Model comparison
GLM-5.1 vs Llama 3.2 3B
GLM-5.1 is the stronger model overall, scoring 47.8 to 28.9 on the Noometry Index. Llama 3.2 3B costs 18× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
MetaSummary
- They share 14 benchmarks with published results for both. GLM-5.1 scores higher in 9 categories and Llama 3.2 3B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5.1 leads 66.9 to 24.7.
- Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- GLM-5.1 accepts more context: 200K tokens versus 131K.
Side by side
| GLM-5.1 | Llama 3.2 3B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 47.8 | 28.9 |
| Released | 2026-04-07 | 2024-09-24 |
| Weights | Open | Open |
| Context window | 200K | 131K |
| Max output | 131K | 118K |
| Input $ / M tokens | $1.40 | $0.05 |
| Output $ / M tokens | $4.40 | $0.33 |
| Results tracked | 41 | 18 |
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 3.2 3B: 27.6 (#319)
| Benchmark | GLM-5.1 | Llama 3.2 3B |
|---|---|---|
| LMArena Coding | 1485 | 1098 |
| SWE-bench Verified | 74.2% | — |
| LMArena WebDev | 1508 | — |
| SciCode | 43.8% | — |
| WeirdML | 57.1% | — |
| BigCodeBench Instruct | — | 23.4% |
| BigCodeBench Complete | — | 28.3% |
| ALE-Bench | 887.1 | — |
Agentic & Tool Use GLM-5.1 leads
GLM-5.1: 24.9 (#113), Llama 3.2 3B: 20.1 (#143)
| Benchmark | GLM-5.1 | Llama 3.2 3B |
|---|---|---|
| APEX-Agents | 40.9% | — |
| Berkeley Function Calling Leaderboard | — | 21.9% |
| BALROG | — | 10.1% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |
Reasoning GLM-5.1 leads
GLM-5.1: 39.1 (#60), Llama 3.2 3B: 21.0 (#228)
| Benchmark | GLM-5.1 | Llama 3.2 3B |
|---|---|---|
| LMArena Hard Prompts | 1472 | 1095 |
| SimpleBench | 55.1% | — |
| NYT Connections (extended) | 77.7% | — |
| CritPt | 4.6% | — |
| Chess Puzzles | 19% | — |
| Thematic Generalization | 69.8% | — |
| Epoch Capabilities Index | 149.84 | — |
Math GLM-5.1 leads
GLM-5.1: 49.7 (#60), Llama 3.2 3B: 32.4 (#214)
| Benchmark | GLM-5.1 | Llama 3.2 3B |
|---|---|---|
| LMArena Math | 1473 | 1126 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |
| ProofBench | 22.2% | — |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GLM-5.1 leads
GLM-5.1: 54.9 (#50), Llama 3.2 3B: 29.7 (#235)
| Benchmark | GLM-5.1 | Llama 3.2 3B |
|---|---|---|
| LMArena Expert | 1476 | 1090 |
| GPQA Diamond | 89.9% | — |
| SimpleQA Verified | 34% | — |
Multilingual GLM-5.1 leads
GLM-5.1: 55.0 (#36), Llama 3.2 3B: 26.2 (#281)
| Benchmark | GLM-5.1 | Llama 3.2 3B |
|---|---|---|
| LMArena Non-English | 1447 | 1019 |
| LMArena Chinese | 1515 | 1017 |
| LMArena German | 1465 | 1056 |
| LMArena Russian | 1454 | 949 |
| LMArena French | 1474 | — |
| LMArena Japanese | 1434 | — |
| LMArena Korean | 1418 | — |
| LMArena Spanish | 1469 | — |
Instruction Following GLM-5.1 leads
GLM-5.1: 76.3 (#42), Llama 3.2 3B: 56.0 (#275)
| Benchmark | GLM-5.1 | Llama 3.2 3B |
|---|---|---|
| LMArena Instruction Following | 1451 | 1089 |
Long Context GLM-5.1 leads
GLM-5.1: 44.9 (#53), Llama 3.2 3B: 33.4 (#261)
| Benchmark | GLM-5.1 | Llama 3.2 3B |
|---|---|---|
| LMArena Longer Query | 1466 | 1100 |
Writing & Preference GLM-5.1 leads
GLM-5.1: 66.9 (#31), Llama 3.2 3B: 24.7 (#307)
| Benchmark | GLM-5.1 | Llama 3.2 3B |
|---|---|---|
| LMArena Text | 1461 | 1110 |
| LMArena Creative Writing | 1453 | 1094 |
| EQ-Bench Creative Writing | 1592 | 595 |
| LMArena Multi-Turn | 1472 | 1105 |
Frequently asked questions
Is GLM-5.1 better than Llama 3.2 3B?
GLM-5.1 is the stronger model overall, scoring 47.8 to 28.9 on the Noometry Index. Llama 3.2 3B costs 18× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Which is cheaper, GLM-5.1 or Llama 3.2 3B?
Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.
Is GLM-5.1 or Llama 3.2 3B better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 27.6 in the Noometry coding category.
Which has the bigger context window?
GLM-5.1 does, with 200K tokens against 131K.
How many benchmarks do GLM-5.1 and Llama 3.2 3B share?
14 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Llama 3.2 3B has 18.