Model comparison
GLM-5.2 vs GPT-5 Nano
GLM-5.2 is the stronger model overall, scoring 51.1 to 33.5 on the Noometry Index. GPT-5 Nano costs 16× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.
Last verified . 33 shared benchmarks.
Summary
- They share 33 benchmarks with published results for both. GLM-5.2 scores higher in 9 categories and GPT-5 Nano in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5.2 leads 70.4 to 39.1.
- The biggest single-benchmark swing is ARC-AGI-1: 77% for GLM-5.2 and 20.7% for GPT-5 Nano.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $1.40 / $4.40 for GLM-5.2.
- GLM-5.2 accepts more context: 1M tokens versus 400K.
- GLM-5.2 has downloadable open weights; the other is API-only.
Side by side
| GLM-5.2 | GPT-5 Nano | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 51.1 | 33.5 |
| Released | 2026-06-13 | 2025-08-07 |
| Weights | Open | Proprietary |
| Context window | 1M | 400K |
| Max output | 131K | 128K |
| Input $ / M tokens | $1.40 | $0.05 |
| Output $ / M tokens | $4.40 | $0.40 |
| Results tracked | 51 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.2 leads
GLM-5.2: 51.3 (#41), GPT-5 Nano: 33.6 (#254)
| Benchmark | GLM-5.2 | GPT-5 Nano |
|---|---|---|
| WeirdML | 70.1% | 38.1% |
| LMArena Coding | 1485 | 1351 |
| ALE-Bench | 1,047 | 718.67 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| SWE-bench Verified (bash only) | — | 34.8% |
| LMArena WebDev | 1603 | — |
| SciCode | 50.5% | — |
Agentic & Tool Use GLM-5.2 leads
GLM-5.2: 32.4 (#63), GPT-5 Nano: 25.8 (#106)
| Benchmark | GLM-5.2 | GPT-5 Nano |
|---|---|---|
| Terminal-Bench | — | 21.8% |
| APEX-Agents | 45.2% | — |
| Berkeley Function Calling Leaderboard | — | 51.5% |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 8,314 | — |
Reasoning GLM-5.2 leads
GLM-5.2: 42.3 (#52), GPT-5 Nano: 16.3 (#306)
| Benchmark | GLM-5.2 | GPT-5 Nano |
|---|---|---|
| ARC-AGI-2 | 22.8% | 2.6% |
| Kagi LLM Benchmark | 62.6% | 62.2% |
| ARC-AGI-1 | 77% | 20.7% |
| Chess Puzzles | 21% | 27% |
| LMArena Hard Prompts | 1480 | 1328 |
| Mystery Game Puzzles | 19% | 9% |
| DTBench | 93.6% | 62.7% |
| LMCA | 45.8% | 7.9% |
| Epoch Capabilities Index | 151.78 | 139.38 |
| SimpleBench | 58.8% | — |
| NYT Connections (extended) | 74.3% | — |
| CritPt | 20.9% | — |
| EBR-Bench | 9.5% | — |
| Surface Evolver Bench | 55.6% | — |
| ForecastBench | — | 59.1 |
Math GLM-5.2 leads
GLM-5.2: 55.7 (#43), GPT-5 Nano: 29.4 (#241)
| Benchmark | GLM-5.2 | GPT-5 Nano |
|---|---|---|
| FrontierMath (Tiers 1-3) | 59.2% | 20% |
| FrontierMath Tier 4 | 29.3% | 2.4% |
| OTIS Mock AIME 2024-2025 | 86.4% | 81.1% |
| ProofBench | 35% | 12% |
| LMArena Math | 1482 | 1317 |
| MathArena Final-Answer Competitions | 67.6% | — |
| Omni-MATH | — | 54.6% |
| MATH Level 5 | — | 95.2% |
| FrontierMath (Feb 2025 set) | — | 8.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GLM-5.2 leads
GLM-5.2: 57.1 (#40), GPT-5 Nano: 35.9 (#178)
| Benchmark | GLM-5.2 | GPT-5 Nano |
|---|---|---|
| GPQA Diamond | 91.9% | 69.4% |
| SimpleQA Verified | 34.2% | 11.7% |
| LMArena Expert | 1486 | 1321 |
| MMLU-Pro | — | 77.8% |
| Vectara Hallucination Rate | — | 10.5% |
| GPQA (HELM) | — | 67.9% |
Multimodal Not comparable
GLM-5.2: —, GPT-5 Nano: 31.3 (#108)
| Benchmark | GLM-5.2 | GPT-5 Nano |
|---|---|---|
| LMArena Vision | — | 1159 |
| VPCT | — | 37.2% |
Multilingual GLM-5.2 leads
GLM-5.2: 55.8 (#26), GPT-5 Nano: 45.3 (#172)
| Benchmark | GLM-5.2 | GPT-5 Nano |
|---|---|---|
| LMArena Non-English | 1459 | 1313 |
| LMArena Chinese | 1519 | 1356 |
| LMArena German | 1468 | 1327 |
| LMArena Japanese | 1451 | 1226 |
| LMArena Korean | 1445 | 1269 |
| LMArena Russian | 1466 | 1296 |
| LMArena Spanish | 1477 | 1360 |
| LMArena French | 1479 | — |
Instruction Following GLM-5.2 leads
GLM-5.2: 76.9 (#34), GPT-5 Nano: 75.0 (#79)
| Benchmark | GLM-5.2 | GPT-5 Nano |
|---|---|---|
| LMArena Instruction Following | 1465 | 1306 |
| IFEval | — | 93.2% |
Long Context GLM-5.2 leads
GLM-5.2: 45.3 (#43), GPT-5 Nano: 31.3 (#281)
| Benchmark | GLM-5.2 | GPT-5 Nano |
|---|---|---|
| LMArena Longer Query | 1479 | 1312 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.4 (#21), GPT-5 Nano: 39.1 (#249)
| Benchmark | GLM-5.2 | GPT-5 Nano |
|---|---|---|
| LMArena Text | 1470 | 1320 |
| LMArena Creative Writing | 1462 | 1249 |
| EQ-Bench Creative Writing | 1757 | 705 |
| LMArena Multi-Turn | 1469 | 1311 |
| WildBench | — | 80.6% |
| EQ-Bench 4 | 1222 | — |
Frequently asked questions
Is GLM-5.2 better than GPT-5 Nano?
GLM-5.2 is the stronger model overall, scoring 51.1 to 33.5 on the Noometry Index. GPT-5 Nano costs 16× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.
Which is cheaper, GLM-5.2 or GPT-5 Nano?
GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; GLM-5.2 lists at $1.40 and $4.40.
Is GLM-5.2 or GPT-5 Nano better for coding?
GLM-5.2 scores higher on coding benchmarks: 51.3 versus 33.6 in the Noometry coding category.
Which has the bigger context window?
GLM-5.2 does, with 1M tokens against 400K.
How many benchmarks do GLM-5.2 and GPT-5 Nano share?
33 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and GPT-5 Nano has 49.