Model comparison
GLM-4.7 vs GPT-4.1
GLM-4.7 is the stronger model overall, scoring 42.0 to 35.9 on the Noometry Index.
Last verified . 28 shared benchmarks.
Summary
- They share 28 benchmarks with published results for both. GLM-4.7 scores higher in 8 categories and GPT-4.1 in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.7 leads 38.6 to 22.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 83.3% for GLM-4.7 and 38.3% for GPT-4.1.
- GLM-4.7 is cheaper at $0.60 / $2.20 per million input/output tokens, against $2 / $8 for GPT-4.1.
- GPT-4.1 accepts more context: 1.05M tokens versus 205K.
- GLM-4.7 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.7 | GPT-4.1 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 42.0 | 35.9 |
| Released | 2025-12-22 | 2025-04-14 |
| Weights | Open | Proprietary |
| Context window | 205K | 1.05M |
| Max output | 131K | 33K |
| Input $ / M tokens | $0.60 | $2 |
| Output $ / M tokens | $2.20 | $8 |
| Results tracked | 36 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.7 leads
GLM-4.7: 44.0 (#79), GPT-4.1: 34.4 (#238)
| Benchmark | GLM-4.7 | GPT-4.1 |
|---|---|---|
| LMArena Coding | 1454 | 1391 |
| ALE-Bench | 399.48 | 558.1 |
| SWE-bench Verified | — | 48.5% |
| SWE-bench Verified (bash only) | — | 39.6% |
| Aider Polyglot | — | 52.4% |
| LMArena WebDev | 1435 | — |
| SciCode | 45.1% | — |
| WeirdML | — | 39% |
| CadEval | — | 42% |
Agentic & Tool Use GPT-4.1 leads
GLM-4.7: 26.5 (#103), GPT-4.1: 34.7 (#43)
| Benchmark | GLM-4.7 | GPT-4.1 |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| Berkeley Function Calling Leaderboard | — | 54% |
| Vending-Bench 2 | 2,377 | — |
Reasoning GLM-4.7 leads
GLM-4.7: 24.3 (#164), GPT-4.1: 11.7 (#339)
| Benchmark | GLM-4.7 | GPT-4.1 |
|---|---|---|
| SimpleBench | 47.7% | 27% |
| Chess Puzzles | 6% | 6% |
| LMArena Hard Prompts | 1443 | 1384 |
| Epoch Capabilities Index | 143.51 | 136.78 |
| ARC-AGI-2 | — | 0.4% |
| Kagi LLM Benchmark | — | 52.3% |
| ARC-AGI-1 | — | 5.5% |
| CritPt | 1.7% | — |
| EnigmaEval | — | 2.2% |
| DTBench | — | 68.3% |
| LMCA | — | 25.6% |
| ForecastBench | — | 61.5 |
Math GLM-4.7 leads
GLM-4.7: 38.6 (#135), GPT-4.1: 22.3 (#280)
| Benchmark | GLM-4.7 | GPT-4.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | 38.3% |
| LMArena Math | 1423 | 1370 |
| FrontierMath (Feb 2025 set) | 2.4% | 5.5% |
| FrontierMath Tier 4 (v1) | 0% | 0% |
| FrontierMath (Tiers 1-3) | — | 6% |
| ProofBench | 6% | — |
| Omni-MATH | — | 47.1% |
| MATH Level 5 | — | 83% |
Knowledge GLM-4.7 leads
GLM-4.7: 47.0 (#80), GPT-4.1: 37.1 (#160)
| Benchmark | GLM-4.7 | GPT-4.1 |
|---|---|---|
| GPQA Diamond | 83.3% | 66.9% |
| SimpleQA Verified | 32.2% | 31.1% |
| Vectara Hallucination Rate | 11.7% | 5.6% |
| LMArena Expert | 1424 | 1364 |
| Humanity's Last Exam | — | 5.4% |
| MMLU-Pro | — | 81.1% |
| GPQA (HELM) | — | 65.9% |
Multimodal Not comparable
GLM-4.7: —, GPT-4.1: 38.2 (#67)
| Benchmark | GLM-4.7 | GPT-4.1 |
|---|---|---|
| LMArena Vision | — | 1211 |
| GeoBench | — | 72% |
Multilingual GLM-4.7 leads
GLM-4.7: 52.8 (#79), GPT-4.1: 49.4 (#133)
| Benchmark | GLM-4.7 | GPT-4.1 |
|---|---|---|
| LMArena Non-English | 1417 | 1370 |
| LMArena Chinese | 1495 | 1382 |
| LMArena French | 1432 | 1382 |
| LMArena German | 1424 | 1381 |
| LMArena Japanese | 1439 | 1319 |
| LMArena Korean | 1399 | 1339 |
| LMArena Russian | 1423 | 1377 |
| LMArena Spanish | 1434 | 1376 |
Instruction Following GLM-4.7 leads
GLM-4.7: 74.4 (#95), GPT-4.1: 71.3 (#153)
| Benchmark | GLM-4.7 | GPT-4.1 |
|---|---|---|
| LMArena Instruction Following | 1411 | 1367 |
| IFEval | — | 83.8% |
Long Context GLM-4.7 leads
GLM-4.7: 42.8 (#116), GPT-4.1: 40.0 (#163)
| Benchmark | GLM-4.7 | GPT-4.1 |
|---|---|---|
| LMArena Longer Query | 1432 | 1385 |
| Fiction.LiveBench | — | 63.9% |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
Writing & Preference GLM-4.7 leads
GLM-4.7: 60.9 (#93), GPT-4.1: 57.6 (#125)
| Benchmark | GLM-4.7 | GPT-4.1 |
|---|---|---|
| LMArena Text | 1435 | 1383 |
| LMArena Creative Writing | 1401 | 1363 |
| EQ-Bench Creative Writing | 1413 | 1420 |
| LMArena Multi-Turn | 1446 | 1398 |
| WildBench | — | 85.4% |
Frequently asked questions
Is GLM-4.7 better than GPT-4.1?
GLM-4.7 is the stronger model overall, scoring 42.0 to 35.9 on the Noometry Index.
Which is cheaper, GLM-4.7 or GPT-4.1?
GLM-4.7 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; GPT-4.1 lists at $2 and $8.
Is GLM-4.7 or GPT-4.1 better for coding?
GLM-4.7 scores higher on coding benchmarks: 44.0 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 does, with 1.05M tokens against 205K.
How many benchmarks do GLM-4.7 and GPT-4.1 share?
28 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and GPT-4.1 has 52.