Model comparison
GLM-4.7 vs o1
GLM-4.7 is the stronger model overall, scoring 42.0 to 40.9 on the Noometry Index.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. GLM-4.7 scores higher in 5 categories and o1 in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where o1 leads 50.3 to 42.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 83.3% for GLM-4.7 and 73.3% for o1.
- GLM-4.7 is cheaper at $0.60 / $2.20 per million input/output tokens, against $15 / $60 for o1.
- GLM-4.7 accepts more context: 205K tokens versus 200K.
- GLM-4.7 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.7 | o1 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 42.0 | 40.9 |
| Released | 2025-12-22 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 205K | 200K |
| Max output | 131K | 100K |
| Input $ / M tokens | $0.60 | $15 |
| Output $ / M tokens | $2.20 | $60 |
| Results tracked | 36 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
GLM-4.7: 44.0 (#79), o1: 46.1 (#70)
| Benchmark | GLM-4.7 | o1 |
|---|---|---|
| LMArena Coding | 1454 | 1367 |
| Aider Polyglot | — | 61.7% |
| LMArena WebDev | 1435 | — |
| SciCode | 45.1% | — |
| WeirdML | — | 47.6% |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| ALE-Bench | 399.48 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use GLM-4.7 leads
GLM-4.7: 26.5 (#103), o1: 24.6 (#117)
| Benchmark | GLM-4.7 | o1 |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| Cybench | — | 10% |
| METR Time Horizons | — | 51.1% |
| Vending-Bench 2 | 2,377 | — |
Reasoning o1 leads
GLM-4.7: 24.3 (#164), o1: 27.9 (#111)
| Benchmark | GLM-4.7 | o1 |
|---|---|---|
| SimpleBench | 47.7% | 41.7% |
| Chess Puzzles | 6% | 15% |
| LMArena Hard Prompts | 1443 | 1371 |
| Epoch Capabilities Index | 143.51 | 141.91 |
| ARC-AGI-1 | — | 30.7% |
| CritPt | 1.7% | — |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| DTBench | — | 74.7% |
| LiveBench Data Analysis | — | 65.5% |
| LMCA | — | 22.3% |
| LiveBench | — | 75.7% |
Math GLM-4.7 leads
GLM-4.7: 38.6 (#135), o1: 36.1 (#175)
| Benchmark | GLM-4.7 | o1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | 73.3% |
| LMArena Math | 1423 | 1388 |
| FrontierMath (Feb 2025 set) | 2.4% | 9.3% |
| FrontierMath (Tiers 1-3) | — | 14.7% |
| ProofBench | 6% | — |
| LiveBench Math | — | 80.3% |
| MATH Level 5 | — | 94.7% |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GLM-4.7 leads
GLM-4.7: 47.0 (#80), o1: 41.5 (#110)
| Benchmark | GLM-4.7 | o1 |
|---|---|---|
| GPQA Diamond | 83.3% | 76.8% |
| SimpleQA Verified | 32.2% | 41.1% |
| LMArena Expert | 1424 | 1361 |
| Humanity's Last Exam | — | 8% |
| Confabulations | — | 11.7% |
| Vectara Hallucination Rate | 11.7% | — |
Multimodal Not comparable
GLM-4.7: —, o1: 34.2 (#93)
| Benchmark | GLM-4.7 | o1 |
|---|---|---|
| LMArena Vision | — | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |
Multilingual GLM-4.7 leads
GLM-4.7: 52.8 (#79), o1: 48.6 (#142)
| Benchmark | GLM-4.7 | o1 |
|---|---|---|
| LMArena Non-English | 1417 | 1358 |
| LMArena Chinese | 1495 | 1394 |
| LMArena French | 1432 | 1344 |
| LMArena German | 1424 | 1337 |
| LMArena Japanese | 1439 | 1346 |
| LMArena Korean | 1399 | 1396 |
| LMArena Russian | 1423 | 1356 |
| LMArena Spanish | 1434 | 1345 |
Instruction Following Too close to call
GLM-4.7: 74.4 (#95), o1: 74.8 (#86)
| Benchmark | GLM-4.7 | o1 |
|---|---|---|
| LMArena Instruction Following | 1411 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
Long Context o1 leads
GLM-4.7: 42.8 (#116), o1: 50.3 (#9)
| Benchmark | GLM-4.7 | o1 |
|---|---|---|
| LMArena Longer Query | 1432 | 1378 |
| Fiction.LiveBench | — | 83.3% |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
Writing & Preference GLM-4.7 leads
GLM-4.7: 60.9 (#93), o1: 55.6 (#144)
| Benchmark | GLM-4.7 | o1 |
|---|---|---|
| LMArena Text | 1435 | 1366 |
| LMArena Creative Writing | 1401 | 1348 |
| LMArena Multi-Turn | 1446 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| EQ-Bench Creative Writing | 1413 | — |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is GLM-4.7 better than o1?
GLM-4.7 is the stronger model overall, scoring 42.0 to 40.9 on the Noometry Index.
Which is cheaper, GLM-4.7 or o1?
GLM-4.7 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; o1 lists at $15 and $60.
Is GLM-4.7 or o1 better for coding?
o1 scores higher on coding benchmarks: 46.1 versus 44.0 in the Noometry coding category.
Which has the bigger context window?
GLM-4.7 does, with 205K tokens against 200K.
How many benchmarks do GLM-4.7 and o1 share?
24 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and o1 has 52.