Model comparison
GLM-4.6 vs GPT-3.5-turbo
GLM-4.6 is the stronger model overall, scoring 41.4 to 23.2 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. GLM-4.6 scores higher in 8 categories and GPT-3.5-turbo in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.6 leads 61.1 to 25.3.
- GPT-3.5-turbo is cheaper at $0.50 / $1.50 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
- GLM-4.6 accepts more context: 205K tokens versus 16K.
- GLM-4.6 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.6 | GPT-3.5-turbo | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 41.4 | 23.2 |
| Released | 2025-09-30 | 2023-03-01 |
| Weights | Open | Proprietary |
| Context window | 205K | 16K |
| Max output | 131K | 4K |
| Input $ / M tokens | $0.60 | $0.50 |
| Output $ / M tokens | $2.20 | $1.50 |
| Results tracked | 29 | 44 |
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), GPT-3.5-turbo: 23.9 (#331)
| Benchmark | GLM-4.6 | GPT-3.5-turbo |
|---|---|---|
| LMArena Coding | 1449 | 1136 |
| SWE-bench Verified (bash only) | 55.4% | — |
| LMArena WebDev | 1340 | — |
| SciCode | 38.4% | — |
| WeirdML | — | 3.5% |
| BigCodeBench Instruct | — | 39.1% |
| BigCodeBench Complete | — | 50.6% |
| ALE-Bench | 340.82 | — |
| HumanEval+ | — | 70.7% |
| MBPP+ | — | 69.7% |
Agentic & Tool Use Not comparable
GLM-4.6: 32.3 (#66), GPT-3.5-turbo: —
| Benchmark | GLM-4.6 | GPT-3.5-turbo |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| METR Time Horizons | — | 21.5% |
Reasoning GLM-4.6 leads
GLM-4.6: 23.7 (#172), GPT-3.5-turbo: 13.8 (#332)
| Benchmark | GLM-4.6 | GPT-3.5-turbo |
|---|---|---|
| LMArena Hard Prompts | 1440 | 1108 |
| Kagi LLM Benchmark | 47.4% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | — | 0% |
| Mystery Game Puzzles | — | 3% |
| DTBench | — | 48.5% |
| LMCA | — | 9.7% |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 61.6% |
| CommonsenseQA 2.0 | — | 57% |
| Epoch Capabilities Index | — | 118.55 |
| ForecastBench | — | 50.4 |
| WinoGrande | — | 81.6% |
Math GLM-4.6 leads
GLM-4.6: 39.1 (#111), GPT-3.5-turbo: 6.3 (#327)
| Benchmark | GLM-4.6 | GPT-3.5-turbo |
|---|---|---|
| LMArena Math | 1432 | 1142 |
| FrontierMath (Tiers 1-3) | — | 0% |
| OTIS Mock AIME 2024-2025 | — | 2.2% |
| MATH Level 5 | — | 15.9% |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
| GSM8K | — | 57.8% |
Knowledge GLM-4.6 leads
GLM-4.6: 40.2 (#124), GPT-3.5-turbo: 10.0 (#303)
| Benchmark | GLM-4.6 | GPT-3.5-turbo |
|---|---|---|
| LMArena Expert | 1431 | 1070 |
| GPQA Diamond | — | 28% |
| Vectara Hallucination Rate | 9.5% | — |
| ARC (AI2) Challenge | — | 87.4% |
| BoolQ | — | 87% |
| MMLU | — | 71.4% |
| OpenBookQA | — | 86% |
| TriviaQA | — | 85.8% |
Multilingual GLM-4.6 leads
GLM-4.6: 53.5 (#66), GPT-3.5-turbo: 31.5 (#258)
| Benchmark | GLM-4.6 | GPT-3.5-turbo |
|---|---|---|
| LMArena Non-English | 1426 | 1108 |
| LMArena Chinese | 1499 | 1075 |
| LMArena French | 1459 | 1118 |
| LMArena German | 1447 | 1090 |
| LMArena Japanese | 1393 | 1043 |
| LMArena Korean | 1400 | 1019 |
| LMArena Russian | 1419 | 1123 |
| LMArena Spanish | 1436 | 1121 |
Instruction Following GLM-4.6 leads
GLM-4.6: 74.3 (#98), GPT-3.5-turbo: 57.9 (#262)
| Benchmark | GLM-4.6 | GPT-3.5-turbo |
|---|---|---|
| LMArena Instruction Following | 1410 | 1119 |
Long Context GLM-4.6 leads
GLM-4.6: 43.4 (#94), GPT-3.5-turbo: 34.0 (#254)
| Benchmark | GLM-4.6 | GPT-3.5-turbo |
|---|---|---|
| LMArena Longer Query | 1422 | 1121 |
Writing & Preference GLM-4.6 leads
GLM-4.6: 61.1 (#90), GPT-3.5-turbo: 25.3 (#305)
| Benchmark | GLM-4.6 | GPT-3.5-turbo |
|---|---|---|
| LMArena Text | 1440 | 1125 |
| LMArena Creative Writing | 1411 | 1092 |
| EQ-Bench Creative Writing | 1411 | 451 |
| LMArena Multi-Turn | 1427 | 1117 |
Frequently asked questions
Is GLM-4.6 better than GPT-3.5-turbo?
GLM-4.6 is the stronger model overall, scoring 41.4 to 23.2 on the Noometry Index.
Which is cheaper, GLM-4.6 or GPT-3.5-turbo?
GPT-3.5-turbo is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.
Is GLM-4.6 or GPT-3.5-turbo better for coding?
GLM-4.6 scores higher on coding benchmarks: 40.1 versus 23.9 in the Noometry coding category.
Which has the bigger context window?
GLM-4.6 does, with 205K tokens against 16K.
How many benchmarks do GLM-4.6 and GPT-3.5-turbo share?
18 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and GPT-3.5-turbo has 44.