Model comparison
GLM-5.2 vs GPT-6.1 Sol
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 51.1 on the Noometry Index. GLM-5.2 costs 1.9× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.
Last verified . 31 shared benchmarks.
Summary
- They share 31 benchmarks with published results for both. GLM-5.2 scores higher in 3 categories and GPT-6.1 Sol in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6.1 Sol leads 81.9 to 42.3.
- The biggest single-benchmark swing is ARC-AGI-2: 22.8% for GLM-5.2 and 94.2% for GPT-6.1 Sol.
- GLM-5.2 is cheaper at $1.40 / $4.40 per million input/output tokens, against $2 / $10 for GPT-6.1 Sol.
- GPT-6.1 Sol accepts more context: 1.05M tokens versus 1M.
- GLM-5.2 has downloadable open weights; the other is API-only.
Side by side
| GLM-5.2 | GPT-6.1 Sol | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 51.1 | 65.6 |
| Released | 2026-06-13 | 2026-09-29 |
| Weights | Open | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 131K | 128K |
| Input $ / M tokens | $1.40 | $2 |
| Output $ / M tokens | $4.40 | $10 |
| Results tracked | 51 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6.1 Sol leads
GLM-5.2: 51.3 (#41), GPT-6.1 Sol: 63.2 (#8)
| Benchmark | GLM-5.2 | GPT-6.1 Sol |
|---|---|---|
| DeepSWE | 43.8% | 75.2% |
| FrontierCode | 24.5% | 50.2% |
| LMArena WebDev | 1603 | 1755 |
| SciCode | 50.5% | 55.8% |
| LMArena Coding | 1485 | 1487 |
| SWE-bench Verified | 78.7% | — |
| WeirdML | 70.1% | — |
| ALE-Bench | 1,047 | — |
Agentic & Tool Use GPT-6.1 Sol leads
GLM-5.2: 32.4 (#63), GPT-6.1 Sol: 39.6 (#26)
| Benchmark | GLM-5.2 | GPT-6.1 Sol |
|---|---|---|
| APEX-Agents | 45.2% | 60% |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
| GDP.pdf | — | 32% |
| Vending-Bench 2 | 8,314 | — |
Reasoning GPT-6.1 Sol leads
GLM-5.2: 42.3 (#52), GPT-6.1 Sol: 81.9 (#2)
| Benchmark | GLM-5.2 | GPT-6.1 Sol |
|---|---|---|
| ARC-AGI-2 | 22.8% | 94.2% |
| NYT Connections (extended) | 74.3% | 95.5% |
| ARC-AGI-1 | 77% | 98.5% |
| CritPt | 20.9% | 31.7% |
| Chess Puzzles | 21% | 61% |
| EBR-Bench | 9.5% | 54.3% |
| LMArena Hard Prompts | 1480 | 1466 |
| Mystery Game Puzzles | 19% | 80% |
| Epoch Capabilities Index | 151.78 | 166.09 |
| SimpleBench | 58.8% | — |
| Kagi LLM Benchmark | 62.6% | — |
| DTBench | 93.6% | — |
| LMCA | 45.8% | — |
| Surface Evolver Bench | 55.6% | — |
Math GPT-6.1 Sol leads
GLM-5.2: 55.7 (#43), GPT-6.1 Sol: 93.7 (#1)
| Benchmark | GLM-5.2 | GPT-6.1 Sol |
|---|---|---|
| FrontierMath (Tiers 1-3) | 59.2% | 93.7% |
| FrontierMath Tier 4 | 29.3% | 100% |
| OTIS Mock AIME 2024-2025 | 86.4% | 100% |
| ProofBench | 35% | 99% |
| LMArena Math | 1482 | 1464 |
| MathArena Final-Answer Competitions | 67.6% | — |
Knowledge GPT-6.1 Sol leads
GLM-5.2: 57.1 (#40), GPT-6.1 Sol: 71.8 (#4)
| Benchmark | GLM-5.2 | GPT-6.1 Sol |
|---|---|---|
| GPQA Diamond | 91.9% | 95.4% |
| SimpleQA Verified | 34.2% | 73.9% |
| LMArena Expert | 1486 | 1502 |
Multimodal Not comparable
GLM-5.2: —, GPT-6.1 Sol: 52.7 (#5)
| Benchmark | GLM-5.2 | GPT-6.1 Sol |
|---|---|---|
| LMArena Vision | — | 1288 |
| Furniture Assembly | — | 80% |
Multilingual GLM-5.2 leads
GLM-5.2: 55.8 (#26), GPT-6.1 Sol: 54.3 (#46)
| Benchmark | GLM-5.2 | GPT-6.1 Sol |
|---|---|---|
| LMArena Non-English | 1459 | 1438 |
| LMArena Chinese | 1519 | 1477 |
| LMArena Russian | 1466 | 1455 |
| LMArena French | 1479 | — |
| LMArena German | 1468 | — |
| LMArena Japanese | 1451 | — |
| LMArena Korean | 1445 | — |
| LMArena Spanish | 1477 | — |
Instruction Following Too close to call
GLM-5.2: 76.9 (#34), GPT-6.1 Sol: 77.0 (#29)
| Benchmark | GLM-5.2 | GPT-6.1 Sol |
|---|---|---|
| LMArena Instruction Following | 1465 | 1468 |
Long Context Too close to call
GLM-5.2: 45.3 (#43), GPT-6.1 Sol: 44.9 (#54)
| Benchmark | GLM-5.2 | GPT-6.1 Sol |
|---|---|---|
| LMArena Longer Query | 1479 | 1465 |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.4 (#21), GPT-6.1 Sol: 63.6 (#63)
| Benchmark | GLM-5.2 | GPT-6.1 Sol |
|---|---|---|
| LMArena Text | 1470 | 1447 |
| LMArena Creative Writing | 1462 | 1432 |
| LMArena Multi-Turn | 1469 | 1449 |
| EQ-Bench Creative Writing | 1757 | — |
| EQ-Bench 4 | 1222 | — |
Frequently asked questions
Is GLM-5.2 better than GPT-6.1 Sol?
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 51.1 on the Noometry Index. GLM-5.2 costs 1.9× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.
Which is cheaper, GLM-5.2 or GPT-6.1 Sol?
GLM-5.2 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; GPT-6.1 Sol lists at $2 and $10.
Is GLM-5.2 or GPT-6.1 Sol better for coding?
GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 51.3 in the Noometry coding category.
Which has the bigger context window?
GPT-6.1 Sol does, with 1.05M tokens against 1M.
How many benchmarks do GLM-5.2 and GPT-6.1 Sol share?
31 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and GPT-6.1 Sol has 34.