Model comparison
GLM-5.3-Flash vs Llama 2-70B
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 24.4 on the Noometry Index.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. GLM-5.3-Flash scores higher in 8 categories and Llama 2-70B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.3-Flash leads 58.4 to 7.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.9% for GLM-5.3-Flash and 0% for Llama 2-70B.
Side by side
| GLM-5.3-Flash | Llama 2-70B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 51.8 | 24.4 |
| Released | 2026-08-20 | 2023-07-18 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.50 | — |
| Results tracked | 40 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3-Flash leads
GLM-5.3-Flash: 53.1 (#31), Llama 2-70B: 31.4 (#286)
| Benchmark | GLM-5.3-Flash | Llama 2-70B |
|---|---|---|
| LMArena Coding | 1508 | 1079 |
| DeepSWE | 63.4% | — |
| FrontierCode | 31.8% | — |
| CursorBench | 36.8% | — |
| LMArena WebDev | 1609 | — |
| FrontierSWE | 18.1% | — |
| SciCode | 51.6% | — |
| ALE-Bench | 303.55 | — |
Agentic & Tool Use Not comparable
GLM-5.3-Flash: 34.2 (#47), Llama 2-70B: —
| Benchmark | GLM-5.3-Flash | Llama 2-70B |
|---|---|---|
| APEX-Agents | 52.8% | — |
| GDP.pdf | 14% | — |
Reasoning GLM-5.3-Flash leads
GLM-5.3-Flash: 48.0 (#42), Llama 2-70B: 14.4 (#325)
| Benchmark | GLM-5.3-Flash | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 1491 | 1073 |
| Epoch Capabilities Index | 151.88 | 113.79 |
| ARC-AGI-2 | 65.8% | — |
| ARC-AGI-1 | 91% | — |
| CritPt | 15.4% | — |
| Chess Puzzles | 14% | — |
| Mystery Game Puzzles | 8% | — |
| DTBench | — | 41.6% |
| Surface Evolver Bench | 52.5% | — |
| Bench to the Future 3 | 0.15 | — |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| ForecastBench | — | 51.4 |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| PIQA | — | 82.8% |
| WinoGrande | — | 80.2% |
Math GLM-5.3-Flash leads
GLM-5.3-Flash: 53.3 (#47), Llama 2-70B: 8.1 (#326)
| Benchmark | GLM-5.3-Flash | Llama 2-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.9% | 0% |
| LMArena Math | 1500 | 1091 |
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 21% | — |
| MATH Level 5 | — | 3.3% |
| GSM8K | — | 69.6% |
Knowledge GLM-5.3-Flash leads
GLM-5.3-Flash: 58.4 (#36), Llama 2-70B: 7.4 (#310)
| Benchmark | GLM-5.3-Flash | Llama 2-70B |
|---|---|---|
| GPQA Diamond | 90.2% | 26.3% |
| LMArena Expert | 1513 | 1039 |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| MMLU | — | 69.9% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |
Multimodal Not comparable
GLM-5.3-Flash: 42.8 (#27), Llama 2-70B: —
| Benchmark | GLM-5.3-Flash | Llama 2-70B |
|---|---|---|
| LMArena Vision | 1296 | — |
Multilingual GLM-5.3-Flash leads
GLM-5.3-Flash: 56.0 (#25), Llama 2-70B: 27.7 (#274)
| Benchmark | GLM-5.3-Flash | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 1462 | 1045 |
| LMArena Chinese | 1527 | 995 |
| LMArena French | 1496 | 1090 |
| LMArena German | 1470 | 1041 |
| LMArena Japanese | 1429 | 927 |
| LMArena Korean | 1446 | 964 |
| LMArena Russian | 1469 | 1083 |
| LMArena Spanish | 1471 | 1143 |
Instruction Following GLM-5.3-Flash leads
GLM-5.3-Flash: 77.5 (#20), Llama 2-70B: 54.9 (#278)
| Benchmark | GLM-5.3-Flash | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 1478 | 1071 |
Long Context GLM-5.3-Flash leads
GLM-5.3-Flash: 45.4 (#39), Llama 2-70B: 32.3 (#270)
| Benchmark | GLM-5.3-Flash | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | 1482 | 1062 |
Writing & Preference GLM-5.3-Flash leads
GLM-5.3-Flash: 65.3 (#50), Llama 2-70B: 32.3 (#279)
| Benchmark | GLM-5.3-Flash | Llama 2-70B |
|---|---|---|
| LMArena Text | 1471 | 1115 |
| LMArena Creative Writing | 1442 | 1075 |
| LMArena Multi-Turn | 1467 | 1088 |
Frequently asked questions
Is GLM-5.3-Flash better than Llama 2-70B?
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 24.4 on the Noometry Index.
Is GLM-5.3-Flash or Llama 2-70B better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.1 versus 31.4 in the Noometry coding category.
How many benchmarks do GLM-5.3-Flash and Llama 2-70B share?
20 benchmarks have published results for both models. GLM-5.3-Flash has 40 scored results on Noometry and Llama 2-70B has 35.