Model comparison
GLM-5.2 vs o3-mini
GLM-5.2 is the stronger model overall, scoring 51.1 to 36.7 on the Noometry Index.
Last verified . 33 shared benchmarks.
Summary
- They share 33 benchmarks with published results for both. GLM-5.2 scores higher in 9 categories and o3-mini in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.2 leads 55.7 to 28.1.
- The biggest single-benchmark swing is ARC-AGI-1: 77% for GLM-5.2 and 34.5% for o3-mini.
- o3-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $1.40 / $4.40 for GLM-5.2.
- GLM-5.2 accepts more context: 1M tokens versus 200K.
- GLM-5.2 has downloadable open weights; the other is API-only.
Side by side
| GLM-5.2 | o3-mini | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 51.1 | 36.7 |
| Released | 2026-06-13 | 2024-12-20 |
| Weights | Open | Proprietary |
| Context window | 1M | 200K |
| Max output | 131K | 100K |
| Input $ / M tokens | $1.40 | $1.10 |
| Output $ / M tokens | $4.40 | $4.40 |
| Results tracked | 51 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.2 leads
GLM-5.2: 51.3 (#41), o3-mini: 40.8 (#132)
| Benchmark | GLM-5.2 | o3-mini |
|---|---|---|
| SciCode | 50.5% | 39.8% |
| WeirdML | 70.1% | 43.7% |
| LMArena Coding | 1485 | 1378 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| Aider Polyglot | — | 60.4% |
| LMArena WebDev | 1603 | — |
| GSO | — | 1.3% |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |
| ALE-Bench | 1,047 | — |
Agentic & Tool Use GLM-5.2 leads
GLM-5.2: 32.4 (#63), o3-mini: 29.6 (#84)
| Benchmark | GLM-5.2 | o3-mini |
|---|---|---|
| APEX-Agents | 45.2% | — |
| τ²-bench Banking | 37.1% | — |
| Cybench | — | 22.5% |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 8,314 | — |
Reasoning GLM-5.2 leads
GLM-5.2: 42.3 (#52), o3-mini: 16.3 (#305)
| Benchmark | GLM-5.2 | o3-mini |
|---|---|---|
| ARC-AGI-2 | 22.8% | 3% |
| SimpleBench | 58.8% | 22.8% |
| ARC-AGI-1 | 77% | 34.5% |
| CritPt | 20.9% | 0.3% |
| Chess Puzzles | 21% | 17% |
| LMArena Hard Prompts | 1480 | 1366 |
| Mystery Game Puzzles | 19% | 7% |
| DTBench | 93.6% | 68.8% |
| LMCA | 45.8% | 19% |
| Epoch Capabilities Index | 151.78 | 140.34 |
| Kagi LLM Benchmark | 62.6% | — |
| NYT Connections (extended) | 74.3% | — |
| EBR-Bench | 9.5% | — |
| LiveBench Reasoning | — | 89.6% |
| LiveBench Data Analysis | — | 70.6% |
| Surface Evolver Bench | 55.6% | — |
| ForecastBench | — | 59.6 |
| LiveBench | — | 75.9% |
Math GLM-5.2 leads
GLM-5.2: 55.7 (#43), o3-mini: 28.1 (#244)
| Benchmark | GLM-5.2 | o3-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 59.2% | 18.6% |
| FrontierMath Tier 4 | 29.3% | 0% |
| OTIS Mock AIME 2024-2025 | 86.4% | 76.9% |
| LMArena Math | 1482 | 1396 |
| MathArena Final-Answer Competitions | 67.6% | — |
| ProofBench | 35% | — |
| LiveBench Math | — | 77.3% |
| MATH Level 5 | — | 96.5% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge GLM-5.2 leads
GLM-5.2: 57.1 (#40), o3-mini: 38.3 (#146)
| Benchmark | GLM-5.2 | o3-mini |
|---|---|---|
| GPQA Diamond | 91.9% | 77% |
| SimpleQA Verified | 34.2% | 15.3% |
| LMArena Expert | 1486 | 1364 |
| Confabulations | — | 17.9% |
Multilingual GLM-5.2 leads
GLM-5.2: 55.8 (#26), o3-mini: 45.7 (#164)
| Benchmark | GLM-5.2 | o3-mini |
|---|---|---|
| LMArena Non-English | 1459 | 1319 |
| LMArena Chinese | 1519 | 1379 |
| LMArena French | 1479 | 1334 |
| LMArena German | 1468 | 1303 |
| LMArena Japanese | 1451 | 1286 |
| LMArena Korean | 1445 | 1314 |
| LMArena Russian | 1466 | 1304 |
| LMArena Spanish | 1477 | 1321 |
Instruction Following GLM-5.2 leads
GLM-5.2: 76.9 (#34), o3-mini: 75.1 (#72)
| Benchmark | GLM-5.2 | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1465 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
Long Context GLM-5.2 leads
GLM-5.2: 45.3 (#43), o3-mini: 33.8 (#256)
| Benchmark | GLM-5.2 | o3-mini |
|---|---|---|
| LMArena Longer Query | 1479 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.4 (#21), o3-mini: 50.3 (#182)
| Benchmark | GLM-5.2 | o3-mini |
|---|---|---|
| LMArena Text | 1470 | 1337 |
| LMArena Creative Writing | 1462 | 1286 |
| LMArena Multi-Turn | 1469 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| EQ-Bench Creative Writing | 1757 | — |
| EQ-Bench 4 | 1222 | — |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is GLM-5.2 better than o3-mini?
GLM-5.2 is the stronger model overall, scoring 51.1 to 36.7 on the Noometry Index.
Which is cheaper, GLM-5.2 or o3-mini?
o3-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; GLM-5.2 lists at $1.40 and $4.40.
Is GLM-5.2 or o3-mini better for coding?
GLM-5.2 scores higher on coding benchmarks: 51.3 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
GLM-5.2 does, with 1M tokens against 200K.
How many benchmarks do GLM-5.2 and o3-mini share?
33 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and o3-mini has 51.