Model comparison
GLM-5.3-Flash vs GPT-5 Mini
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 41.8 on the Noometry Index.
Last verified . 31 shared benchmarks.
Summary
- They share 31 benchmarks with published results for both. GLM-5.3-Flash scores higher in 10 categories and GPT-5 Mini in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.3-Flash leads 48.0 to 23.9.
- The biggest single-benchmark swing is ARC-AGI-2: 65.8% for GLM-5.3-Flash and 4.4% for GPT-5 Mini.
- GLM-5.3-Flash is cheaper at $0.15 / $0.50 per million input/output tokens, against $0.25 / $2 for GPT-5 Mini.
- 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 Mini | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 51.8 | 41.8 |
| Released | 2026-08-20 | 2025-08-07 |
| Weights | Open | Proprietary |
| Context window | 1M | 400K |
| Max output | 131K | 128K |
| Input $ / M tokens | $0.15 | $0.25 |
| Output $ / M tokens | $0.50 | $2 |
| Results tracked | 40 | 60 |
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 Mini: 40.1 (#146)
| Benchmark | GLM-5.3-Flash | GPT-5 Mini |
|---|---|---|
| SciCode | 51.6% | 39.2% |
| LMArena Coding | 1508 | 1406 |
| ALE-Bench | 303.55 | 799.77 |
| SWE-bench Verified | — | 64.7% |
| DeepSWE | 63.4% | — |
| FrontierCode | 31.8% | — |
| SWE-bench Verified (bash only) | — | 59.8% |
| CursorBench | 36.8% | — |
| LMArena WebDev | 1609 | — |
| SWE-bench Multilingual | — | 39.7% |
| FrontierSWE | 18.1% | — |
| WeirdML | — | 52.7% |
| AlgoTune | — | 1.38 |
Agentic & Tool Use GLM-5.3-Flash leads
GLM-5.3-Flash: 34.2 (#47), GPT-5 Mini: 31.1 (#70)
| Benchmark | GLM-5.3-Flash | GPT-5 Mini |
|---|---|---|
| Terminal-Bench | — | 34.8% |
| APEX-Agents | 52.8% | — |
| Berkeley Function Calling Leaderboard | — | 55.5% |
| GDP.pdf | 14% | — |
| Vending-Bench 2 | — | -31.18 |
Reasoning GLM-5.3-Flash leads
GLM-5.3-Flash: 48.0 (#42), GPT-5 Mini: 23.9 (#168)
| Benchmark | GLM-5.3-Flash | GPT-5 Mini |
|---|---|---|
| ARC-AGI-2 | 65.8% | 4.4% |
| ARC-AGI-1 | 91% | 54.3% |
| CritPt | 15.4% | 0% |
| Chess Puzzles | 14% | 30% |
| LMArena Hard Prompts | 1491 | 1380 |
| Mystery Game Puzzles | 8% | 10% |
| Epoch Capabilities Index | 151.88 | 145.52 |
| Kagi LLM Benchmark | — | 70.3% |
| EnigmaEval | — | 8.2% |
| DTBench | — | 80.5% |
| LMCA | — | 34.2% |
| Surface Evolver Bench | 52.5% | — |
| Bench to the Future 3 | 0.15 | — |
| ForecastBench | — | 61 |
Math GLM-5.3-Flash leads
GLM-5.3-Flash: 53.3 (#47), GPT-5 Mini: 46.7 (#69)
| Benchmark | GLM-5.3-Flash | GPT-5 Mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.8% | 46.7% |
| FrontierMath Tier 4 | 17.1% | 12.2% |
| OTIS Mock AIME 2024-2025 | 93.9% | 86.7% |
| ProofBench | 21% | 9% |
| LMArena Math | 1500 | 1378 |
| Omni-MATH | — | 72.2% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 27.2% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge GLM-5.3-Flash leads
GLM-5.3-Flash: 58.4 (#36), GPT-5 Mini: 45.6 (#86)
| Benchmark | GLM-5.3-Flash | GPT-5 Mini |
|---|---|---|
| GPQA Diamond | 90.2% | 75% |
| LMArena Expert | 1513 | 1379 |
| Humanity's Last Exam | — | 19.4% |
| SimpleQA Verified | — | 21.6% |
| MMLU-Pro | — | 83.5% |
| Confabulations | — | 13.3% |
| Vectara Hallucination Rate | — | 12.9% |
| GPQA (HELM) | — | 75.6% |
Multimodal GLM-5.3-Flash leads
GLM-5.3-Flash: 42.8 (#27), GPT-5 Mini: 35.6 (#85)
| Benchmark | GLM-5.3-Flash | GPT-5 Mini |
|---|---|---|
| LMArena Vision | 1296 | 1202 |
| VPCT | — | 40.2% |
Multilingual GLM-5.3-Flash leads
GLM-5.3-Flash: 56.0 (#25), GPT-5 Mini: 48.9 (#137)
| Benchmark | GLM-5.3-Flash | GPT-5 Mini |
|---|---|---|
| LMArena Non-English | 1462 | 1363 |
| LMArena Chinese | 1527 | 1385 |
| LMArena French | 1496 | 1386 |
| LMArena German | 1470 | 1366 |
| LMArena Japanese | 1429 | 1341 |
| LMArena Korean | 1446 | 1308 |
| LMArena Russian | 1469 | 1362 |
| LMArena Spanish | 1471 | 1355 |
Instruction Following GLM-5.3-Flash leads
GLM-5.3-Flash: 77.5 (#20), GPT-5 Mini: 76.2 (#46)
| Benchmark | GLM-5.3-Flash | GPT-5 Mini |
|---|---|---|
| LMArena Instruction Following | 1478 | 1357 |
| IFEval | — | 92.7% |
Long Context GLM-5.3-Flash leads
GLM-5.3-Flash: 45.4 (#39), GPT-5 Mini: 41.9 (#132)
| Benchmark | GLM-5.3-Flash | GPT-5 Mini |
|---|---|---|
| LMArena Longer Query | 1482 | 1355 |
| Fiction.LiveBench | — | 69.4% |
Writing & Preference GLM-5.3-Flash leads
GLM-5.3-Flash: 65.3 (#50), GPT-5 Mini: 55.2 (#148)
| Benchmark | GLM-5.3-Flash | GPT-5 Mini |
|---|---|---|
| LMArena Text | 1471 | 1373 |
| LMArena Creative Writing | 1442 | 1325 |
| LMArena Multi-Turn | 1467 | 1363 |
| Short-Story Creative Writing | — | 83.1% |
| EQ-Bench Creative Writing | — | 1313 |
| WildBench | — | 85.5% |
Frequently asked questions
Is GLM-5.3-Flash better than GPT-5 Mini?
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 41.8 on the Noometry Index.
Which is cheaper, GLM-5.3-Flash or GPT-5 Mini?
GLM-5.3-Flash is cheaper. It lists at $0.15 per million input tokens and $0.50 per million output tokens; GPT-5 Mini lists at $0.25 and $2.
Is GLM-5.3-Flash or GPT-5 Mini better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.1 versus 40.1 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 Mini share?
31 benchmarks have published results for both models. GLM-5.3-Flash has 40 scored results on Noometry and GPT-5 Mini has 60.