Model comparison
GLM-4.6 vs Llama-3.3-70B-Instruct
GLM-4.6 is the stronger model overall, scoring 41.4 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct costs 6.5× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
MetaSummary
- They share 21 benchmarks with published results for both. GLM-4.6 scores higher in 9 categories and Llama-3.3-70B-Instruct in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.6 leads 39.1 to 15.3.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 72.4% for GLM-4.6 and 31.9% for Llama-3.3-70B-Instruct.
- Llama-3.3-70B-Instruct is cheaper at $0.10 / $0.32 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
- GLM-4.6 accepts more context: 205K tokens versus 128K.
Side by side
| GLM-4.6 | Llama-3.3-70B-Instruct | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 41.4 | 30.6 |
| Released | 2025-09-30 | 2024-12-06 |
| Weights | Open | Open |
| Context window | 205K | 128K |
| Max output | 131K | 4K |
| Input $ / M tokens | $0.60 | $0.10 |
| Output $ / M tokens | $2.20 | $0.32 |
| Results tracked | 29 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6 leads
GLM-4.6: 40.1 (#148), Llama-3.3-70B-Instruct: 31.0 (#290)
| Benchmark | GLM-4.6 | Llama-3.3-70B-Instruct |
|---|---|---|
| SciCode | 38.4% | 26% |
| LMArena Coding | 1449 | 1268 |
| SWE-bench Verified (bash only) | 55.4% | — |
| LMArena WebDev | 1340 | — |
| WeirdML | — | 14.4% |
| BigCodeBench Instruct | — | 46.9% |
| LiveBench Coding | — | 36.6% |
| BigCodeBench Complete | — | 57.5% |
| ALE-Bench | 340.82 | — |
Agentic & Tool Use GLM-4.6 leads
GLM-4.6: 32.3 (#66), Llama-3.3-70B-Instruct: 25.8 (#105)
| Benchmark | GLM-4.6 | Llama-3.3-70B-Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 72.4% | 31.9% |
| Terminal-Bench | 24.5% | — |
| BALROG | — | 23% |
Reasoning GLM-4.6 leads
GLM-4.6: 23.7 (#172), Llama-3.3-70B-Instruct: 14.1 (#327)
| Benchmark | GLM-4.6 | Llama-3.3-70B-Instruct |
|---|---|---|
| CritPt | 1.1% | 0% |
| LMArena Hard Prompts | 1440 | 1257 |
| SimpleBench | — | 19.9% |
| Kagi LLM Benchmark | 47.4% | — |
| LiveBench Reasoning | — | 50.8% |
| DTBench | — | 59.5% |
| LiveBench Data Analysis | — | 49.5% |
| LMCA | — | 17.5% |
| Epoch Capabilities Index | — | 127.33 |
| ForecastBench | — | 58.6 |
| LiveBench | — | 50.2% |
Math GLM-4.6 leads
GLM-4.6: 39.1 (#111), Llama-3.3-70B-Instruct: 15.3 (#298)
| Benchmark | GLM-4.6 | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Math | 1432 | 1267 |
| OTIS Mock AIME 2024-2025 | — | 5.1% |
| LiveBench Math | — | 42.2% |
| MATH Level 5 | — | 41.6% |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-4.6 leads
GLM-4.6: 40.2 (#124), Llama-3.3-70B-Instruct: 30.6 (#226)
| Benchmark | GLM-4.6 | Llama-3.3-70B-Instruct |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | 4.1% |
| LMArena Expert | 1431 | 1225 |
| GPQA Diamond | — | 47.4% |
| Confabulations | — | 22.8% |
| MMLU | — | 86.3% |
Multilingual GLM-4.6 leads
GLM-4.6: 53.5 (#66), Llama-3.3-70B-Instruct: 39.9 (#220)
| Benchmark | GLM-4.6 | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Non-English | 1426 | 1236 |
| LMArena Chinese | 1499 | 1217 |
| LMArena French | 1459 | 1281 |
| LMArena German | 1447 | 1251 |
| LMArena Japanese | 1393 | 1150 |
| LMArena Korean | 1400 | 1143 |
| LMArena Russian | 1419 | 1252 |
| LMArena Spanish | 1436 | 1270 |
Instruction Following GLM-4.6 leads
GLM-4.6: 74.3 (#98), Llama-3.3-70B-Instruct: 71.1 (#157)
| Benchmark | GLM-4.6 | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Instruction Following | 1410 | 1242 |
| LiveBench Instruction Following | — | 82.7% |
Long Context GLM-4.6 leads
GLM-4.6: 43.4 (#94), Llama-3.3-70B-Instruct: 26.4 (#295)
| Benchmark | GLM-4.6 | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Longer Query | 1422 | 1256 |
| Fiction.LiveBench | — | 33.3% |
Writing & Preference GLM-4.6 leads
GLM-4.6: 61.1 (#90), Llama-3.3-70B-Instruct: 47.6 (#207)
| Benchmark | GLM-4.6 | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Text | 1440 | 1274 |
| LMArena Creative Writing | 1411 | 1250 |
| LMArena Multi-Turn | 1427 | 1280 |
| EQ-Bench Creative Writing | 1411 | — |
| LiveBench Language | — | 39.2% |
Frequently asked questions
Is GLM-4.6 better than Llama-3.3-70B-Instruct?
GLM-4.6 is the stronger model overall, scoring 41.4 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct costs 6.5× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.
Which is cheaper, GLM-4.6 or Llama-3.3-70B-Instruct?
Llama-3.3-70B-Instruct is cheaper. It lists at $0.10 per million input tokens and $0.32 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.
Is GLM-4.6 or Llama-3.3-70B-Instruct better for coding?
GLM-4.6 scores higher on coding benchmarks: 40.1 versus 31.0 in the Noometry coding category.
Which has the bigger context window?
GLM-4.6 does, with 205K tokens against 128K.
How many benchmarks do GLM-4.6 and Llama-3.3-70B-Instruct share?
21 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Llama-3.3-70B-Instruct has 43.