Model comparison
GLM-5.3 vs Llama 2-13B
GLM-5.3 is the stronger model overall, scoring 54.6 to 29.1 on the Noometry Index.
Last verified . 20 shared benchmarks.
MetaSummary
- They share 20 benchmarks with published results for both. GLM-5.3 scores higher in 8 categories and Llama 2-13B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5.3 leads 75.9 to 30.0.
- The biggest single-benchmark swing is DTBench: 87.7% for GLM-5.3 and 42.2% for Llama 2-13B.
Side by side
| GLM-5.3 | Llama 2-13B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 54.6 | 29.1 |
| Released | 2026-08-14 | 2023-07-18 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 131K | — |
| Input $ / M tokens | $1.40 | — |
| Output $ / M tokens | $4.40 | — |
| Results tracked | 41 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3 leads
GLM-5.3: 59.0 (#12), Llama 2-13B: 30.4 (#287)
| Benchmark | GLM-5.3 | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1499 | 1062 |
| DeepSWE | 69% | — |
| FrontierCode | 40.1% | — |
| LMArena WebDev | 1623 | — |
| FrontierSWE | 30.2% | — |
| SciCode | 59% | — |
| WeirdML | 75.4% | — |
| ALE-Bench | 1,317 | — |
Agentic & Tool Use Not comparable
GLM-5.3: 36.3 (#34), Llama 2-13B: —
| Benchmark | GLM-5.3 | Llama 2-13B |
|---|---|---|
| APEX-Agents | 56.6% | — |
| Vending-Bench 2 | 8,164 | — |
Reasoning GLM-5.3 leads
GLM-5.3: 45.2 (#42), Llama 2-13B: 12.3 (#333)
| Benchmark | GLM-5.3 | Llama 2-13B |
|---|---|---|
| Chess Puzzles | 21% | 0% |
| LMArena Hard Prompts | 1491 | 1051 |
| DTBench | 87.7% | 42.2% |
| Epoch Capabilities Index | 155.56 | 105.8 |
| NYT Connections (extended) | 74.2% | — |
| CritPt | 19.1% | — |
| Mystery Game Puzzles | 33% | — |
| LMCA | 55.5% | — |
| Bench to the Future 3 | 0.15 | — |
| BIG-Bench Hard | — | 58.2% |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math GLM-5.3 leads
GLM-5.3: 62.1 (#27), Llama 2-13B: 28.7 (#226)
| Benchmark | GLM-5.3 | Llama 2-13B |
|---|---|---|
| LMArena Math | 1493 | 1065 |
| FrontierMath (Tiers 1-3) | 68.8% | — |
| FrontierMath Tier 4 | 29.3% | — |
| OTIS Mock AIME 2024-2025 | 91.1% | — |
| ProofBench | 49% | — |
| GSM8K | — | 36.9% |
Knowledge GLM-5.3 leads
GLM-5.3: 58.3 (#34), Llama 2-13B: 27.5 (#244)
| Benchmark | GLM-5.3 | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1512 | 1030 |
| GPQA Diamond | 90.9% | — |
| SimpleQA Verified | 41% | — |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
GLM-5.3: —, Llama 2-13B: —
| Benchmark | GLM-5.3 | Llama 2-13B |
|---|---|---|
| ScienceQA | — | 55.8% |
Multilingual GLM-5.3 leads
GLM-5.3: 55.9 (#27), Llama 2-13B: 26.7 (#274)
| Benchmark | GLM-5.3 | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1457 | 1024 |
| LMArena Chinese | 1523 | 1001 |
| LMArena French | 1499 | 1043 |
| LMArena German | 1505 | 1009 |
| LMArena Japanese | 1438 | 894 |
| LMArena Korean | 1478 | 953 |
| LMArena Russian | 1460 | 1055 |
| LMArena Spanish | 1444 | 1086 |
Instruction Following GLM-5.3 leads
GLM-5.3: 77.8 (#15), Llama 2-13B: 53.5 (#282)
| Benchmark | GLM-5.3 | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1481 | 1046 |
Long Context GLM-5.3 leads
GLM-5.3: 45.5 (#32), Llama 2-13B: 32.3 (#264)
| Benchmark | GLM-5.3 | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1485 | 1064 |
Writing & Preference GLM-5.3 leads
GLM-5.3: 75.9 (#6), Llama 2-13B: 30.0 (#284)
| Benchmark | GLM-5.3 | Llama 2-13B |
|---|---|---|
| LMArena Text | 1473 | 1085 |
| LMArena Creative Writing | 1459 | 1047 |
| LMArena Multi-Turn | 1473 | 1050 |
| EQ-Bench Creative Writing | 2075 | — |
Frequently asked questions
Is GLM-5.3 better than Llama 2-13B?
GLM-5.3 is the stronger model overall, scoring 54.6 to 29.1 on the Noometry Index.
Is GLM-5.3 or Llama 2-13B better for coding?
GLM-5.3 scores higher on coding benchmarks: 59.0 versus 30.4 in the Noometry coding category.
How many benchmarks do GLM-5.3 and Llama 2-13B share?
20 benchmarks have published results for both models. GLM-5.3 has 41 scored results on Noometry and Llama 2-13B has 32.