Model comparison
GLM-4.6 vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 61.8 to 41.4 on the Noometry Index. GLM-4.6 costs 4.0× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
Summary
- They share 23 benchmarks with published results for both. GLM-4.6 scores higher in 2 categories and GPT-6 Sol in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 74.0 to 23.7.
- The biggest single-benchmark swing is CritPt: 1.1% for GLM-4.6 and 30.9% for GPT-6 Sol.
- GLM-4.6 is cheaper at $0.60 / $2.20 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol accepts more context: 1.05M tokens versus 205K.
- GLM-4.6 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.6 | GPT-6 Sol | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 41.4 | 61.8 |
| Released | 2025-09-30 | 2026-09-22 |
| Weights | Open | Proprietary |
| Context window | 205K | 1.05M |
| Max output | 131K | 128K |
| Input $ / M tokens | $0.60 | $2 |
| Output $ / M tokens | $2.20 | $10 |
| Results tracked | 29 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
GLM-4.6: 40.1 (#148), GPT-6 Sol: 60.1 (#11)
| Benchmark | GLM-4.6 | GPT-6 Sol |
|---|---|---|
| LMArena WebDev | 1340 | 1688 |
| SciCode | 38.4% | 57.6% |
| LMArena Coding | 1449 | 1447 |
| ALE-Bench | 340.82 | 2,462 |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| SWE-bench Verified (bash only) | 55.4% | — |
Agentic & Tool Use GPT-6 Sol leads
GLM-4.6: 32.3 (#66), GPT-6 Sol: 37.2 (#36)
| Benchmark | GLM-4.6 | GPT-6 Sol |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| APEX-Agents | — | 54.3% |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| GDP.pdf | — | 26.4% |
| Vending-Bench 2 | — | 14,428 |
Reasoning GPT-6 Sol leads
GLM-4.6: 23.7 (#172), GPT-6 Sol: 74.0 (#9)
| Benchmark | GLM-4.6 | GPT-6 Sol |
|---|---|---|
| CritPt | 1.1% | 30.9% |
| LMArena Hard Prompts | 1440 | 1418 |
| ARC-AGI-2 | — | 89.6% |
| Kagi LLM Benchmark | 47.4% | — |
| NYT Connections (extended) | — | 90.1% |
| ARC-AGI-1 | — | 95.5% |
| EBR-Bench | — | 53.3% |
| Mystery Game Puzzles | — | 56% |
| DTBench | — | 97.3% |
| LMCA | — | 59.1% |
| Epoch Capabilities Index | — | 162.72 |
Math GPT-6 Sol leads
GLM-4.6: 39.1 (#111), GPT-6 Sol: 87.2 (#7)
| Benchmark | GLM-4.6 | GPT-6 Sol |
|---|---|---|
| LMArena Math | 1432 | 1402 |
| FrontierMath (Tiers 1-3) | — | 89.8% |
| FrontierMath Tier 4 | — | 90% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 83% |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GPT-6 Sol leads
GLM-4.6: 40.2 (#124), GPT-6 Sol: 64.8 (#15)
| Benchmark | GLM-4.6 | GPT-6 Sol |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | 6.5% |
| LMArena Expert | 1431 | 1439 |
| GPQA Diamond | — | 94.3% |
| SimpleQA Verified | — | 60.7% |
Multimodal Not comparable
GLM-4.6: —, GPT-6 Sol: 47.6 (#10)
| Benchmark | GLM-4.6 | GPT-6 Sol |
|---|---|---|
| LMArena Vision | — | 1245 |
| Blueprint-Bench 2 | — | 36.9% |
| Furniture Assembly | — | 58.3% |
Multilingual GLM-4.6 leads
GLM-4.6: 53.5 (#66), GPT-6 Sol: 50.5 (#118)
| Benchmark | GLM-4.6 | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1426 | 1385 |
| LMArena Chinese | 1499 | 1405 |
| LMArena French | 1459 | 1410 |
| LMArena German | 1447 | 1390 |
| LMArena Japanese | 1393 | 1385 |
| LMArena Korean | 1400 | 1341 |
| LMArena Russian | 1419 | 1401 |
| LMArena Spanish | 1436 | 1384 |
Instruction Following Too close to call
GLM-4.6: 74.3 (#98), GPT-6 Sol: 74.5 (#94)
| Benchmark | GLM-4.6 | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1410 | 1412 |
Long Context Too close to call
GLM-4.6: 43.4 (#94), GPT-6 Sol: 43.1 (#108)
| Benchmark | GLM-4.6 | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1422 | 1411 |
Writing & Preference GPT-6 Sol leads
GLM-4.6: 61.1 (#90), GPT-6 Sol: 71.9 (#18)
| Benchmark | GLM-4.6 | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1440 | 1395 |
| LMArena Creative Writing | 1411 | 1378 |
| EQ-Bench Creative Writing | 1411 | 2125 |
| LMArena Multi-Turn | 1427 | 1412 |
Frequently asked questions
Is GLM-4.6 better than GPT-6 Sol?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 41.4 on the Noometry Index. GLM-4.6 costs 4.0× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Which is cheaper, GLM-4.6 or GPT-6 Sol?
GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is GLM-4.6 or GPT-6 Sol better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 205K.
How many benchmarks do GLM-4.6 and GPT-6 Sol share?
23 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and GPT-6 Sol has 45.