Model comparison
GLM-4.6 vs Llama 2-13B
GLM-4.6 is the stronger model overall, scoring 41.4 to 29.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
MetaSummary
- They share 17 benchmarks with published results for both. GLM-4.6 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-4.6 leads 61.1 to 29.8.
Side by side
| GLM-4.6 | Llama 2-13B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 41.4 | 29.6 |
| Released | 2025-09-30 | 2023-07-18 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $2.20 | — |
| Results tracked | 29 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6 leads
GLM-4.6: 40.1 (#148), Llama 2-13B: 30.9 (#291)
| Benchmark | GLM-4.6 | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1449 | 1062 |
| SWE-bench Verified (bash only) | 55.4% | — |
| LMArena WebDev | 1340 | — |
| SciCode | 38.4% | — |
| ALE-Bench | 340.82 | — |
Agentic & Tool Use Not comparable
GLM-4.6: 32.3 (#66), Llama 2-13B: —
| Benchmark | GLM-4.6 | Llama 2-13B |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |
Reasoning GLM-4.6 leads
GLM-4.6: 23.7 (#172), Llama 2-13B: 12.8 (#337)
| Benchmark | GLM-4.6 | Llama 2-13B |
|---|---|---|
| LMArena Hard Prompts | 1440 | 1051 |
| Kagi LLM Benchmark | 47.4% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.2% |
| BIG-Bench Hard | — | 58.2% |
| Epoch Capabilities Index | — | 106.17 |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math GLM-4.6 leads
GLM-4.6: 39.1 (#111), Llama 2-13B: 31.1 (#229)
| Benchmark | GLM-4.6 | Llama 2-13B |
|---|---|---|
| LMArena Math | 1432 | 1065 |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
| GSM8K | — | 36.9% |
Knowledge GLM-4.6 leads
GLM-4.6: 40.2 (#124), Llama 2-13B: 28.1 (#249)
| Benchmark | GLM-4.6 | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1431 | 1030 |
| Vectara Hallucination Rate | 9.5% | — |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
GLM-4.6: —, Llama 2-13B: —
| Benchmark | GLM-4.6 | Llama 2-13B |
|---|---|---|
| ScienceQA | — | 55.8% |
Multilingual GLM-4.6 leads
GLM-4.6: 53.5 (#66), Llama 2-13B: 26.5 (#279)
| Benchmark | GLM-4.6 | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1426 | 1024 |
| LMArena Chinese | 1499 | 1001 |
| LMArena French | 1459 | 1044 |
| LMArena German | 1447 | 1009 |
| LMArena Japanese | 1393 | 894 |
| LMArena Korean | 1400 | 953 |
| LMArena Russian | 1419 | 1055 |
| LMArena Spanish | 1436 | 1087 |
Instruction Following GLM-4.6 leads
GLM-4.6: 74.3 (#98), Llama 2-13B: 53.3 (#287)
| Benchmark | GLM-4.6 | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1410 | 1045 |
Long Context GLM-4.6 leads
GLM-4.6: 43.4 (#94), Llama 2-13B: 32.3 (#269)
| Benchmark | GLM-4.6 | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1422 | 1064 |
Writing & Preference GLM-4.6 leads
GLM-4.6: 61.1 (#90), Llama 2-13B: 29.8 (#289)
| Benchmark | GLM-4.6 | Llama 2-13B |
|---|---|---|
| LMArena Text | 1440 | 1084 |
| LMArena Creative Writing | 1411 | 1047 |
| LMArena Multi-Turn | 1427 | 1050 |
| EQ-Bench Creative Writing | 1411 | — |
Frequently asked questions
Is GLM-4.6 better than Llama 2-13B?
GLM-4.6 is the stronger model overall, scoring 41.4 to 29.6 on the Noometry Index.
Is GLM-4.6 or Llama 2-13B better for coding?
GLM-4.6 scores higher on coding benchmarks: 40.1 versus 30.9 in the Noometry coding category.
How many benchmarks do GLM-4.6 and Llama 2-13B share?
17 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Llama 2-13B has 32.