Model comparison
GLM-4.6V vs GPT-5.1
GPT-5.1 is the stronger model overall, scoring 48.8 to 40.9 on the Noometry Index. GLM-4.6V costs 7.6× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. GLM-4.6V scores higher in 0 categories and GPT-5.1 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.1 leads 39.9 to 26.5.
- GLM-4.6V is cheaper at $0.30 / $0.90 per million input/output tokens, against $1.25 / $10 for GPT-5.1.
- GPT-5.1 accepts more context: 400K tokens versus 128K.
- GLM-4.6V has downloadable open weights; the other is API-only.
Side by side
| GLM-4.6V | GPT-5.1 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 40.9 | 48.8 |
| Released | 2025-12-08 | 2025-11-13 |
| Weights | Open | Proprietary |
| Context window | 128K | 400K |
| Max output | 33K | 128K |
| Input $ / M tokens | $0.30 | $1.25 |
| Output $ / M tokens | $0.90 | $10 |
| Results tracked | 12 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1 leads
GLM-4.6V: 40.2 (#128), GPT-5.1: 46.9 (#59)
| Benchmark | GLM-4.6V | GPT-5.1 |
|---|---|---|
| LMArena Coding | 1390 | 1454 |
| SWE-bench Verified | — | 68% |
| SWE-bench Verified (bash only) | — | 66% |
| LMArena WebDev | — | 1395 |
| SciCode | — | 43.3% |
| GSO | — | 13.7% |
| WeirdML | — | 60.8% |
| LiveBench Coding | — | 72.5% |
| ALE-Bench | — | 1,192 |
Agentic & Tool Use Not comparable
GLM-4.6V: —, GPT-5.1: 32.5 (#55)
| Benchmark | GLM-4.6V | GPT-5.1 |
|---|---|---|
| Terminal-Bench | — | 47.6% |
| DeepResearch Bench | — | 42.8% |
| LMArena Search | — | 1199 |
| Vending-Bench 2 | — | 1,473 |
Reasoning GPT-5.1 leads
GLM-4.6V: 26.5 (#117), GPT-5.1: 39.9 (#50)
| Benchmark | GLM-4.6V | GPT-5.1 |
|---|---|---|
| LMArena Hard Prompts | 1368 | 1457 |
| ARC-AGI-2 | — | 17.6% |
| SimpleBench | — | 53.2% |
| ARC-AGI-1 | — | 72.8% |
| CritPt | — | 4.9% |
| Chess Puzzles | — | 32% |
| EnigmaEval | — | 11.2% |
| LiveBench Reasoning | — | 95.8% |
| Mystery Game Puzzles | — | 19% |
| DTBench | — | 90.1% |
| LiveBench Data Analysis | — | 72.1% |
| LMCA | — | 43.9% |
| Epoch Capabilities Index | — | 149.66 |
| ForecastBench | — | 58.1 |
| LiveBench | — | 78.8% |
Math Not comparable
GLM-4.6V: —, GPT-5.1: 50.3 (#45)
| Benchmark | GLM-4.6V | GPT-5.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 88.6% |
| Omni-MATH | — | 46.4% |
| LiveBench Math | — | 94.5% |
| LMArena Math | — | 1446 |
| FrontierMath (Feb 2025 set) | — | 31% |
| FrontierMath Tier 4 (v1) | — | 12.5% |
Knowledge GPT-5.1 leads
GLM-4.6V: 37.4 (#148), GPT-5.1: 50.5 (#65)
| Benchmark | GLM-4.6V | GPT-5.1 |
|---|---|---|
| LMArena Expert | 1372 | 1470 |
| GPQA Diamond | — | 87.6% |
| Humanity's Last Exam | — | 23.7% |
| SimpleQA Verified | — | 48% |
| MMLU-Pro | — | 57.9% |
| Vectara Hallucination Rate | — | 10.9% |
| GPQA (HELM) | — | 44.2% |
Multimodal GPT-5.1 leads
GLM-4.6V: 34.2 (#83), GPT-5.1: 44.0 (#17)
| Benchmark | GLM-4.6V | GPT-5.1 |
|---|---|---|
| LMArena Vision | 1164 | 1250 |
| VPCT | — | 58.7% |
| LMArena Document | — | 1403 |
Multilingual GPT-5.1 leads
GLM-4.6V: 48.8 (#135), GPT-5.1: 54.0 (#51)
| Benchmark | GLM-4.6V | GPT-5.1 |
|---|---|---|
| LMArena Non-English | 1359 | 1431 |
| LMArena Chinese | 1426 | 1495 |
| LMArena Russian | 1341 | 1435 |
| LMArena French | — | 1451 |
| LMArena German | — | 1439 |
| LMArena Japanese | — | 1453 |
| LMArena Korean | — | 1401 |
| LMArena Spanish | — | 1430 |
Instruction Following GPT-5.1 leads
GLM-4.6V: 71.6 (#145), GPT-5.1: 84.0 (#1)
| Benchmark | GLM-4.6V | GPT-5.1 |
|---|---|---|
| LMArena Instruction Following | 1351 | 1442 |
| LiveBench Instruction Following | — | 93.3% |
| IFEval | — | 93.5% |
Long Context GPT-5.1 leads
GLM-4.6V: 41.3 (#138), GPT-5.1: 47.6 (#14)
| Benchmark | GLM-4.6V | GPT-5.1 |
|---|---|---|
| LMArena Longer Query | 1358 | 1448 |
| CL-bench | — | 23.7% |
| CL-bench Life | — | 17.3% |
Writing & Preference GPT-5.1 leads
GLM-4.6V: 56.8 (#132), GPT-5.1: 64.7 (#53)
| Benchmark | GLM-4.6V | GPT-5.1 |
|---|---|---|
| LMArena Text | 1377 | 1443 |
| LMArena Creative Writing | 1347 | 1427 |
| LMArena Multi-Turn | 1359 | 1449 |
| WildBench | — | 86.3% |
| LiveBench Language | — | 80.2% |
Frequently asked questions
Is GLM-4.6V better than GPT-5.1?
GPT-5.1 is the stronger model overall, scoring 48.8 to 40.9 on the Noometry Index. GLM-4.6V costs 7.6× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.
Which is cheaper, GLM-4.6V or GPT-5.1?
GLM-4.6V is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; GPT-5.1 lists at $1.25 and $10.
Is GLM-4.6V or GPT-5.1 better for coding?
GPT-5.1 scores higher on coding benchmarks: 46.9 versus 40.2 in the Noometry coding category.
Which has the bigger context window?
GPT-5.1 does, with 400K tokens against 128K.
How many benchmarks do GLM-4.6V and GPT-5.1 share?
12 benchmarks have published results for both models. GLM-4.6V has 12 scored results on Noometry and GPT-5.1 has 63.