Model comparison
GLM-5.3-Flash vs GPT-5
GLM-5.3-Flash and GPT-5 score almost the same on the Noometry Index (51.8 vs 50.9), so choose on price, context window or the category you care about most.
Last verified . 32 shared benchmarks.
Summary
- They share 32 benchmarks with published results for both. GLM-5.3-Flash scores higher in 7 categories and GPT-5 in 3 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in long context, where GPT-5 leads 69.5 to 45.4.
- The biggest single-benchmark swing is ARC-AGI-2: 65.8% for GLM-5.3-Flash and 9.9% for GPT-5.
- GLM-5.3-Flash is cheaper at $0.15 / $0.50 per million input/output tokens, against $1.25 / $10 for GPT-5.
- GLM-5.3-Flash accepts more context: 1M tokens versus 400K.
- GLM-5.3-Flash has downloadable open weights; the other is API-only.
Side by side
| GLM-5.3-Flash | GPT-5 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 51.8 | 50.9 |
| Released | 2026-08-20 | 2025-08-07 |
| Weights | Open | Proprietary |
| Context window | 1M | 400K |
| Max output | 131K | 128K |
| Input $ / M tokens | $0.15 | $1.25 |
| Output $ / M tokens | $0.50 | $10 |
| Results tracked | 40 | 69 |
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-5: 50.3 (#47)
| Benchmark | GLM-5.3-Flash | GPT-5 |
|---|---|---|
| LMArena WebDev | 1609 | 1418 |
| SciCode | 51.6% | 42.9% |
| LMArena Coding | 1508 | 1436 |
| ALE-Bench | 303.55 | 1,162 |
| SWE-bench Verified | — | 73.6% |
| DeepSWE | 63.4% | — |
| FrontierCode | 31.8% | — |
| SWE-bench Verified (bash only) | — | 65% |
| Aider Polyglot | — | 88% |
| CursorBench | 36.8% | — |
| FrontierSWE | 18.1% | — |
| GSO | — | 6.9% |
| WeirdML | — | 60.7% |
| AlgoTune | — | 1.67 |
Agentic & Tool Use GLM-5.3-Flash leads
GLM-5.3-Flash: 34.2 (#47), GPT-5: 33.1 (#56)
| Benchmark | GLM-5.3-Flash | GPT-5 |
|---|---|---|
| Terminal-Bench | — | 49.6% |
| APEX-Agents | 52.8% | — |
| GDPval | — | 34.8% |
| Remote Labor Index | — | 1.7% |
| DeepResearch Bench | — | 49.6% |
| BALROG | — | 32.8% |
| GDP.pdf | 14% | — |
| LMArena Search | — | 1133 |
| METR Time Horizons | — | 69.6% |
Reasoning GLM-5.3-Flash leads
GLM-5.3-Flash: 48.0 (#42), GPT-5: 38.3 (#64)
| Benchmark | GLM-5.3-Flash | GPT-5 |
|---|---|---|
| ARC-AGI-2 | 65.8% | 9.9% |
| ARC-AGI-1 | 91% | 65.7% |
| CritPt | 15.4% | 12.6% |
| Chess Puzzles | 14% | 37% |
| LMArena Hard Prompts | 1491 | 1416 |
| Mystery Game Puzzles | 8% | 23% |
| Epoch Capabilities Index | 151.88 | 150 |
| SimpleBench | — | 56.7% |
| Kagi LLM Benchmark | — | 72.7% |
| EnigmaEval | — | 10.5% |
| EBR-Bench | — | 12.7% |
| DTBench | — | 90.7% |
| LMCA | — | 40% |
| Surface Evolver Bench | 52.5% | — |
| Bench to the Future 3 | 0.15 | — |
| ForecastBench | — | 61.4 |
Math GPT-5 leads
GLM-5.3-Flash: 53.3 (#47), GPT-5: 55.0 (#44)
| Benchmark | GLM-5.3-Flash | GPT-5 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.8% | 55.4% |
