Model comparison
GLM-5.1 vs GPT-3.5-turbo
GLM-5.1 is the stronger model overall, scoring 47.8 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-5.1's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. GLM-5.1 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-5.1 leads 54.9 to 10.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for GLM-5.1 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-5.1.
- GLM-5.1 accepts more context: 200K tokens versus 16K.
- GLM-5.1 has downloadable open weights; the other is API-only.
Side by side
| GLM-5.1 | GPT-3.5-turbo | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 47.8 | 23.2 |
| Released | 2026-04-07 | 2023-03-01 |
| Weights | Open | Proprietary |
| Context window | 200K | 16K |
| Max output | 131K | 4K |
| Input $ / M tokens | $1.40 | $0.50 |
| Output $ / M tokens | $4.40 | $1.50 |
| Results tracked | 41 | 44 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
GLM-5.1: 48.7 (#55), GPT-3.5-turbo: 23.9 (#331)
| Benchmark | GLM-5.1 | GPT-3.5-turbo |
|---|---|---|
| WeirdML | 57.1% | 3.5% |
| LMArena Coding | 1485 | 1136 |
| SWE-bench Verified | 74.2% | — |
| LMArena WebDev | 1508 | — |
| SciCode | 43.8% | — |
| BigCodeBench Instruct | — | 39.1% |
| BigCodeBench Complete | — | 50.6% |
| ALE-Bench | 887.1 | — |
| HumanEval+ | — | 70.7% |
| MBPP+ | — | 69.7% |
Agentic & Tool Use Not comparable
GLM-5.1: 24.9 (#113), GPT-3.5-turbo: —
| Benchmark | GLM-5.1 | GPT-3.5-turbo |
|---|---|---|
| APEX-Agents | 40.9% | — |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| METR Time Horizons | — | 21.5% |
| Vending-Bench 2 | 5,634 | — |
Reasoning GLM-5.1 leads
GLM-5.1: 39.1 (#60), GPT-3.5-turbo: 13.8 (#332)
| Benchmark | GLM-5.1 | GPT-3.5-turbo |
|---|---|---|
| Chess Puzzles | 19% | 0% |
| LMArena Hard Prompts | 1472 | 1108 |
| Epoch Capabilities Index | 149.84 | 118.55 |
| SimpleBench | 55.1% | — |
| NYT Connections (extended) | 77.7% | — |
| CritPt | 4.6% | — |
| Thematic Generalization | 69.8% | — |
| Mystery Game Puzzles | — | 3% |
| DTBench | — | 48.5% |
| LMCA | — | 9.7% |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 61.6% |
| CommonsenseQA 2.0 | — | 57% |
| ForecastBench | — | 50.4 |
| WinoGrande | — | 81.6% |
Math GLM-5.1 leads
GLM-5.1: 49.7 (#60), GPT-3.5-turbo: 6.3 (#327)
| Benchmark | GLM-5.1 | GPT-3.5-turbo |
|---|---|---|
| FrontierMath (Tiers 1-3) | 36.8% | 0% |
| OTIS Mock AIME 2024-2025 | 93.3% | 2.2% |
| LMArena Math | 1473 | 1142 |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| MATH Level 5 | — | 15.9% |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
| GSM8K | — | 57.8% |
Knowledge GLM-5.1 leads
GLM-5.1: 54.9 (#50), GPT-3.5-turbo: 10.0 (#303)
| Benchmark | GLM-5.1 | GPT-3.5-turbo |
|---|---|---|
| GPQA Diamond | 89.9% | 28% |
| LMArena Expert | 1476 | 1070 |
| SimpleQA Verified | 34% | — |
| ARC (AI2) Challenge | — | 87.4% |
| BoolQ | — | 87% |
| MMLU | — | 71.4% |
| OpenBookQA | — | 86% |
| TriviaQA | — | 85.8% |
Multilingual GLM-5.1 leads
GLM-5.1: 55.0 (#36), GPT-3.5-turbo: 31.5 (#258)
| Benchmark | GLM-5.1 | GPT-3.5-turbo |
|---|---|---|
| LMArena Non-English | 1447 | 1108 |
| LMArena Chinese | 1515 | 1075 |
| LMArena French | 1474 | 1118 |
| LMArena German | 1465 | 1090 |
| LMArena Japanese | 1434 | 1043 |
| LMArena Korean | 1418 | 1019 |
| LMArena Russian | 1454 | 1123 |
| LMArena Spanish | 1469 | 1121 |
Instruction Following GLM-5.1 leads
GLM-5.1: 76.3 (#42), GPT-3.5-turbo: 57.9 (#262)
| Benchmark | GLM-5.1 | GPT-3.5-turbo |
|---|---|---|
| LMArena Instruction Following | 1451 | 1119 |
Long Context GLM-5.1 leads
GLM-5.1: 44.9 (#53), GPT-3.5-turbo: 34.0 (#254)
| Benchmark | GLM-5.1 | GPT-3.5-turbo |
|---|---|---|
| LMArena Longer Query | 1466 | 1121 |
Writing & Preference GLM-5.1 leads
GLM-5.1: 66.9 (#31), GPT-3.5-turbo: 25.3 (#305)
| Benchmark | GLM-5.1 | GPT-3.5-turbo |
|---|---|---|
| LMArena Text | 1461 | 1125 |
| LMArena Creative Writing | 1453 | 1092 |
| EQ-Bench Creative Writing | 1592 | 451 |
| LMArena Multi-Turn | 1472 | 1117 |
Frequently asked questions
Is GLM-5.1 better than GPT-3.5-turbo?
GLM-5.1 is the stronger model overall, scoring 47.8 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-5.1's lead doesn't matter for your workload.
Which is cheaper, GLM-5.1 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-5.1 lists at $1.40 and $4.40.
Is GLM-5.1 or GPT-3.5-turbo better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 23.9 in the Noometry coding category.
Which has the bigger context window?
GLM-5.1 does, with 200K tokens against 16K.
How many benchmarks do GLM-5.1 and GPT-3.5-turbo share?
24 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and GPT-3.5-turbo has 44.