Model comparison
GLM-4.5 vs GPT-3.5-turbo
GLM-4.5 is the stronger model overall, scoring 41.4 to 23.1 on the Noometry Index.
Last verified . 19 shared benchmarks.
Summary
- They share 19 benchmarks with published results for both. GLM-4.5 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-4.5 leads 57.7 to 25.4.
- The biggest single-benchmark swing is WeirdML: 40.6% for GLM-4.5 and 3.5% for GPT-3.5-turbo.
- GPT-3.5-turbo is cheaper at $0.50 / $1.50 per million input/output tokens, against $0.60 / $2.20 for GLM-4.5.
- GLM-4.5 accepts more context: 131K tokens versus 16K.
- GLM-4.5 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.5 | GPT-3.5-turbo | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 41.4 | 23.1 |
| Released | 2025-07-27 | 2023-03-01 |
| Weights | Open | Proprietary |
| Context window | 131K | 16K |
| Max output | 98K | 4K |
| Input $ / M tokens | $0.60 | $0.50 |
| Output $ / M tokens | $2.20 | $1.50 |
| Results tracked | 27 | 44 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.5 leads
GLM-4.5: 41.1 (#121), GPT-3.5-turbo: 23.5 (#326)
| Benchmark | GLM-4.5 | GPT-3.5-turbo |
|---|---|---|
| WeirdML | 40.6% | 3.5% |
| LMArena Coding | 1434 | 1137 |
| SWE-bench Verified (bash only) | 54.2% | — |
| BigCodeBench Instruct | — | 39.1% |
| BigCodeBench Complete | — | 50.6% |
| ALE-Bench | 344.82 | — |
| AlgoTune | 1.52 | — |
| HumanEval+ | — | 70.7% |
| MBPP+ | — | 69.7% |
Agentic & Tool Use Not comparable
GLM-4.5: —, GPT-3.5-turbo: —
| Benchmark | GLM-4.5 | GPT-3.5-turbo |
|---|---|---|
| METR Time Horizons | — | 21.5% |
Reasoning GLM-4.5 leads
GLM-4.5: 27.7 (#99), GPT-3.5-turbo: 13.3 (#328)
| Benchmark | GLM-4.5 | GPT-3.5-turbo |
|---|---|---|
| LMArena Hard Prompts | 1430 | 1108 |
| Kagi LLM Benchmark | 57.9% | — |
| 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 | — | 118.48 |
| ForecastBench | — | 50.4 |
| WinoGrande | — | 81.6% |
Math GLM-4.5 leads
GLM-4.5: 36.3 (#119), GPT-3.5-turbo: 6.0 (#321)
| Benchmark | GLM-4.5 | GPT-3.5-turbo |
|---|---|---|
| LMArena Math | 1427 | 1142 |
| FrontierMath (Tiers 1-3) | — | 0% |
| OTIS Mock AIME 2024-2025 | — | 2.2% |
| MATH Level 5 | — | 15.9% |
| GSM8K | — | 57.8% |
Knowledge GLM-4.5 leads
GLM-4.5: 35.5 (#172), GPT-3.5-turbo: 10.0 (#298)
| Benchmark | GLM-4.5 | GPT-3.5-turbo |
|---|---|---|
| LMArena Expert | 1433 | 1070 |
| GPQA Diamond | — | 28% |
| Humanity's Last Exam | 8.3% | — |
| Confabulations | 11.3% | — |
| ARC (AI2) Challenge | — | 87.4% |
| BoolQ | — | 87% |
| MMLU | — | 71.4% |
| OpenBookQA | — | 86% |
| TriviaQA | — | 85.8% |
Multilingual GLM-4.5 leads
GLM-4.5: 53.0 (#74), GPT-3.5-turbo: 31.6 (#253)
| Benchmark | GLM-4.5 | GPT-3.5-turbo |
|---|---|---|
| LMArena Non-English | 1417 | 1108 |
| LMArena Chinese | 1465 | 1075 |
| LMArena French | 1423 | 1117 |
| LMArena German | 1406 | 1090 |
| LMArena Japanese | 1416 | 1043 |
| LMArena Korean | 1382 | 1019 |
| LMArena Russian | 1414 | 1123 |
| LMArena Spanish | 1454 | 1120 |
Instruction Following GLM-4.5 leads
GLM-4.5: 74.3 (#100), GPT-3.5-turbo: 58.1 (#257)
| Benchmark | GLM-4.5 | GPT-3.5-turbo |
|---|---|---|
| LMArena Instruction Following | 1405 | 1119 |
Long Context GLM-4.5 leads
GLM-4.5: 38.2 (#196), GPT-3.5-turbo: 34.0 (#249)
| Benchmark | GLM-4.5 | GPT-3.5-turbo |
|---|---|---|
| LMArena Longer Query | 1413 | 1121 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference GLM-4.5 leads
GLM-4.5: 57.7 (#121), GPT-3.5-turbo: 25.4 (#300)
| Benchmark | GLM-4.5 | GPT-3.5-turbo |
|---|---|---|
| LMArena Text | 1430 | 1125 |
| LMArena Creative Writing | 1395 | 1092 |
| EQ-Bench Creative Writing | 1343 | 451 |
| LMArena Multi-Turn | 1415 | 1117 |
| Short-Story Creative Writing | 73.4% | — |
Frequently asked questions
Is GLM-4.5 better than GPT-3.5-turbo?
GLM-4.5 is the stronger model overall, scoring 41.4 to 23.1 on the Noometry Index.
Which is cheaper, GLM-4.5 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-4.5 lists at $0.60 and $2.20.
Is GLM-4.5 or GPT-3.5-turbo better for coding?
GLM-4.5 scores higher on coding benchmarks: 41.1 versus 23.5 in the Noometry coding category.
Which has the bigger context window?
GLM-4.5 does, with 131K tokens against 16K.
How many benchmarks do GLM-4.5 and GPT-3.5-turbo share?
19 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and GPT-3.5-turbo has 44.