Model comparison
GLM-5 vs GPT-4 Turbo
GLM-5 is the stronger model overall, scoring 46.1 to 30.5 on the Noometry Index.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. GLM-5 scores higher in 8 categories and GPT-4 Turbo in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5 leads 46.4 to 9.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 80% for GLM-5 and 6.7% for GPT-4 Turbo.
- GLM-5 is cheaper at $1 / $3.20 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- GLM-5 accepts more context: 205K tokens versus 128K.
- GLM-5 has downloadable open weights; the other is API-only.
Side by side
| GLM-5 | GPT-4 Turbo | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 46.1 | 30.5 |
| Released | 2026-02-11 | 2023-11-06 |
| Weights | Open | Proprietary |
| Context window | 205K | 128K |
| Max output | 131K | 4K |
| Input $ / M tokens | $1 | $10 |
| Output $ / M tokens | $3.20 | $30 |
| Results tracked | 45 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#52), GPT-4 Turbo: 33.8 (#249)
| Benchmark | GLM-5 | GPT-4 Turbo |
|---|---|---|
| WeirdML | 48.2% | 18% |
| LMArena Coding | 1461 | 1268 |
| SWE-bench Verified | 72.1% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| BigCodeBench Instruct | — | 48.2% |
| BigCodeBench Complete | — | 58.2% |
| ALE-Bench | 765.62 | — |
| HumanEval+ | — | 86.6% |
| MBPP+ | — | 73.3% |
Agentic & Tool Use Not comparable
GLM-5: 31.1 (#71), GPT-4 Turbo: —
| Benchmark | GLM-5 | GPT-4 Turbo |
|---|---|---|
| Terminal-Bench | 52.4% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
| METR Time Horizons | — | 36.7% |
| Vending-Bench 2 | 4,432 | — |
Reasoning GLM-5 leads
GLM-5: 27.6 (#116), GPT-4 Turbo: 15.3 (#317)
| Benchmark | GLM-5 | GPT-4 Turbo |
|---|---|---|
| SimpleBench | 53.2% | 25.1% |
| Chess Puzzles | 10% | 6% |
| LMArena Hard Prompts | 1452 | 1251 |
| Epoch Capabilities Index | 145.83 | 127.25 |
| ForecastBench | 61 | 59.4 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 74.8% | — |
| ARC-AGI-1 | 44.7% | — |
| DTBench | — | 61.6% |
| LMCA | — | 9.8% |
Math GLM-5 leads
GLM-5: 46.4 (#71), GPT-4 Turbo: 9.0 (#322)
| Benchmark | GLM-5 | GPT-4 Turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 6.7% |
| LMArena Math | 1440 | 1272 |
| FrontierMath (Tiers 1-3) | — | 0.7% |
| MathArena Final-Answer Competitions | 65.7% | — |
| MATH Level 5 | — | 46.7% |
| FrontierMath (Feb 2025 set) | 16.4% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-5 leads
GLM-5: 52.3 (#64), GPT-4 Turbo: 24.3 (#268)
| Benchmark | GLM-5 | GPT-4 Turbo |
|---|---|---|
| GPQA Diamond | 87.8% | 46.6% |
| LMArena Expert | 1454 | 1223 |
| Confabulations | — | 28.4% |
| Vectara Hallucination Rate | 10.1% | — |
| MMLU | — | 81.3% |
Multimodal Not comparable
GLM-5: —, GPT-4 Turbo: 30.6 (#110)
| Benchmark | GLM-5 | GPT-4 Turbo |
|---|---|---|
| LMArena Vision | — | 1090 |
Multilingual GLM-5 leads
GLM-5: 53.7 (#58), GPT-4 Turbo: 40.5 (#216)
| Benchmark | GLM-5 | GPT-4 Turbo |
|---|---|---|
| LMArena Non-English | 1430 | 1245 |
| LMArena Chinese | 1511 | 1242 |
| LMArena French | 1455 | 1276 |
| LMArena German | 1445 | 1259 |
| LMArena Japanese | 1416 | 1194 |
| LMArena Korean | 1423 | 1187 |
| LMArena Russian | 1436 | 1259 |
| LMArena Spanish | 1454 | 1260 |
Instruction Following GLM-5 leads
GLM-5: 75.2 (#67), GPT-4 Turbo: 65.8 (#216)
| Benchmark | GLM-5 | GPT-4 Turbo |
|---|---|---|
| LMArena Instruction Following | 1428 | 1249 |
Long Context GLM-5 leads
GLM-5: 44.7 (#60), GPT-4 Turbo: 38.0 (#206)
| Benchmark | GLM-5 | GPT-4 Turbo |
|---|---|---|
| LMArena Longer Query | 1446 | 1254 |
| CL-bench | 18.7% | — |
Writing & Preference GLM-5 leads
GLM-5: 66.0 (#38), GPT-4 Turbo: 47.7 (#206)
| Benchmark | GLM-5 | GPT-4 Turbo |
|---|---|---|
| LMArena Text | 1446 | 1272 |
| LMArena Creative Writing | 1439 | 1269 |
| LMArena Multi-Turn | 1456 | 1267 |
| EQ-Bench Creative Writing | 1601 | — |
Frequently asked questions
Is GLM-5 better than GPT-4 Turbo?
GLM-5 is the stronger model overall, scoring 46.1 to 30.5 on the Noometry Index.
Which is cheaper, GLM-5 or GPT-4 Turbo?
GLM-5 is cheaper. It lists at $1 per million input tokens and $3.20 per million output tokens; GPT-4 Turbo lists at $10 and $30.
Is GLM-5 or GPT-4 Turbo better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
GLM-5 does, with 205K tokens against 128K.
How many benchmarks do GLM-5 and GPT-4 Turbo share?
24 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and GPT-4 Turbo has 36.