Model comparison
GLM-5.1 vs o3-mini
GLM-5.1 is the stronger model overall, scoring 47.8 to 36.7 on the Noometry Index.
Last verified . 29 shared benchmarks.
Summary
- They share 29 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and o3-mini in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.1 leads 39.1 to 16.3.
- The biggest single-benchmark swing is SimpleBench: 55.1% for GLM-5.1 and 22.8% for o3-mini.
- o3-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- GLM-5.1 has downloadable open weights; the other is API-only.
Side by side
| GLM-5.1 | o3-mini | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 47.8 | 36.7 |
| Released | 2026-04-07 | 2024-12-20 |
| Weights | Open | Proprietary |
| Context window | 200K | 200K |
| Max output | 131K | 100K |
| Input $ / M tokens | $1.40 | $1.10 |
| Output $ / M tokens | $4.40 | $4.40 |
| Results tracked | 41 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
GLM-5.1: 48.7 (#55), o3-mini: 40.8 (#132)
| Benchmark | GLM-5.1 | o3-mini |
|---|---|---|
| SciCode | 43.8% | 39.8% |
| WeirdML | 57.1% | 43.7% |
| LMArena Coding | 1485 | 1378 |
| SWE-bench Verified | 74.2% | — |
| Aider Polyglot | — | 60.4% |
| LMArena WebDev | 1508 | — |
| GSO | — | 1.3% |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |
| ALE-Bench | 887.1 | — |
Agentic & Tool Use o3-mini leads
GLM-5.1: 24.9 (#113), o3-mini: 29.6 (#84)
| Benchmark | GLM-5.1 | o3-mini |
|---|---|---|
| APEX-Agents | 40.9% | — |
| Cybench | — | 22.5% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |
Reasoning GLM-5.1 leads
GLM-5.1: 39.1 (#60), o3-mini: 16.3 (#305)
| Benchmark | GLM-5.1 | o3-mini |
|---|---|---|
| SimpleBench | 55.1% | 22.8% |
| CritPt | 4.6% | 0.3% |
| Chess Puzzles | 19% | 17% |
| LMArena Hard Prompts | 1472 | 1366 |
| Epoch Capabilities Index | 149.84 | 140.34 |
| ARC-AGI-2 | — | 3% |
| NYT Connections (extended) | 77.7% | — |
| ARC-AGI-1 | — | 34.5% |
| Thematic Generalization | 69.8% | — |
| LiveBench Reasoning | — | 89.6% |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 68.8% |
| LiveBench Data Analysis | — | 70.6% |
| LMCA | — | 19% |
| ForecastBench | — | 59.6 |
| LiveBench | — | 75.9% |
Math GLM-5.1 leads
GLM-5.1: 49.7 (#60), o3-mini: 28.1 (#244)
| Benchmark | GLM-5.1 | o3-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 36.8% | 18.6% |
| OTIS Mock AIME 2024-2025 | 93.3% | 76.9% |
| LMArena Math | 1473 | 1396 |
| FrontierMath (Feb 2025 set) | 33.4% | 12.4% |
| FrontierMath Tier 4 (v1) | 12.5% | 4.2% |
| FrontierMath Tier 4 | — | 0% |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| LiveBench Math | — | 77.3% |
| MATH Level 5 | — | 96.5% |
Knowledge GLM-5.1 leads
GLM-5.1: 54.9 (#50), o3-mini: 38.3 (#146)
| Benchmark | GLM-5.1 | o3-mini |
|---|---|---|
| GPQA Diamond | 89.9% | 77% |
| SimpleQA Verified | 34% | 15.3% |
| LMArena Expert | 1476 | 1364 |
| Confabulations | — | 17.9% |
Multilingual GLM-5.1 leads
GLM-5.1: 55.0 (#36), o3-mini: 45.7 (#164)
| Benchmark | GLM-5.1 | o3-mini |
|---|---|---|
| LMArena Non-English | 1447 | 1319 |
| LMArena Chinese | 1515 | 1379 |
| LMArena French | 1474 | 1334 |
| LMArena German | 1465 | 1303 |
| LMArena Japanese | 1434 | 1286 |
| LMArena Korean | 1418 | 1314 |
| LMArena Russian | 1454 | 1304 |
| LMArena Spanish | 1469 | 1321 |
Instruction Following GLM-5.1 leads
GLM-5.1: 76.3 (#42), o3-mini: 75.1 (#72)
| Benchmark | GLM-5.1 | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1451 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
Long Context GLM-5.1 leads
GLM-5.1: 44.9 (#53), o3-mini: 33.8 (#256)
| Benchmark | GLM-5.1 | o3-mini |
|---|---|---|
| LMArena Longer Query | 1466 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference GLM-5.1 leads
GLM-5.1: 66.9 (#31), o3-mini: 50.3 (#182)
| Benchmark | GLM-5.1 | o3-mini |
|---|---|---|
| LMArena Text | 1461 | 1337 |
| LMArena Creative Writing | 1453 | 1286 |
| LMArena Multi-Turn | 1472 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| EQ-Bench Creative Writing | 1592 | — |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is GLM-5.1 better than o3-mini?
GLM-5.1 is the stronger model overall, scoring 47.8 to 36.7 on the Noometry Index.
Which is cheaper, GLM-5.1 or o3-mini?
o3-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.
Is GLM-5.1 or o3-mini better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 200K tokens.
How many benchmarks do GLM-5.1 and o3-mini share?
29 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and o3-mini has 51.