Model comparison
GLM-5 vs Llama 2-13B
GLM-5 is the stronger model overall, scoring 46.1 to 29.6 on the Noometry Index.
Last verified . 19 shared benchmarks.
MetaSummary
- They share 19 benchmarks with published results for both. GLM-5 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 leads 66.0 to 29.8.
- The biggest single-benchmark swing is Chess Puzzles: 10% for GLM-5 and 0% for Llama 2-13B.
Side by side
| GLM-5 | Llama 2-13B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 46.1 | 29.6 |
| Released | 2026-02-11 | 2023-07-18 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $3.20 | — |
| Results tracked | 45 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#52), Llama 2-13B: 30.9 (#291)
| Benchmark | GLM-5 | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1461 | 1062 |
| SWE-bench Verified | 72.1% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| WeirdML | 48.2% | — |
| ALE-Bench | 765.62 | — |
Agentic & Tool Use Not comparable
GLM-5: 31.1 (#71), Llama 2-13B: —
| Benchmark | GLM-5 | Llama 2-13B |
|---|---|---|
| Terminal-Bench | 52.4% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
| Vending-Bench 2 | 4,432 | — |
Reasoning GLM-5 leads
GLM-5: 27.6 (#116), Llama 2-13B: 12.8 (#337)
| Benchmark | GLM-5 | Llama 2-13B |
|---|---|---|
| Chess Puzzles | 10% | 0% |
| LMArena Hard Prompts | 1452 | 1051 |
| Epoch Capabilities Index | 145.83 | 106.17 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 53.2% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 74.8% | — |
| ARC-AGI-1 | 44.7% | — |
| DTBench | — | 42.2% |
| BIG-Bench Hard | — | 58.2% |
| ForecastBench | 61 | — |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math GLM-5 leads
GLM-5: 46.4 (#71), Llama 2-13B: 31.1 (#229)
| Benchmark | GLM-5 | Llama 2-13B |
|---|---|---|
| LMArena Math | 1440 | 1065 |
| MathArena Final-Answer Competitions | 65.7% | — |
| OTIS Mock AIME 2024-2025 | 80% | — |
| FrontierMath (Feb 2025 set) | 16.4% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
| GSM8K | — | 36.9% |
Knowledge GLM-5 leads
GLM-5: 52.3 (#64), Llama 2-13B: 28.1 (#249)
| Benchmark | GLM-5 | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1454 | 1030 |
| GPQA Diamond | 87.8% | — |
| Vectara Hallucination Rate | 10.1% | — |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
GLM-5: —, Llama 2-13B: —
| Benchmark | GLM-5 | Llama 2-13B |
|---|---|---|
| ScienceQA | — | 55.8% |
Multilingual GLM-5 leads
GLM-5: 53.7 (#58), Llama 2-13B: 26.5 (#279)
| Benchmark | GLM-5 | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1430 | 1024 |
| LMArena Chinese | 1511 | 1001 |
| LMArena French | 1455 | 1044 |
| LMArena German | 1445 | 1009 |
| LMArena Japanese | 1416 | 894 |
| LMArena Korean | 1423 | 953 |
| LMArena Russian | 1436 | 1055 |
| LMArena Spanish | 1454 | 1087 |
Instruction Following GLM-5 leads
GLM-5: 75.2 (#67), Llama 2-13B: 53.3 (#287)
| Benchmark | GLM-5 | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1428 | 1045 |
Long Context GLM-5 leads
GLM-5: 44.7 (#60), Llama 2-13B: 32.3 (#269)
| Benchmark | GLM-5 | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1446 | 1064 |
| CL-bench | 18.7% | — |
Writing & Preference GLM-5 leads
GLM-5: 66.0 (#38), Llama 2-13B: 29.8 (#289)
| Benchmark | GLM-5 | Llama 2-13B |
|---|---|---|
| LMArena Text | 1446 | 1084 |
| LMArena Creative Writing | 1439 | 1047 |
| LMArena Multi-Turn | 1456 | 1050 |
| EQ-Bench Creative Writing | 1601 | — |
Frequently asked questions
Is GLM-5 better than Llama 2-13B?
GLM-5 is the stronger model overall, scoring 46.1 to 29.6 on the Noometry Index.
Is GLM-5 or Llama 2-13B better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 30.9 in the Noometry coding category.
How many benchmarks do GLM-5 and Llama 2-13B share?
19 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and Llama 2-13B has 32.