Model comparison
GLM-5.1 vs GPT-4 Turbo
GLM-5.1 is the stronger model overall, scoring 47.6 to 30.3 on the Noometry Index.
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-4 Turbo in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.1 leads 49.0 to 8.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for GLM-5.1 and 6.7% for GPT-4 Turbo.
- GLM-5.1 is cheaper at $1.40 / $4.40 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- GLM-5.1 accepts more context: 200K tokens versus 128K.
- GLM-5.1 has downloadable open weights; the other is API-only.
Side by side
| GLM-5.1 | GPT-4 Turbo | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 47.6 | 30.3 |
| Released | 2026-04-07 | 2023-11-06 |
| Weights | Open | Proprietary |
| Context window | 200K | 128K |
| Max output | 131K | 4K |
| Input $ / M tokens | $1.40 | $10 |
| Output $ / M tokens | $4.40 | $30 |
| Results tracked | 41 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
GLM-5.1: 48.5 (#52), GPT-4 Turbo: 33.4 (#247)
| Benchmark | GLM-5.1 | GPT-4 Turbo |
|---|---|---|
| WeirdML | 57.1% | 18% |
| LMArena Coding | 1486 | 1268 |
| SWE-bench Verified | 74.2% | — |
| LMArena WebDev | 1509 | — |
| SciCode | 43.8% | — |
| BigCodeBench Instruct | — | 48.2% |
| BigCodeBench Complete | — | 58.2% |
| ALE-Bench | 887.1 | — |
| HumanEval+ | — | 86.6% |
| MBPP+ | — | 73.3% |
Agentic & Tool Use Not comparable
GLM-5.1: 24.8 (#106), GPT-4 Turbo: —
| Benchmark | GLM-5.1 | GPT-4 Turbo |
|---|---|---|
| APEX-Agents | 40.9% | — |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| METR Time Horizons | — | 36.7% |
| Vending-Bench 2 | 5,634 | — |
Reasoning GLM-5.1 leads
GLM-5.1: 38.2 (#57), GPT-4 Turbo: 14.9 (#311)
| Benchmark | GLM-5.1 | GPT-4 Turbo |
|---|---|---|
| SimpleBench | 55.1% | 25.1% |
| Chess Puzzles | 19% | 6% |
| LMArena Hard Prompts | 1472 | 1251 |
| Epoch Capabilities Index | 149.86 | 127.25 |
| NYT Connections (extended) | 77.7% | — |
| CritPt | 4.6% | — |
| Thematic Generalization | 69.8% | — |
| DTBench | — | 61.6% |
| LMCA | — | 9.8% |
| ForecastBench | — | 59.4 |
Math GLM-5.1 leads
GLM-5.1: 49.0 (#48), GPT-4 Turbo: 8.6 (#316)
| Benchmark | GLM-5.1 | GPT-4 Turbo |
|---|---|---|
| FrontierMath (Tiers 1-3) | 36.8% | 0.7% |
| OTIS Mock AIME 2024-2025 | 93.3% | 6.7% |
| LMArena Math | 1472 | 1272 |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| MATH Level 5 | — | 46.7% |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GLM-5.1 leads
GLM-5.1: 55.0 (#45), GPT-4 Turbo: 24.3 (#263)
| Benchmark | GLM-5.1 | GPT-4 Turbo |
|---|---|---|
| GPQA Diamond | 89.9% | 46.6% |
| LMArena Expert | 1477 | 1223 |
| SimpleQA Verified | 34% | — |
| Confabulations | — | 28.4% |
| MMLU | — | 81.3% |
Multimodal Not comparable
GLM-5.1: —, GPT-4 Turbo: 30.0 (#104)
| Benchmark | GLM-5.1 | GPT-4 Turbo |
|---|---|---|
| LMArena Vision | — | 1090 |
Multilingual GLM-5.1 leads
GLM-5.1: 55.2 (#34), GPT-4 Turbo: 40.7 (#211)
| Benchmark | GLM-5.1 | GPT-4 Turbo |
|---|---|---|
| LMArena Non-English | 1448 | 1245 |
| LMArena Chinese | 1516 | 1242 |
| LMArena French | 1478 | 1275 |
| LMArena German | 1466 | 1259 |
| LMArena Japanese | 1436 | 1194 |
| LMArena Korean | 1423 | 1187 |
| LMArena Russian | 1453 | 1259 |
| LMArena Spanish | 1467 | 1260 |
Instruction Following GLM-5.1 leads
GLM-5.1: 76.5 (#41), GPT-4 Turbo: 66.0 (#211)
| Benchmark | GLM-5.1 | GPT-4 Turbo |
|---|---|---|
| LMArena Instruction Following | 1451 | 1250 |
Long Context GLM-5.1 leads
GLM-5.1: 44.9 (#51), GPT-4 Turbo: 38.0 (#200)
| Benchmark | GLM-5.1 | GPT-4 Turbo |
|---|---|---|
| LMArena Longer Query | 1467 | 1254 |
Writing & Preference GLM-5.1 leads
GLM-5.1: 67.2 (#29), GPT-4 Turbo: 47.9 (#201)
| Benchmark | GLM-5.1 | GPT-4 Turbo |
|---|---|---|
| LMArena Text | 1462 | 1272 |
| LMArena Creative Writing | 1454 | 1269 |
| LMArena Multi-Turn | 1473 | 1267 |
| EQ-Bench Creative Writing | 1592 | — |
Frequently asked questions
Is GLM-5.1 better than GPT-4 Turbo?
GLM-5.1 is the stronger model overall, scoring 47.6 to 30.3 on the Noometry Index.
Which is cheaper, GLM-5.1 or GPT-4 Turbo?
GLM-5.1 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; GPT-4 Turbo lists at $10 and $30.
Is GLM-5.1 or GPT-4 Turbo better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.5 versus 33.4 in the Noometry coding category.
Which has the bigger context window?
GLM-5.1 does, with 200K tokens against 128K.
How many benchmarks do GLM-5.1 and GPT-4 Turbo share?
24 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and GPT-4 Turbo has 36.