Model comparison
GLM-5 vs o3-mini
GLM-5 is the stronger model overall, scoring 46.1 to 36.7 on the Noometry Index.
Last verified . 28 shared benchmarks.
Summary
- They share 28 benchmarks with published results for both. GLM-5 scores higher in 9 categories and o3-mini in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5 leads 46.4 to 28.1.
- The biggest single-benchmark swing is SimpleBench: 53.2% for GLM-5 and 22.8% for o3-mini.
- GLM-5 is cheaper at $1 / $3.20 per million input/output tokens, against $1.10 / $4.40 for o3-mini.
- GLM-5 accepts more context: 205K tokens versus 200K.
- GLM-5 has downloadable open weights; the other is API-only.
Side by side
| GLM-5 | o3-mini | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 46.1 | 36.7 |
| Released | 2026-02-11 | 2024-12-20 |
| Weights | Open | Proprietary |
| Context window | 205K | 200K |
| Max output | 131K | 100K |
| Input $ / M tokens | $1 | $1.10 |
| Output $ / M tokens | $3.20 | $4.40 |
| Results tracked | 45 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#52), o3-mini: 40.8 (#132)
| Benchmark | GLM-5 | o3-mini |
|---|---|---|
| WeirdML | 48.2% | 43.7% |
| LMArena Coding | 1461 | 1378 |
| SWE-bench Verified | 72.1% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| Aider Polyglot | — | 60.4% |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |
| ALE-Bench | 765.62 | — |
Agentic & Tool Use GLM-5 leads
GLM-5: 31.1 (#71), o3-mini: 29.6 (#84)
| Benchmark | GLM-5 | o3-mini |
|---|---|---|
| Terminal-Bench | 52.4% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
| Cybench | — | 22.5% |
| Vending-Bench 2 | 4,432 | — |
Reasoning GLM-5 leads
GLM-5: 27.6 (#116), o3-mini: 16.3 (#305)
| Benchmark | GLM-5 | o3-mini |
|---|---|---|
| ARC-AGI-2 | 4.9% | 3% |
| SimpleBench | 53.2% | 22.8% |
| ARC-AGI-1 | 44.7% | 34.5% |
| Chess Puzzles | 10% | 17% |
| LMArena Hard Prompts | 1452 | 1366 |
| Epoch Capabilities Index | 145.83 | 140.34 |
| ForecastBench | 61 | 59.6 |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 74.8% | — |
| CritPt | — | 0.3% |
| LiveBench Reasoning | — | 89.6% |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 68.8% |
| LiveBench Data Analysis | — | 70.6% |
| LMCA | — | 19% |
| LiveBench | — | 75.9% |
Math GLM-5 leads
GLM-5: 46.4 (#71), o3-mini: 28.1 (#244)
| Benchmark | GLM-5 | o3-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 76.9% |
| LMArena Math | 1440 | 1396 |
| FrontierMath (Feb 2025 set) | 16.4% | 12.4% |
| FrontierMath Tier 4 (v1) | 2.1% | 4.2% |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| MathArena Final-Answer Competitions | 65.7% | — |
| LiveBench Math | — | 77.3% |
| MATH Level 5 | — | 96.5% |
Knowledge GLM-5 leads
GLM-5: 52.3 (#64), o3-mini: 38.3 (#146)
| Benchmark | GLM-5 | o3-mini |
|---|---|---|
| GPQA Diamond | 87.8% | 77% |
| LMArena Expert | 1454 | 1364 |
| SimpleQA Verified | — | 15.3% |
| Confabulations | — | 17.9% |
| Vectara Hallucination Rate | 10.1% | — |
Multilingual GLM-5 leads
GLM-5: 53.7 (#58), o3-mini: 45.7 (#164)
| Benchmark | GLM-5 | o3-mini |
|---|---|---|
| LMArena Non-English | 1430 | 1319 |
| LMArena Chinese | 1511 | 1379 |
| LMArena French | 1455 | 1334 |
| LMArena German | 1445 | 1303 |
| LMArena Japanese | 1416 | 1286 |
| LMArena Korean | 1423 | 1314 |
| LMArena Russian | 1436 | 1304 |
| LMArena Spanish | 1454 | 1321 |
Instruction Following Too close to call
GLM-5: 75.2 (#67), o3-mini: 75.1 (#72)
| Benchmark | GLM-5 | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1428 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
Long Context GLM-5 leads
GLM-5: 44.7 (#60), o3-mini: 33.8 (#256)
| Benchmark | GLM-5 | o3-mini |
|---|---|---|
| LMArena Longer Query | 1446 | 1343 |
| Fiction.LiveBench | — | 50% |
| CL-bench | 18.7% | — |
Writing & Preference GLM-5 leads
GLM-5: 66.0 (#38), o3-mini: 50.3 (#182)
| Benchmark | GLM-5 | o3-mini |
|---|---|---|
| LMArena Text | 1446 | 1337 |
| LMArena Creative Writing | 1439 | 1286 |
| LMArena Multi-Turn | 1456 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| EQ-Bench Creative Writing | 1601 | — |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is GLM-5 better than o3-mini?
GLM-5 is the stronger model overall, scoring 46.1 to 36.7 on the Noometry Index.
Which is cheaper, GLM-5 or o3-mini?
GLM-5 is cheaper. It lists at $1 per million input tokens and $3.20 per million output tokens; o3-mini lists at $1.10 and $4.40.
Is GLM-5 or o3-mini better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
GLM-5 does, with 205K tokens against 200K.
How many benchmarks do GLM-5 and o3-mini share?
28 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and o3-mini has 51.