Model comparison
GLM-5.1 vs Llama 2-70B
GLM-5.1 is the stronger model overall, scoring 47.8 to 24.4 on the Noometry Index.
Last verified . 20 shared benchmarks.
MetaSummary
- They share 20 benchmarks with published results for both. GLM-5.1 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-5.1 leads 54.9 to 7.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for GLM-5.1 and 0% for Llama 2-70B.
Side by side
| GLM-5.1 | Llama 2-70B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 47.8 | 24.4 |
| Released | 2026-04-07 | 2023-07-18 |
| Weights | Open | Open |
| Context window | 200K | — |
| Max output | 131K | — |
| Input $ / M tokens | $1.40 | — |
| Output $ / M tokens | $4.40 | — |
| Results tracked | 41 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
GLM-5.1: 48.7 (#55), Llama 2-70B: 31.4 (#286)
| Benchmark | GLM-5.1 | Llama 2-70B |
|---|---|---|
| LMArena Coding | 1485 | 1079 |
| SWE-bench Verified | 74.2% | — |
| LMArena WebDev | 1508 | — |
| SciCode | 43.8% | — |
| WeirdML | 57.1% | — |
| ALE-Bench | 887.1 | — |
Agentic & Tool Use Not comparable
GLM-5.1: 24.9 (#113), Llama 2-70B: —
| Benchmark | GLM-5.1 | Llama 2-70B |
|---|---|---|
| APEX-Agents | 40.9% | — |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |
Reasoning GLM-5.1 leads
GLM-5.1: 39.1 (#60), Llama 2-70B: 14.4 (#325)
| Benchmark | GLM-5.1 | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 1472 | 1073 |
| Epoch Capabilities Index | 149.84 | 113.79 |
| SimpleBench | 55.1% | — |
| NYT Connections (extended) | 77.7% | — |
| CritPt | 4.6% | — |
| Chess Puzzles | 19% | — |
| Thematic Generalization | 69.8% | — |
| DTBench | — | 41.6% |
| 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-5.1 leads
GLM-5.1: 49.7 (#60), Llama 2-70B: 8.1 (#326)
| Benchmark | GLM-5.1 | Llama 2-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.3% | 0% |
| LMArena Math | 1473 | 1091 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| MATH Level 5 | — | 3.3% |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
| GSM8K | — | 69.6% |
Knowledge GLM-5.1 leads
GLM-5.1: 54.9 (#50), Llama 2-70B: 7.4 (#310)
| Benchmark | GLM-5.1 | Llama 2-70B |
|---|---|---|
| GPQA Diamond | 89.9% | 26.3% |
| LMArena Expert | 1476 | 1039 |
| SimpleQA Verified | 34% | — |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| MMLU | — | 69.9% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |
Multilingual GLM-5.1 leads
GLM-5.1: 55.0 (#36), Llama 2-70B: 27.7 (#274)
| Benchmark | GLM-5.1 | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 1447 | 1045 |
| LMArena Chinese | 1515 | 995 |
| LMArena French | 1474 | 1090 |
| LMArena German | 1465 | 1041 |
| LMArena Japanese | 1434 | 927 |
| LMArena Korean | 1418 | 964 |
| LMArena Russian | 1454 | 1083 |
| LMArena Spanish | 1469 | 1143 |
Instruction Following GLM-5.1 leads
GLM-5.1: 76.3 (#42), Llama 2-70B: 54.9 (#278)
| Benchmark | GLM-5.1 | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 1451 | 1071 |
Long Context GLM-5.1 leads
GLM-5.1: 44.9 (#53), Llama 2-70B: 32.3 (#270)
| Benchmark | GLM-5.1 | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | 1466 | 1062 |
Writing & Preference GLM-5.1 leads
GLM-5.1: 66.9 (#31), Llama 2-70B: 32.3 (#279)
| Benchmark | GLM-5.1 | Llama 2-70B |
|---|---|---|
| LMArena Text | 1461 | 1115 |
| LMArena Creative Writing | 1453 | 1075 |
| LMArena Multi-Turn | 1472 | 1088 |
| EQ-Bench Creative Writing | 1592 | — |
Frequently asked questions
Is GLM-5.1 better than Llama 2-70B?
GLM-5.1 is the stronger model overall, scoring 47.8 to 24.4 on the Noometry Index.
Is GLM-5.1 or Llama 2-70B better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 31.4 in the Noometry coding category.
How many benchmarks do GLM-5.1 and Llama 2-70B share?
20 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Llama 2-70B has 35.