Model comparison
GLM-5.1 vs o1
GLM-5.1 is the stronger model overall, scoring 47.8 to 40.9 on the Noometry Index.
Last verified . 26 shared benchmarks.
Summary
- They share 26 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and o1 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.1 leads 49.7 to 36.1.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 36.8% for GLM-5.1 and 14.7% for o1.
- GLM-5.1 is cheaper at $1.40 / $4.40 per million input/output tokens, against $15 / $60 for o1.
- GLM-5.1 has downloadable open weights; the other is API-only.
Side by side
| GLM-5.1 | o1 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 47.8 | 40.9 |
| Released | 2026-04-07 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 200K | 200K |
| Max output | 131K | 100K |
| Input $ / M tokens | $1.40 | $15 |
| Output $ / M tokens | $4.40 | $60 |
| Results tracked | 41 | 52 |
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), o1: 46.1 (#70)
| Benchmark | GLM-5.1 | o1 |
|---|---|---|
| WeirdML | 57.1% | 47.6% |
| LMArena Coding | 1485 | 1367 |
| SWE-bench Verified | 74.2% | — |
| Aider Polyglot | — | 61.7% |
| LMArena WebDev | 1508 | — |
| SciCode | 43.8% | — |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| ALE-Bench | 887.1 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use Too close to call
GLM-5.1: 24.9 (#113), o1: 24.6 (#117)
| Benchmark | GLM-5.1 | o1 |
|---|---|---|
| APEX-Agents | 40.9% | — |
| Cybench | — | 10% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| METR Time Horizons | — | 51.1% |
| Vending-Bench 2 | 5,634 | — |
Reasoning GLM-5.1 leads
GLM-5.1: 39.1 (#60), o1: 27.9 (#111)
| Benchmark | GLM-5.1 | o1 |
|---|---|---|
| SimpleBench | 55.1% | 41.7% |
| Chess Puzzles | 19% | 15% |
| LMArena Hard Prompts | 1472 | 1371 |
| Epoch Capabilities Index | 149.84 | 141.91 |
| NYT Connections (extended) | 77.7% | — |
| ARC-AGI-1 | — | 30.7% |
| CritPt | 4.6% | — |
| EnigmaEval | — | 5.7% |
| Thematic Generalization | 69.8% | — |
| LiveBench Reasoning | — | 91.6% |
| DTBench | — | 74.7% |
| LiveBench Data Analysis | — | 65.5% |
| LMCA | — | 22.3% |
| LiveBench | — | 75.7% |
Math GLM-5.1 leads
GLM-5.1: 49.7 (#60), o1: 36.1 (#175)
| Benchmark | GLM-5.1 | o1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 36.8% | 14.7% |
| OTIS Mock AIME 2024-2025 | 93.3% | 73.3% |
| LMArena Math | 1473 | 1388 |
| FrontierMath (Feb 2025 set) | 33.4% | 9.3% |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| LiveBench Math | — | 80.3% |
| MATH Level 5 | — | 94.7% |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GLM-5.1 leads
GLM-5.1: 54.9 (#50), o1: 41.5 (#110)
| Benchmark | GLM-5.1 | o1 |
|---|---|---|
| GPQA Diamond | 89.9% | 76.8% |
| SimpleQA Verified | 34% | 41.1% |
| LMArena Expert | 1476 | 1361 |
| Humanity's Last Exam | — | 8% |
| Confabulations | — | 11.7% |
Multimodal Not comparable
GLM-5.1: —, o1: 34.2 (#93)
| Benchmark | GLM-5.1 | o1 |
|---|---|---|
| LMArena Vision | — | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |
Multilingual GLM-5.1 leads
GLM-5.1: 55.0 (#36), o1: 48.6 (#142)
| Benchmark | GLM-5.1 | o1 |
|---|---|---|
| LMArena Non-English | 1447 | 1358 |
| LMArena Chinese | 1515 | 1394 |
| LMArena French | 1474 | 1344 |
| LMArena German | 1465 | 1337 |
| LMArena Japanese | 1434 | 1346 |
| LMArena Korean | 1418 | 1396 |
| LMArena Russian | 1454 | 1356 |
| LMArena Spanish | 1469 | 1345 |
Instruction Following GLM-5.1 leads
GLM-5.1: 76.3 (#42), o1: 74.8 (#86)
| Benchmark | GLM-5.1 | o1 |
|---|---|---|
| LMArena Instruction Following | 1451 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
Long Context o1 leads
GLM-5.1: 44.9 (#53), o1: 50.3 (#9)
| Benchmark | GLM-5.1 | o1 |
|---|---|---|
| LMArena Longer Query | 1466 | 1378 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference GLM-5.1 leads
GLM-5.1: 66.9 (#31), o1: 55.6 (#144)
| Benchmark | GLM-5.1 | o1 |
|---|---|---|
| LMArena Text | 1461 | 1366 |
| LMArena Creative Writing | 1453 | 1348 |
| LMArena Multi-Turn | 1472 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| EQ-Bench Creative Writing | 1592 | — |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is GLM-5.1 better than o1?
GLM-5.1 is the stronger model overall, scoring 47.8 to 40.9 on the Noometry Index.
Which is cheaper, GLM-5.1 or o1?
GLM-5.1 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; o1 lists at $15 and $60.
Is GLM-5.1 or o1 better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 46.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 200K tokens.
How many benchmarks do GLM-5.1 and o1 share?
26 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and o1 has 52.