Model comparison
GLM-5.1 vs GPT-6.1 Sol
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 47.8 on the Noometry Index. GLM-5.1 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 . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. GLM-5.1 scores higher in 3 categories and GPT-6.1 Sol in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 49.7.
- The biggest single-benchmark swing is ProofBench: 22.2% for GLM-5.1 and 99% for GPT-6.1 Sol.
- GLM-5.1 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 200K.
- GLM-5.1 has downloadable open weights; the other is API-only.
Side by side
| GLM-5.1 | GPT-6.1 Sol | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 47.8 | 65.6 |
| Released | 2026-04-07 | 2026-09-29 |
| Weights | Open | Proprietary |
| Context window | 200K | 1.05M |
| Max output | 131K | 128K |
| Input $ / M tokens | $1.40 | $2 |
| Output $ / M tokens | $4.40 | $10 |
| Results tracked | 41 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6.1 Sol leads
GLM-5.1: 48.7 (#55), GPT-6.1 Sol: 63.2 (#8)
| Benchmark | GLM-5.1 | GPT-6.1 Sol |
|---|---|---|
| LMArena WebDev | 1508 | 1755 |
| SciCode | 43.8% | 55.8% |
| LMArena Coding | 1485 | 1487 |
| SWE-bench Verified | 74.2% | — |
| DeepSWE | — | 75.2% |
| FrontierCode | — | 50.2% |
| WeirdML | 57.1% | — |
| ALE-Bench | 887.1 | — |
Agentic & Tool Use GPT-6.1 Sol leads
GLM-5.1: 24.9 (#113), GPT-6.1 Sol: 39.6 (#26)
| Benchmark | GLM-5.1 | GPT-6.1 Sol |
|---|---|---|
| APEX-Agents | 40.9% | 60% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| GDP.pdf | — | 32% |
| Vending-Bench 2 | 5,634 | — |
Reasoning GPT-6.1 Sol leads
GLM-5.1: 39.1 (#60), GPT-6.1 Sol: 81.9 (#2)
| Benchmark | GLM-5.1 | GPT-6.1 Sol |
|---|---|---|
| NYT Connections (extended) | 77.7% | 95.5% |
| CritPt | 4.6% | 31.7% |
| Chess Puzzles | 19% | 61% |
| LMArena Hard Prompts | 1472 | 1466 |
| Epoch Capabilities Index | 149.84 | 166.09 |
| ARC-AGI-2 | — | 94.2% |
| SimpleBench | 55.1% | — |
| ARC-AGI-1 | — | 98.5% |
| Thematic Generalization | 69.8% | — |
| EBR-Bench | — | 54.3% |
| Mystery Game Puzzles | — | 80% |
Math GPT-6.1 Sol leads
GLM-5.1: 49.7 (#60), GPT-6.1 Sol: 93.7 (#1)
| Benchmark | GLM-5.1 | GPT-6.1 Sol |
|---|---|---|
| FrontierMath (Tiers 1-3) | 36.8% | 93.7% |
| OTIS Mock AIME 2024-2025 | 93.3% | 100% |
| ProofBench | 22.2% | 99% |
| LMArena Math | 1473 | 1464 |
| FrontierMath Tier 4 | — | 100% |
| MathArena Final-Answer Competitions | 67.1% | — |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GPT-6.1 Sol leads
GLM-5.1: 54.9 (#50), GPT-6.1 Sol: 71.8 (#4)
| Benchmark | GLM-5.1 | GPT-6.1 Sol |
|---|---|---|
| GPQA Diamond | 89.9% | 95.4% |
| SimpleQA Verified | 34% | 73.9% |
| LMArena Expert | 1476 | 1502 |
Multimodal Not comparable
GLM-5.1: —, GPT-6.1 Sol: 52.7 (#5)
| Benchmark | GLM-5.1 | GPT-6.1 Sol |
|---|---|---|
| LMArena Vision | — | 1288 |
| Furniture Assembly | — | 80% |
Multilingual Too close to call
GLM-5.1: 55.0 (#36), GPT-6.1 Sol: 54.3 (#46)
| Benchmark | GLM-5.1 | GPT-6.1 Sol |
|---|---|---|
| LMArena Non-English | 1447 | 1438 |
| LMArena Chinese | 1515 | 1477 |
| LMArena Russian | 1454 | 1455 |
| LMArena French | 1474 | — |
| LMArena German | 1465 | — |
| LMArena Japanese | 1434 | — |
| LMArena Korean | 1418 | — |
| LMArena Spanish | 1469 | — |
Instruction Following Too close to call
GLM-5.1: 76.3 (#42), GPT-6.1 Sol: 77.0 (#29)
| Benchmark | GLM-5.1 | GPT-6.1 Sol |
|---|---|---|
| LMArena Instruction Following | 1451 | 1468 |
Long Context Too close to call
GLM-5.1: 44.9 (#53), GPT-6.1 Sol: 44.9 (#54)
| Benchmark | GLM-5.1 | GPT-6.1 Sol |
|---|---|---|
| LMArena Longer Query | 1466 | 1465 |
Writing & Preference GLM-5.1 leads
GLM-5.1: 66.9 (#31), GPT-6.1 Sol: 63.6 (#63)
| Benchmark | GLM-5.1 | GPT-6.1 Sol |
|---|---|---|
| LMArena Text | 1461 | 1447 |
| LMArena Creative Writing | 1453 | 1432 |
| LMArena Multi-Turn | 1472 | 1449 |
| EQ-Bench Creative Writing | 1592 | — |
Frequently asked questions
Is GLM-5.1 better than GPT-6.1 Sol?
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 47.8 on the Noometry Index. GLM-5.1 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-5.1 or GPT-6.1 Sol?
GLM-5.1 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-5.1 or GPT-6.1 Sol better for coding?
GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 48.7 in the Noometry coding category.
Which has the bigger context window?
GPT-6.1 Sol does, with 1.05M tokens against 200K.
How many benchmarks do GLM-5.1 and GPT-6.1 Sol share?
24 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and GPT-6.1 Sol has 34.