Model comparison
GLM-4.5-Air vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 61.8 to 38.9 on the Noometry Index. GLM-4.5-Air costs 9.4× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. GLM-4.5-Air scores higher in 0 categories and GPT-6 Sol in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Sol leads 87.2 to 36.2.
- GLM-4.5-Air is cheaper at $0.20 / $1.10 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol accepts more context: 1.05M tokens versus 131K.
- GLM-4.5-Air has downloadable open weights; the other is API-only.
Side by side
| GLM-4.5-Air | GPT-6 Sol | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 38.9 | 61.8 |
| Released | 2025-07-20 | 2026-09-22 |
| Weights | Open | Proprietary |
| Context window | 131K | 1.05M |
| Max output | 98K | 128K |
| Input $ / M tokens | $0.20 | $2 |
| Output $ / M tokens | $1.10 | $10 |
| Results tracked | 27 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
GLM-4.5-Air: 33.3 (#259), GPT-6 Sol: 60.1 (#11)
| Benchmark | GLM-4.5-Air | GPT-6 Sol |
|---|---|---|
| LMArena Coding | 1397 | 1447 |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| LMArena WebDev | — | 1688 |
| SciCode | — | 57.6% |
| GSO | 2.9% | — |
| ALE-Bench | — | 2,462 |
Agentic & Tool Use Not comparable
GLM-4.5-Air: —, GPT-6 Sol: 37.2 (#36)
| Benchmark | GLM-4.5-Air | GPT-6 Sol |
|---|---|---|
| APEX-Agents | — | 54.3% |
| GDP.pdf | — | 26.4% |
| Vending-Bench 2 | — | 14,428 |
Reasoning GPT-6 Sol leads
GLM-4.5-Air: 24.1 (#166), GPT-6 Sol: 74.0 (#9)
| Benchmark | GLM-4.5-Air | GPT-6 Sol |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1418 |
| ARC-AGI-2 | — | 89.6% |
| Kagi LLM Benchmark | 43% | — |
| NYT Connections (extended) | — | 90.1% |
| ARC-AGI-1 | — | 95.5% |
| CritPt | — | 30.9% |
| EBR-Bench | — | 53.3% |
| Mystery Game Puzzles | — | 56% |
| DTBench | — | 97.3% |
| LMCA | — | 59.1% |
| Epoch Capabilities Index | — | 162.72 |
| ForecastBench | 59.2 | — |
Math GPT-6 Sol leads
GLM-4.5-Air: 36.2 (#170), GPT-6 Sol: 87.2 (#7)
| Benchmark | GLM-4.5-Air | GPT-6 Sol |
|---|---|---|
| LMArena Math | 1396 | 1402 |
| FrontierMath (Tiers 1-3) | — | 89.8% |
| FrontierMath Tier 4 | — | 90% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 83% |
| Omni-MATH | 39.1% | — |
Knowledge GPT-6 Sol leads
GLM-4.5-Air: 35.0 (#191), GPT-6 Sol: 64.8 (#15)
| Benchmark | GLM-4.5-Air | GPT-6 Sol |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | 6.5% |
| LMArena Expert | 1370 | 1439 |
| GPQA Diamond | — | 94.3% |
| Humanity's Last Exam | 8.1% | — |
| SimpleQA Verified | — | 60.7% |
| MMLU-Pro | 76.2% | — |
| GPQA (HELM) | 59.4% | — |
Multimodal Not comparable
GLM-4.5-Air: —, GPT-6 Sol: 47.6 (#10)
| Benchmark | GLM-4.5-Air | GPT-6 Sol |
|---|---|---|
| LMArena Vision | — | 1245 |
| Blueprint-Bench 2 | — | 36.9% |
| Furniture Assembly | — | 58.3% |
Multilingual GPT-6 Sol leads
GLM-4.5-Air: 49.1 (#135), GPT-6 Sol: 50.5 (#118)
| Benchmark | GLM-4.5-Air | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1366 | 1385 |
| LMArena Chinese | 1426 | 1405 |
| LMArena French | 1399 | 1410 |
| LMArena German | 1377 | 1390 |
| LMArena Japanese | 1348 | 1385 |
| LMArena Korean | 1308 | 1341 |
| LMArena Russian | 1373 | 1401 |
| LMArena Spanish | 1386 | 1384 |
Instruction Following GPT-6 Sol leads
GLM-4.5-Air: 69.6 (#171), GPT-6 Sol: 74.5 (#94)
| Benchmark | GLM-4.5-Air | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1354 | 1412 |
| IFEval | 81.2% | — |
Long Context GPT-6 Sol leads
GLM-4.5-Air: 41.6 (#135), GPT-6 Sol: 43.1 (#108)
| Benchmark | GLM-4.5-Air | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1366 | 1411 |
Writing & Preference GPT-6 Sol leads
GLM-4.5-Air: 55.9 (#139), GPT-6 Sol: 71.9 (#18)
| Benchmark | GLM-4.5-Air | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1384 | 1395 |
| LMArena Creative Writing | 1343 | 1378 |
| LMArena Multi-Turn | 1371 | 1412 |
| EQ-Bench Creative Writing | — | 2125 |
| WildBench | 78.9% | — |
Frequently asked questions
Is GLM-4.5-Air better than GPT-6 Sol?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 38.9 on the Noometry Index. GLM-4.5-Air costs 9.4× 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-4.5-Air or GPT-6 Sol?
GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is GLM-4.5-Air or GPT-6 Sol better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 33.3 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 131K.
How many benchmarks do GLM-4.5-Air and GPT-6 Sol share?
18 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and GPT-6 Sol has 45.