Model comparison
GLM-5.2 vs GPT-5
GLM-5.2 and GPT-5 score almost the same on the Noometry Index (51.1 vs 50.9), so choose on price, context window or the category you care about most.
Last verified . 40 shared benchmarks.
Summary
- They share 40 benchmarks with published results for both. GLM-5.2 scores higher in 7 categories and GPT-5 in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where GPT-5 leads 69.5 to 45.3.
- The biggest single-benchmark swing is ProofBench: 35% for GLM-5.2 and 18% for GPT-5.
- GLM-5.2 is cheaper at $1.40 / $4.40 per million input/output tokens, against $1.25 / $10 for GPT-5.
- GLM-5.2 accepts more context: 1M tokens versus 400K.
- GLM-5.2 has downloadable open weights; the other is API-only.
Side by side
| GLM-5.2 | GPT-5 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 51.1 | 50.9 |
| Released | 2026-06-13 | 2025-08-07 |
| Weights | Open | Proprietary |
| Context window | 1M | 400K |
| Max output | 131K | 128K |
| Input $ / M tokens | $1.40 | $1.25 |
| Output $ / M tokens | $4.40 | $10 |
| Results tracked | 51 | 69 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-5.2: 51.3 (#41), GPT-5: 50.3 (#47)
| Benchmark | GLM-5.2 | GPT-5 |
|---|---|---|
| SWE-bench Verified | 78.7% | 73.6% |
| LMArena WebDev | 1603 | 1418 |
| SciCode | 50.5% | 42.9% |
| WeirdML | 70.1% | 60.7% |
| LMArena Coding | 1485 | 1436 |
| ALE-Bench | 1,047 | 1,162 |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| SWE-bench Verified (bash only) | — | 65% |
| Aider Polyglot | — | 88% |
| GSO | — | 6.9% |
| AlgoTune | — | 1.67 |
Agentic & Tool Use Too close to call
GLM-5.2: 32.4 (#63), GPT-5: 33.1 (#56)
| Benchmark | GLM-5.2 | GPT-5 |
|---|---|---|
| Terminal-Bench | — | 49.6% |
| APEX-Agents | 45.2% | — |
| GDPval | — | 34.8% |
| Remote Labor Index | — | 1.7% |
| τ²-bench Banking | 37.1% | — |
| DeepResearch Bench | — | 49.6% |
| PostTrainBench | 31.7% | — |
| BALROG | — | 32.8% |
| GBAEval | 0% | — |
| LMArena Search | — | 1133 |
| METR Time Horizons | — | 69.6% |
| Vending-Bench 2 | 8,314 | — |
Reasoning GLM-5.2 leads
GLM-5.2: 42.3 (#52), GPT-5: 38.3 (#64)
| Benchmark | GLM-5.2 | GPT-5 |
|---|---|---|
| ARC-AGI-2 | 22.8% | 9.9% |
| SimpleBench | 58.8% | 56.7% |
| Kagi LLM Benchmark | 62.6% | 72.7% |
| ARC-AGI-1 | 77% | 65.7% |
| CritPt | 20.9% | 12.6% |
| Chess Puzzles | 21% | 37% |
| EBR-Bench | 9.5% | 12.7% |
| LMArena Hard Prompts | 1480 | 1416 |
| Mystery Game Puzzles | 19% | 23% |
| DTBench | 93.6% | 90.7% |
| LMCA | 45.8% | 40% |
| Epoch Capabilities Index | 151.78 | 150 |
| NYT Connections (extended) | 74.3% | — |
| EnigmaEval | — | 10.5% |
| Surface Evolver Bench | 55.6% | — |
| ForecastBench | — | 61.4 |
Math Too close to call
GLM-5.2: 55.7 (#43), GPT-5: 55.0 (#44)
| Benchmark | GLM-5.2 | GPT-5 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 59.2% | 55.4% |
| FrontierMath Tier 4 | 29.3% | 22% |
| OTIS Mock AIME 2024-2025 | 86.4% | 91.4% |
| ProofBench | 35% | 18% |
| LMArena Math | 1482 | 1407 |
| MathArena Final-Answer Competitions | 67.6% | — |
| Omni-MATH | — | 64.7% |
| MATH Level 5 | — | 98.1% |
| FrontierMath (Feb 2025 set) | — | 32.4% |
| FrontierMath Tier 4 (v1) | — | 12.5% |
Knowledge Too close to call
GLM-5.2: 57.1 (#40), GPT-5: 56.6 (#43)
| Benchmark | GLM-5.2 | GPT-5 |
|---|---|---|
| GPQA Diamond | 91.9% | 86.2% |
| SimpleQA Verified | 34.2% | 50.1% |
| LMArena Expert | 1486 | 1419 |
| Humanity's Last Exam | — | 25.3% |
| MMLU-Pro | — | 86.3% |
| Confabulations | — | 10.3% |
| Vectara Hallucination Rate | — | 14.7% |
| GPQA (HELM) | — | 79.2% |
Multimodal Not comparable
GLM-5.2: —, GPT-5: 46.8 (#13)
| Benchmark | GLM-5.2 | GPT-5 |
|---|---|---|
| LMArena Vision | — | 1232 |
| GeoBench | — | 81% |
| VPCT | — | 66% |
Multilingual GLM-5.2 leads
GLM-5.2: 55.8 (#26), GPT-5: 51.4 (#110)
| Benchmark | GLM-5.2 | GPT-5 |
|---|---|---|
| LMArena Non-English | 1459 | 1397 |
| LMArena Chinese | 1519 | 1422 |
| LMArena French | 1479 | 1410 |
| LMArena German | 1468 | 1416 |
| LMArena Japanese | 1451 | 1409 |
| LMArena Korean | 1445 | 1360 |
| LMArena Russian | 1466 | 1406 |
| LMArena Spanish | 1477 | 1399 |
Instruction Following GLM-5.2 leads
GLM-5.2: 76.9 (#34), GPT-5: 73.8 (#113)
| Benchmark | GLM-5.2 | GPT-5 |
|---|---|---|
| LMArena Instruction Following | 1465 | 1388 |
| IFEval | — | 87.5% |
Long Context GPT-5 leads
GLM-5.2: 45.3 (#43), GPT-5: 69.5 (#2)
| Benchmark | GLM-5.2 | GPT-5 |
|---|---|---|
| LMArena Longer Query | 1479 | 1399 |
| Fiction.LiveBench | — | 97.2% |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.4 (#21), GPT-5: 63.4 (#65)
| Benchmark | GLM-5.2 | GPT-5 |
|---|---|---|
| LMArena Text | 1470 | 1406 |
| LMArena Creative Writing | 1462 | 1365 |
| EQ-Bench Creative Writing | 1757 | 1627 |
| LMArena Multi-Turn | 1469 | 1426 |
| Short-Story Creative Writing | — | 86% |
| WildBench | — | 85.7% |
| EQ-Bench 4 | 1222 | — |
Frequently asked questions
Is GLM-5.2 better than GPT-5?
GLM-5.2 and GPT-5 score almost the same on the Noometry Index (51.1 vs 50.9), so choose on price, context window or the category you care about most.
Which is cheaper, GLM-5.2 or GPT-5?
GLM-5.2 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; GPT-5 lists at $1.25 and $10.
Is GLM-5.2 or GPT-5 better for coding?
They score almost the same on coding (51.3 vs 50.3); test both on your own repository before choosing.
Which has the bigger context window?
GLM-5.2 does, with 1M tokens against 400K.
How many benchmarks do GLM-5.2 and GPT-5 share?
40 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and GPT-5 has 69.