Model comparison
GLM-4.5 vs Llama 3.1-8B
GLM-4.5 is the stronger model overall, scoring 42.0 to 23.0 on the Noometry Index. Llama 3.1-8B costs 17× less per token, which makes it the better buy when GLM-4.5's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
MetaSummary
- They share 19 benchmarks with published results for both. GLM-4.5 scores higher in 8 categories and Llama 3.1-8B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.5 leads 39.0 to 10.2.
- The biggest single-benchmark swing is WeirdML: 40.6% for GLM-4.5 and 1.7% for Llama 3.1-8B.
- Llama 3.1-8B is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.60 / $2.20 for GLM-4.5.
- GLM-4.5 accepts more context: 131K tokens versus 128K.
Side by side
| GLM-4.5 | Llama 3.1-8B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 42.0 | 23.0 |
| Released | 2025-07-27 | 2024-07-23 |
| Weights | Open | Open |
| Context window | 131K | 128K |
| Max output | 98K | 4K |
| Input $ / M tokens | $0.60 | $0.05 |
| Output $ / M tokens | $2.20 | $0.08 |
| Results tracked | 27 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.5 leads
GLM-4.5: 41.4 (#125), Llama 3.1-8B: 20.2 (#340)
| Benchmark | GLM-4.5 | Llama 3.1-8B |
|---|---|---|
| WeirdML | 40.6% | 1.7% |
| LMArena Coding | 1434 | 1195 |
| SWE-bench Verified (bash only) | 54.2% | — |
| SciCode | — | 13.2% |
| BigCodeBench Instruct | — | 32.8% |
| BigCodeBench Complete | — | 40.5% |
| ALE-Bench | 344.82 | — |
| AlgoTune | 1.52 | — |
| HumanEval+ | — | 62.8% |
| MBPP+ | — | 55.6% |
Agentic & Tool Use Not comparable
GLM-4.5: —, Llama 3.1-8B: 22.5 (#131)
| Benchmark | GLM-4.5 | Llama 3.1-8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 25.8% |
| BALROG | — | 15.1% |
Reasoning GLM-4.5 leads
GLM-4.5: 28.6 (#100), Llama 3.1-8B: 14.9 (#321)
| Benchmark | GLM-4.5 | Llama 3.1-8B |
|---|---|---|
| LMArena Hard Prompts | 1429 | 1175 |
| Kagi LLM Benchmark | 57.9% | — |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| DTBench | — | 50.9% |
| LMCA | — | 5.4% |
| Epoch Capabilities Index | — | 116.57 |
| PIQA | — | 81.2% |
Math GLM-4.5 leads
GLM-4.5: 39.0 (#116), Llama 3.1-8B: 10.2 (#317)
| Benchmark | GLM-4.5 | Llama 3.1-8B |
|---|---|---|
| LMArena Math | 1427 | 1179 |
| OTIS Mock AIME 2024-2025 | — | 1.7% |
| Omni-MATH | — | 13.7% |
| MATH Level 5 | — | 22.9% |
| GSM8K | — | 82.4% |
Knowledge GLM-4.5 leads
GLM-4.5: 35.9 (#179), Llama 3.1-8B: 8.0 (#307)
| Benchmark | GLM-4.5 | Llama 3.1-8B |
|---|---|---|
| LMArena Expert | 1433 | 1144 |
| GPQA Diamond | — | 27% |
| Humanity's Last Exam | 8.3% | — |
| MMLU-Pro | — | 40.6% |
| Confabulations | 11.3% | — |
| GPQA (HELM) | — | 24.7% |
| BoolQ | — | 82.8% |
| MMLU | — | 56.1% |
Multilingual GLM-4.5 leads
GLM-4.5: 52.8 (#77), Llama 3.1-8B: 34.0 (#249)
| Benchmark | GLM-4.5 | Llama 3.1-8B |
|---|---|---|
| LMArena Non-English | 1417 | 1148 |
| LMArena Chinese | 1465 | 1151 |
| LMArena French | 1418 | 1177 |
| LMArena German | 1407 | 1144 |
| LMArena Japanese | 1415 | 1061 |
| LMArena Korean | 1380 | 1053 |
| LMArena Russian | 1414 | 1158 |
| LMArena Spanish | 1454 | 1169 |
Instruction Following GLM-4.5 leads
GLM-4.5: 74.1 (#104), Llama 3.1-8B: 58.9 (#258)
| Benchmark | GLM-4.5 | Llama 3.1-8B |
|---|---|---|
| LMArena Instruction Following | 1404 | 1159 |
| IFEval | — | 74.3% |
Long Context GLM-4.5 leads
GLM-4.5: 38.2 (#201), Llama 3.1-8B: 35.8 (#238)
| Benchmark | GLM-4.5 | Llama 3.1-8B |
|---|---|---|
| LMArena Longer Query | 1412 | 1182 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference GLM-4.5 leads
GLM-4.5: 57.5 (#127), Llama 3.1-8B: 29.7 (#290)
| Benchmark | GLM-4.5 | Llama 3.1-8B |
|---|---|---|
| LMArena Text | 1430 | 1187 |
| LMArena Creative Writing | 1395 | 1154 |
| EQ-Bench Creative Writing | 1343 | 713 |
| LMArena Multi-Turn | 1415 | 1172 |
| Short-Story Creative Writing | 73.4% | — |
| WildBench | — | 68.7% |
Frequently asked questions
Is GLM-4.5 better than Llama 3.1-8B?
GLM-4.5 is the stronger model overall, scoring 42.0 to 23.0 on the Noometry Index. Llama 3.1-8B costs 17× less per token, which makes it the better buy when GLM-4.5's lead doesn't matter for your workload.
Which is cheaper, GLM-4.5 or Llama 3.1-8B?
Llama 3.1-8B is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; GLM-4.5 lists at $0.60 and $2.20.
Is GLM-4.5 or Llama 3.1-8B better for coding?
GLM-4.5 scores higher on coding benchmarks: 41.4 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
GLM-4.5 does, with 131K tokens against 128K.
How many benchmarks do GLM-4.5 and Llama 3.1-8B share?
19 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Llama 3.1-8B has 43.