Model comparison
GLM-5 vs o1
GLM-5 is the stronger model overall, scoring 46.1 to 40.9 on the Noometry Index.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. GLM-5 scores higher in 7 categories and o1 in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5 leads 52.3 to 41.5.
- The biggest single-benchmark swing is ARC-AGI-1: 44.7% for GLM-5 and 30.7% for o1.
- GLM-5 is cheaper at $1 / $3.20 per million input/output tokens, against $15 / $60 for o1.
- 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 | o1 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 46.1 | 40.9 |
| Released | 2026-02-11 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 205K | 200K |
| Max output | 131K | 100K |
| Input $ / M tokens | $1 | $15 |
| Output $ / M tokens | $3.20 | $60 |
| Results tracked | 45 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#52), o1: 46.1 (#70)
| Benchmark | GLM-5 | o1 |
|---|---|---|
| WeirdML | 48.2% | 47.6% |
| LMArena Coding | 1461 | 1367 |
| SWE-bench Verified | 72.1% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| Aider Polyglot | — | 61.7% |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| ALE-Bench | 765.62 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use GLM-5 leads
GLM-5: 31.1 (#71), o1: 24.6 (#117)
| Benchmark | GLM-5 | o1 |
|---|---|---|
| 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 | — | 10% |
| METR Time Horizons | — | 51.1% |
| Vending-Bench 2 | 4,432 | — |
Reasoning Too close to call
GLM-5: 27.6 (#116), o1: 27.9 (#111)
| Benchmark | GLM-5 | o1 |
|---|---|---|
| SimpleBench | 53.2% | 41.7% |
| ARC-AGI-1 | 44.7% | 30.7% |
| Chess Puzzles | 10% | 15% |
| LMArena Hard Prompts | 1452 | 1371 |
| Epoch Capabilities Index | 145.83 | 141.91 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 74.8% | — |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| DTBench | — | 74.7% |
| LiveBench Data Analysis | — | 65.5% |
| LMCA | — | 22.3% |
| ForecastBench | 61 | — |
| LiveBench | — | 75.7% |
Math GLM-5 leads
GLM-5: 46.4 (#71), o1: 36.1 (#175)
| Benchmark | GLM-5 | o1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 73.3% |
| LMArena Math | 1440 | 1388 |
| FrontierMath (Feb 2025 set) | 16.4% | 9.3% |
| FrontierMath (Tiers 1-3) | — | 14.7% |
| MathArena Final-Answer Competitions | 65.7% | — |
| LiveBench Math | — | 80.3% |
| MATH Level 5 | — | 94.7% |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-5 leads
GLM-5: 52.3 (#64), o1: 41.5 (#110)
| Benchmark | GLM-5 | o1 |
|---|---|---|
| GPQA Diamond | 87.8% | 76.8% |
| LMArena Expert | 1454 | 1361 |
| Humanity's Last Exam | — | 8% |
| SimpleQA Verified | — | 41.1% |
| Confabulations | — | 11.7% |
| Vectara Hallucination Rate | 10.1% | — |
Multimodal Not comparable
GLM-5: —, o1: 34.2 (#93)
| Benchmark | GLM-5 | o1 |
|---|---|---|
| LMArena Vision | — | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |
Multilingual GLM-5 leads
GLM-5: 53.7 (#58), o1: 48.6 (#142)
| Benchmark | GLM-5 | o1 |
|---|---|---|
| LMArena Non-English | 1430 | 1358 |
| LMArena Chinese | 1511 | 1394 |
| LMArena French | 1455 | 1344 |
| LMArena German | 1445 | 1337 |
| LMArena Japanese | 1416 | 1346 |
| LMArena Korean | 1423 | 1396 |
| LMArena Russian | 1436 | 1356 |
| LMArena Spanish | 1454 | 1345 |
Instruction Following Too close to call
GLM-5: 75.2 (#67), o1: 74.8 (#86)
| Benchmark | GLM-5 | o1 |
|---|---|---|
| LMArena Instruction Following | 1428 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
Long Context o1 leads
GLM-5: 44.7 (#60), o1: 50.3 (#9)
| Benchmark | GLM-5 | o1 |
|---|---|---|
| LMArena Longer Query | 1446 | 1378 |
| Fiction.LiveBench | — | 83.3% |
| CL-bench | 18.7% | — |
Writing & Preference GLM-5 leads
GLM-5: 66.0 (#38), o1: 55.6 (#144)
| Benchmark | GLM-5 | o1 |
|---|---|---|
| LMArena Text | 1446 | 1366 |
| LMArena Creative Writing | 1439 | 1348 |
| LMArena Multi-Turn | 1456 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| EQ-Bench Creative Writing | 1601 | — |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is GLM-5 better than o1?
GLM-5 is the stronger model overall, scoring 46.1 to 40.9 on the Noometry Index.
Which is cheaper, GLM-5 or o1?
GLM-5 is cheaper. It lists at $1 per million input tokens and $3.20 per million output tokens; o1 lists at $15 and $60.
Is GLM-5 or o1 better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 46.1 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 o1 share?
25 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and o1 has 52.