Model comparison
GLM-5.3-Flash vs GPT-3.5-turbo
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 23.2 on the Noometry Index.
Last verified . 23 shared benchmarks.
Summary
- They share 23 benchmarks with published results for both. GLM-5.3-Flash 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 knowledge, where GLM-5.3-Flash leads 58.4 to 10.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.9% for GLM-5.3-Flash and 2.2% for GPT-3.5-turbo.
- GLM-5.3-Flash is cheaper at $0.15 / $0.50 per million input/output tokens, against $0.50 / $1.50 for GPT-3.5-turbo.
- GLM-5.3-Flash accepts more context: 1M tokens versus 16K.
- GLM-5.3-Flash has downloadable open weights; the other is API-only.
Side by side
| GLM-5.3-Flash | GPT-3.5-turbo | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 51.8 | 23.2 |
| Released | 2026-08-20 | 2023-03-01 |
| Weights | Open | Proprietary |
| Context window | 1M | 16K |
| Max output | 131K | 4K |
| Input $ / M tokens | $0.15 | $0.50 |
| Output $ / M tokens | $0.50 | $1.50 |
| Results tracked | 40 | 44 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3-Flash leads
GLM-5.3-Flash: 53.1 (#31), GPT-3.5-turbo: 23.9 (#331)
| Benchmark | GLM-5.3-Flash | GPT-3.5-turbo |
|---|---|---|
| LMArena Coding | 1508 | 1136 |
| DeepSWE | 63.4% | — |
| FrontierCode | 31.8% | — |
| CursorBench | 36.8% | — |
| LMArena WebDev | 1609 | — |
| FrontierSWE | 18.1% | — |
| SciCode | 51.6% | — |
| WeirdML | — | 3.5% |
| BigCodeBench Instruct | — | 39.1% |
| BigCodeBench Complete | — | 50.6% |
| ALE-Bench | 303.55 | — |
| HumanEval+ | — | 70.7% |
| MBPP+ | — | 69.7% |
Agentic & Tool Use Not comparable
GLM-5.3-Flash: 34.2 (#47), GPT-3.5-turbo: —
| Benchmark | GLM-5.3-Flash | GPT-3.5-turbo |
|---|---|---|
| APEX-Agents | 52.8% | — |
| GDP.pdf | 14% | — |
| METR Time Horizons | — | 21.5% |
Reasoning GLM-5.3-Flash leads
GLM-5.3-Flash: 48.0 (#42), GPT-3.5-turbo: 13.8 (#332)
| Benchmark | GLM-5.3-Flash | GPT-3.5-turbo |
|---|---|---|
| Chess Puzzles | 14% | 0% |
| LMArena Hard Prompts | 1491 | 1108 |
| Mystery Game Puzzles | 8% | 3% |
| Epoch Capabilities Index | 151.88 | 118.55 |
| ARC-AGI-2 | 65.8% | — |
| ARC-AGI-1 | 91% | — |
| CritPt | 15.4% | — |
| DTBench | — | 48.5% |
| LMCA | — | 9.7% |
| Surface Evolver Bench | 52.5% | — |
| Adversarial NLI | — | 58.1% |
| Bench to the Future 3 | 0.15 | — |
| BIG-Bench Hard | — | 61.6% |
| CommonsenseQA 2.0 | — | 57% |
| ForecastBench | — | 50.4 |
| WinoGrande | — | 81.6% |
Math GLM-5.3-Flash leads
GLM-5.3-Flash: 53.3 (#47), GPT-3.5-turbo: 6.3 (#327)
| Benchmark | GLM-5.3-Flash | GPT-3.5-turbo |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.8% | 0% |
| OTIS Mock AIME 2024-2025 | 93.9% | 2.2% |
| LMArena Math | 1500 | 1142 |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 21% | — |
| MATH Level 5 | — | 15.9% |
| GSM8K | — | 57.8% |
Knowledge GLM-5.3-Flash leads
GLM-5.3-Flash: 58.4 (#36), GPT-3.5-turbo: 10.0 (#303)
| Benchmark | GLM-5.3-Flash | GPT-3.5-turbo |
|---|---|---|
| GPQA Diamond | 90.2% | 28% |
| LMArena Expert | 1513 | 1070 |
| ARC (AI2) Challenge | — | 87.4% |
| BoolQ | — | 87% |
| MMLU | — | 71.4% |
| OpenBookQA | — | 86% |
| TriviaQA | — | 85.8% |
Multimodal Not comparable
GLM-5.3-Flash: 42.8 (#27), GPT-3.5-turbo: —
| Benchmark | GLM-5.3-Flash | GPT-3.5-turbo |
|---|---|---|
| LMArena Vision | 1296 | — |
Multilingual GLM-5.3-Flash leads
GLM-5.3-Flash: 56.0 (#25), GPT-3.5-turbo: 31.5 (#258)
| Benchmark | GLM-5.3-Flash | GPT-3.5-turbo |
|---|---|---|
| LMArena Non-English | 1462 | 1108 |
| LMArena Chinese | 1527 | 1075 |
| LMArena French | 1496 | 1118 |
| LMArena German | 1470 | 1090 |
| LMArena Japanese | 1429 | 1043 |
| LMArena Korean | 1446 | 1019 |
| LMArena Russian | 1469 | 1123 |
| LMArena Spanish | 1471 | 1121 |
Instruction Following GLM-5.3-Flash leads
GLM-5.3-Flash: 77.5 (#20), GPT-3.5-turbo: 57.9 (#262)
| Benchmark | GLM-5.3-Flash | GPT-3.5-turbo |
|---|---|---|
| LMArena Instruction Following | 1478 | 1119 |
Long Context GLM-5.3-Flash leads
GLM-5.3-Flash: 45.4 (#39), GPT-3.5-turbo: 34.0 (#254)
| Benchmark | GLM-5.3-Flash | GPT-3.5-turbo |
|---|---|---|
| LMArena Longer Query | 1482 | 1121 |
Writing & Preference GLM-5.3-Flash leads
GLM-5.3-Flash: 65.3 (#50), GPT-3.5-turbo: 25.3 (#305)
| Benchmark | GLM-5.3-Flash | GPT-3.5-turbo |
|---|---|---|
| LMArena Text | 1471 | 1125 |
| LMArena Creative Writing | 1442 | 1092 |
| LMArena Multi-Turn | 1467 | 1117 |
| EQ-Bench Creative Writing | — | 451 |
Frequently asked questions
Is GLM-5.3-Flash better than GPT-3.5-turbo?
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 23.2 on the Noometry Index.
Which is cheaper, GLM-5.3-Flash or GPT-3.5-turbo?
GLM-5.3-Flash is cheaper. It lists at $0.15 per million input tokens and $0.50 per million output tokens; GPT-3.5-turbo lists at $0.50 and $1.50.
Is GLM-5.3-Flash or GPT-3.5-turbo better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.1 versus 23.9 in the Noometry coding category.
Which has the bigger context window?
GLM-5.3-Flash does, with 1M tokens against 16K.
How many benchmarks do GLM-5.3-Flash and GPT-3.5-turbo share?
23 benchmarks have published results for both models. GLM-5.3-Flash has 40 scored results on Noometry and GPT-3.5-turbo has 44.