451 | 1208 |
| LMArena Korean | 1445 | 1184 |
| LMArena Russian | 1467 | 1265 |
| LMArena Spanish | 1477 | 1259 |
Instruction Following GLM-5.2 leads
GLM-5.2: 77.1 (#32), Llama 3.1-405B: 66.1 (#209)
| Benchmark | GLM-5.2 | Llama 3.1-405B |
|---|---|---|
| LMArena Instruction Following | 1465 | 1259 |
| IFEval | — | 81.1% |
Long Context GLM-5.2 leads
GLM-5.2: 45.3 (#43), Llama 3.1-405B: 38.4 (#192)
| Benchmark | GLM-5.2 | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1479 | 1266 |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.7 (#20), Llama 3.1-405B: 39.1 (#246)
| Benchmark | GLM-5.2 | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1470 | 1284 |
| LMArena Creative Writing | 1465 | 1262 |
| EQ-Bench Creative Writing | 1757 | 870 |
| LMArena Multi-Turn | 1468 | 1297 |
| WildBench | — | 78.3% |
| EQ-Bench 4 | 1222 | — |
Frequently asked questions
Is GLM-5.2 better than Llama 3.1-405B?
GLM-5.2 is the stronger model overall, scoring 50.9 to 30.4 on the Noometry Index.
Is GLM-5.2 or Llama 3.1-405B better for coding?
GLM-5.2 scores higher on coding benchmarks: 50.9 versus 32.7 in the Noometry coding category.
How many benchmarks do GLM-5.2 and Llama 3.1-405B share?
25 benchmarks have published results for both models. GLM-5.2 has 50 scored results on Noometry and Llama 3.1-405B has 42.