| FrontierMath Tier 4 | 17.1% | 22% |
| OTIS Mock AIME 2024-2025 | 93.9% | 91.4% |
| ProofBench | 21% | 18% |
| LMArena Math | 1500 | 1407 |
| Omni-MATH | — | 64.7% |
| MATH Level 5 | — | 98.1% |
| FrontierMath (Feb 2025 set) | — | 32.4% |
| FrontierMath Tier 4 (v1) | — | 12.5% |
Knowledge GLM-5.3-Flash leads
GLM-5.3-Flash: 58.4 (#36), GPT-5: 56.6 (#43)
| Benchmark | GLM-5.3-Flash | GPT-5 |
|---|---|---|
| GPQA Diamond | 90.2% | 86.2% |
| LMArena Expert | 1513 | 1419 |
| Humanity's Last Exam | — | 25.3% |
| SimpleQA Verified | — | 50.1% |
| MMLU-Pro | — | 86.3% |
| Confabulations | — | 10.3% |
| Vectara Hallucination Rate | — | 14.7% |
| GPQA (HELM) | — | 79.2% |
Multimodal GPT-5 leads
GLM-5.3-Flash: 42.8 (#27), GPT-5: 46.8 (#13)
| Benchmark | GLM-5.3-Flash | GPT-5 |
|---|---|---|
| LMArena Vision | 1296 | 1232 |
| GeoBench | — | 81% |
| VPCT | — | 66% |
Multilingual GLM-5.3-Flash leads
GLM-5.3-Flash: 56.0 (#25), GPT-5: 51.4 (#110)
| Benchmark | GLM-5.3-Flash | GPT-5 |
|---|---|---|
| LMArena Non-English | 1462 | 1397 |
| LMArena Chinese | 1527 | 1422 |
| LMArena French | 1496 | 1410 |
| LMArena German | 1470 | 1416 |
| LMArena Japanese | 1429 | 1409 |
| LMArena Korean | 1446 | 1360 |
| LMArena Russian | 1469 | 1406 |
| LMArena Spanish | 1471 | 1399 |
Instruction Following GLM-5.3-Flash leads
GLM-5.3-Flash: 77.5 (#20), GPT-5: 73.8 (#113)
| Benchmark | GLM-5.3-Flash | GPT-5 |
|---|---|---|
| LMArena Instruction Following | 1478 | 1388 |
| IFEval | — | 87.5% |
Long Context GPT-5 leads
GLM-5.3-Flash: 45.4 (#39), GPT-5: 69.5 (#2)
| Benchmark | GLM-5.3-Flash | GPT-5 |
|---|---|---|
| LMArena Longer Query | 1482 | 1399 |
| Fiction.LiveBench | — | 97.2% |
Writing & Preference GLM-5.3-Flash leads
GLM-5.3-Flash: 65.3 (#50), GPT-5: 63.4 (#65)
| Benchmark | GLM-5.3-Flash | GPT-5 |
|---|---|---|
| LMArena Text | 1471 | 1406 |
| LMArena Creative Writing | 1442 | 1365 |
| LMArena Multi-Turn | 1467 | 1426 |
| Short-Story Creative Writing | — | 86% |
| EQ-Bench Creative Writing | — | 1627 |
| WildBench | — | 85.7% |
Frequently asked questions
Is GLM-5.3-Flash better than GPT-5?
GLM-5.3-Flash and GPT-5 score almost the same on the Noometry Index (51.8 vs 50.9), so choose on price, context window or the category you care about most.
Which is cheaper, GLM-5.3-Flash or GPT-5?
GLM-5.3-Flash is cheaper. It lists at $0.15 per million input tokens and $0.50 per million output tokens; GPT-5 lists at $1.25 and $10.
Is GLM-5.3-Flash or GPT-5 better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.1 versus 50.3 in the Noometry coding category.
Which has the bigger context window?
GLM-5.3-Flash does, with 1M tokens against 400K.
How many benchmarks do GLM-5.3-Flash and GPT-5 share?
32 benchmarks have published results for both models. GLM-5.3-Flash has 40 scored results on Noometry and GPT-5 has 69.