Model comparison
GLM-4.6 vs GPT-5.1
GPT-5.1 is the stronger model overall, scoring 49.0 to 41.4 on the Noometry Index. GLM-4.6 costs 3.4× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
Summary
- They share 26 benchmarks with published results for both. GLM-4.6 scores higher in 0 categories and GPT-5.1 in 9 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.1 leads 39.8 to 23.7.
- The biggest single-benchmark swing is Terminal-Bench: 24.5% for GLM-4.6 and 47.6% for GPT-5.1.
- GLM-4.6 is cheaper at $0.60 / $2.20 per million input/output tokens, against $1.25 / $10 for GPT-5.1.
- GPT-5.1 accepts more context: 400K tokens versus 205K.
- GLM-4.6 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.6 | GPT-5.1 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 41.4 | 49.0 |
| Released | 2025-09-30 | 2025-11-13 |
| Weights | Open | Proprietary |
| Context window | 205K | 400K |
| Max output | 131K | 128K |
| Input $ / M tokens | $0.60 | $1.25 |
| Output $ / M tokens | $2.20 | $10 |
| Results tracked | 29 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1 leads
GLM-4.6: 40.1 (#148), GPT-5.1: 46.4 (#66)
| Benchmark | GLM-4.6 | GPT-5.1 |
|---|---|---|
| SWE-bench Verified (bash only) | 55.4% | 66% |
| LMArena WebDev | 1340 | 1395 |
| SciCode | 38.4% | 43.3% |
| LMArena Coding | 1449 | 1454 |
| ALE-Bench | 340.82 | 1,192 |
| SWE-bench Verified | — | 68% |
| GSO | — | 13.7% |
| WeirdML | — | 60.8% |
| LiveBench Coding | — | 72.5% |
Agentic & Tool Use Too close to call
GLM-4.6: 32.3 (#66), GPT-5.1: 32.7 (#60)
| Benchmark | GLM-4.6 | GPT-5.1 |
|---|---|---|
| Terminal-Bench | 24.5% | 47.6% |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| DeepResearch Bench | — | 42.8% |
| LMArena Search | — | 1199 |
| Vending-Bench 2 | — | 1,473 |
Reasoning GPT-5.1 leads
GLM-4.6: 23.7 (#172), GPT-5.1: 39.8 (#58)
| Benchmark | GLM-4.6 | GPT-5.1 |
|---|---|---|
| CritPt | 1.1% | 4.9% |
| LMArena Hard Prompts | 1440 | 1457 |
| ARC-AGI-2 | — | 17.6% |
| SimpleBench | — | 53.2% |
| Kagi LLM Benchmark | 47.4% | — |
| ARC-AGI-1 | — | 72.8% |
| 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 | — | 149.64 |
| ForecastBench | — | 58.1 |
| LiveBench | — | 78.8% |
Math GPT-5.1 leads
GLM-4.6: 39.1 (#111), GPT-5.1: 52.2 (#51)
| Benchmark | GLM-4.6 | GPT-5.1 |
|---|---|---|
| LMArena Math | 1432 | 1447 |
| FrontierMath (Feb 2025 set) | 3.8% | 31% |
| FrontierMath Tier 4 (v1) | 2.1% | 12.5% |
| OTIS Mock AIME 2024-2025 | — | 88.6% |
| Omni-MATH | — | 46.4% |
| LiveBench Math | — | 94.5% |
Knowledge GPT-5.1 leads
GLM-4.6: 40.2 (#124), GPT-5.1: 50.6 (#71)
| Benchmark | GLM-4.6 | GPT-5.1 |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | 10.9% |
| LMArena Expert | 1431 | 1470 |
| GPQA Diamond | — | 87.6% |
| Humanity's Last Exam | — | 23.7% |
| SimpleQA Verified | — | 48% |
| MMLU-Pro | — | 57.9% |
| GPQA (HELM) | — | 44.2% |
Multimodal Not comparable
GLM-4.6: —, GPT-5.1: 44.8 (#19)
| Benchmark | GLM-4.6 | GPT-5.1 |
|---|---|---|
| LMArena Vision | — | 1250 |
| VPCT | — | 58.7% |
| LMArena Document | — | 1403 |
Multilingual Too close to call
GLM-4.6: 53.5 (#66), GPT-5.1: 53.8 (#56)
| Benchmark | GLM-4.6 | GPT-5.1 |
|---|---|---|
| LMArena Non-English | 1426 | 1431 |
| LMArena Chinese | 1499 | 1495 |
| LMArena French | 1459 | 1450 |
| LMArena German | 1447 | 1438 |
| LMArena Japanese | 1393 | 1453 |
| LMArena Korean | 1400 | 1401 |
| LMArena Russian | 1419 | 1435 |
| LMArena Spanish | 1436 | 1433 |
Instruction Following GPT-5.1 leads
GLM-4.6: 74.3 (#98), GPT-5.1: 83.9 (#1)
| Benchmark | GLM-4.6 | GPT-5.1 |
|---|---|---|
| LMArena Instruction Following | 1410 | 1443 |
| LiveBench Instruction Following | — | 93.3% |
| IFEval | — | 93.5% |
Long Context GPT-5.1 leads
GLM-4.6: 43.4 (#94), GPT-5.1: 47.6 (#14)
| Benchmark | GLM-4.6 | GPT-5.1 |
|---|---|---|
| LMArena Longer Query | 1422 | 1447 |
| CL-bench | — | 23.7% |
| CL-bench Life | — | 17.3% |
Writing & Preference GPT-5.1 leads
GLM-4.6: 61.1 (#90), GPT-5.1: 64.5 (#55)
| Benchmark | GLM-4.6 | GPT-5.1 |
|---|---|---|
| LMArena Text | 1440 | 1443 |
| LMArena Creative Writing | 1411 | 1427 |
| LMArena Multi-Turn | 1427 | 1450 |
| EQ-Bench Creative Writing | 1411 | — |
| WildBench | — | 86.3% |
| LiveBench Language | — | 80.2% |
Frequently asked questions
Is GLM-4.6 better than GPT-5.1?
GPT-5.1 is the stronger model overall, scoring 49.0 to 41.4 on the Noometry Index. GLM-4.6 costs 3.4× 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-4.6 or GPT-5.1?
GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; GPT-5.1 lists at $1.25 and $10.
Is GLM-4.6 or GPT-5.1 better for coding?
GPT-5.1 scores higher on coding benchmarks: 46.4 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5.1 does, with 400K tokens against 205K.
How many benchmarks do GLM-4.6 and GPT-5.1 share?
26 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and GPT-5.1 has 63.