Model comparison
GLM-5.2 vs GPT-3.5-turbo
GLM-5.2 is the stronger model overall, scoring 51.1 to 23.2 on the Noometry Index. GPT-3.5-turbo costs 2.9× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. GLM-5.2 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 math, where GLM-5.2 leads 55.7 to 6.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 86.4% for GLM-5.2 and 2.2% for GPT-3.5-turbo.
- GPT-3.5-turbo is cheaper at $0.50 / $1.50 per million input/output tokens, against $1.40 / $4.40 for GLM-5.2.
- GLM-5.2 accepts more context: 1M tokens versus 16K.
- GLM-5.2 has downloadable open weights; the other is API-only.
Side by side
| GLM-5.2 | GPT-3.5-turbo | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 51.1 | 23.2 |
| Released | 2026-06-13 | 2023-03-01 |
| Weights | Open | Proprietary |
| Context window | 1M | 16K |
| Max output | 131K | 4K |
| Input $ / M tokens | $1.40 | $0.50 |
| Output $ / M tokens | $4.40 | $1.50 |
| Results tracked | 51 | 44 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.2 leads
GLM-5.2: 51.3 (#41), GPT-3.5-turbo: 23.9 (#331)
| Benchmark | GLM-5.2 | GPT-3.5-turbo |
|---|---|---|
| WeirdML | 70.1% | 3.5% |
| LMArena Coding | 1485 | 1136 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| LMArena WebDev | 1603 | — |
| SciCode | 50.5% | — |
| BigCodeBench Instruct | — | 39.1% |
| BigCodeBench Complete | — | 50.6% |
| ALE-Bench | 1,047 | — |
| HumanEval+ | — | 70.7% |
| MBPP+ | — | 69.7% |
Agentic & Tool Use Not comparable
GLM-5.2: 32.4 (#63), GPT-3.5-turbo: —
| Benchmark | GLM-5.2 | GPT-3.5-turbo |
|---|---|---|
| APEX-Agents | 45.2% | — |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
| METR Time Horizons | — | 21.5% |
| Vending-Bench 2 | 8,314 | — |
Reasoning GLM-5.2 leads
GLM-5.2: 42.3 (#52), GPT-3.5-turbo: 13.8 (#332)
| Benchmark | GLM-5.2 | GPT-3.5-turbo |
|---|---|---|
| Chess Puzzles | 21% | 0% |
| LMArena Hard Prompts | 1480 | 1108 |
| Mystery Game Puzzles | 19% | 3% |
| DTBench | 93.6% | 48.5% |
| LMCA | 45.8% | 9.7% |
| Epoch Capabilities Index | 151.78 | 118.55 |
| ARC-AGI-2 | 22.8% | — |
| SimpleBench | 58.8% | — |
| Kagi LLM Benchmark | 62.6% | — |
| NYT Connections (extended) | 74.3% | — |
| ARC-AGI-1 | 77% | — |
| CritPt | 20.9% | — |
| EBR-Bench | 9.5% | — |
| Surface Evolver Bench | 55.6% | — |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 61.6% |
| CommonsenseQA 2.0 | — | 57% |
| ForecastBench | — | 50.4 |
| WinoGrande | — | 81.6% |
Math GLM-5.2 leads
GLM-5.2: 55.7 (#43), GPT-3.5-turbo: 6.3 (#327)
| Benchmark | GLM-5.2 | GPT-3.5-turbo |
|---|---|---|
| FrontierMath (Tiers 1-3) | 59.2% | 0% |
| OTIS Mock AIME 2024-2025 | 86.4% | 2.2% |
| LMArena Math | 1482 | 1142 |
| FrontierMath Tier 4 | 29.3% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| ProofBench | 35% | — |
| MATH Level 5 | — | 15.9% |
| GSM8K | — | 57.8% |
Knowledge GLM-5.2 leads
GLM-5.2: 57.1 (#40), GPT-3.5-turbo: 10.0 (#303)
| Benchmark | GLM-5.2 | GPT-3.5-turbo |
|---|---|---|
| GPQA Diamond | 91.9% | 28% |
| LMArena Expert | 1486 | 1070 |
| SimpleQA Verified | 34.2% | — |
| ARC (AI2) Challenge | — | 87.4% |
| BoolQ | — | 87% |
| MMLU | — | 71.4% |
| OpenBookQA | — | 86% |
| TriviaQA | — | 85.8% |
Multilingual GLM-5.2 leads
GLM-5.2: 55.8 (#26), GPT-3.5-turbo: 31.5 (#258)
| Benchmark | GLM-5.2 | GPT-3.5-turbo |
|---|---|---|
| LMArena Non-English | 1459 | 1108 |
| LMArena Chinese | 1519 | 1075 |
| LMArena French | 1479 | 1118 |
| LMArena German | 1468 | 1090 |
| LMArena Japanese | 1451 | 1043 |
| LMArena Korean | 1445 | 1019 |
| LMArena Russian | 1466 | 1123 |
| LMArena Spanish | 1477 | 1121 |
Instruction Following GLM-5.2 leads
GLM-5.2: 76.9 (#34), GPT-3.5-turbo: 57.9 (#262)
| Benchmark | GLM-5.2 | GPT-3.5-turbo |
|---|---|---|
| LMArena Instruction Following | 1465 | 1119 |
Long Context GLM-5.2 leads
GLM-5.2: 45.3 (#43), GPT-3.5-turbo: 34.0 (#254)
| Benchmark | GLM-5.2 | GPT-3.5-turbo |
|---|---|---|
| LMArena Longer Query | 1479 | 1121 |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.4 (#21), GPT-3.5-turbo: 25.3 (#305)
| Benchmark | GLM-5.2 | GPT-3.5-turbo |
|---|---|---|
| LMArena Text | 1470 | 1125 |
| LMArena Creative Writing | 1462 | 1092 |
| EQ-Bench Creative Writing | 1757 | 451 |
| LMArena Multi-Turn | 1469 | 1117 |
| EQ-Bench 4 | 1222 | — |
Frequently asked questions
Is GLM-5.2 better than GPT-3.5-turbo?
GLM-5.2 is the stronger model overall, scoring 51.1 to 23.2 on the Noometry Index. GPT-3.5-turbo costs 2.9× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.
Which is cheaper, GLM-5.2 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-5.2 lists at $1.40 and $4.40.
Is GLM-5.2 or GPT-3.5-turbo better for coding?
GLM-5.2 scores higher on coding benchmarks: 51.3 versus 23.9 in the Noometry coding category.
Which has the bigger context window?
GLM-5.2 does, with 1M tokens against 16K.
How many benchmarks do GLM-5.2 and GPT-3.5-turbo share?
27 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and GPT-3.5-turbo has 44.