Model comparison
GLM-4.6 vs GPT-5 Nano
GLM-4.6 is the stronger model overall, scoring 41.4 to 33.5 on the Noometry Index. GPT-5 Nano costs 7.3× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. GLM-4.6 scores higher in 8 categories and GPT-5 Nano in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.6 leads 61.1 to 39.1.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 72.4% for GLM-4.6 and 51.5% for GPT-5 Nano.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
- GPT-5 Nano accepts more context: 400K tokens versus 205K.
- GLM-4.6 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.6 | GPT-5 Nano | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 41.4 | 33.5 |
| Released | 2025-09-30 | 2025-08-07 |
| Weights | Open | Proprietary |
| Context window | 205K | 400K |
| Max output | 131K | 128K |
| Input $ / M tokens | $0.60 | $0.05 |
| Output $ / M tokens | $2.20 | $0.40 |
| Results tracked | 29 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6 leads
GLM-4.6: 40.1 (#148), GPT-5 Nano: 33.6 (#254)
| Benchmark | GLM-4.6 | GPT-5 Nano |
|---|---|---|
| SWE-bench Verified (bash only) | 55.4% | 34.8% |
| LMArena Coding | 1449 | 1351 |
| ALE-Bench | 340.82 | 718.67 |
| LMArena WebDev | 1340 | — |
| SciCode | 38.4% | — |
| WeirdML | — | 38.1% |
Agentic & Tool Use GLM-4.6 leads
GLM-4.6: 32.3 (#66), GPT-5 Nano: 25.8 (#106)
| Benchmark | GLM-4.6 | GPT-5 Nano |
|---|---|---|
| Terminal-Bench | 24.5% | 21.8% |
| Berkeley Function Calling Leaderboard | 72.4% | 51.5% |
Reasoning GLM-4.6 leads
GLM-4.6: 23.7 (#172), GPT-5 Nano: 16.3 (#306)
| Benchmark | GLM-4.6 | GPT-5 Nano |
|---|---|---|
| Kagi LLM Benchmark | 47.4% | 62.2% |
| LMArena Hard Prompts | 1440 | 1328 |
| ARC-AGI-2 | — | 2.6% |
| ARC-AGI-1 | — | 20.7% |
| CritPt | 1.1% | — |
| Chess Puzzles | — | 27% |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 62.7% |
| LMCA | — | 7.9% |
| Epoch Capabilities Index | — | 139.38 |
| ForecastBench | — | 59.1 |
Math GLM-4.6 leads
GLM-4.6: 39.1 (#111), GPT-5 Nano: 29.4 (#241)
| Benchmark | GLM-4.6 | GPT-5 Nano |
|---|---|---|
| LMArena Math | 1432 | 1317 |
| FrontierMath (Feb 2025 set) | 3.8% | 8.3% |
| FrontierMath Tier 4 (v1) | 2.1% | 2.1% |
| FrontierMath (Tiers 1-3) | — | 20% |
| FrontierMath Tier 4 | — | 2.4% |
| OTIS Mock AIME 2024-2025 | — | 81.1% |
| ProofBench | — | 12% |
| Omni-MATH | — | 54.6% |
| MATH Level 5 | — | 95.2% |
Knowledge GLM-4.6 leads
GLM-4.6: 40.2 (#124), GPT-5 Nano: 35.9 (#178)
| Benchmark | GLM-4.6 | GPT-5 Nano |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | 10.5% |
| LMArena Expert | 1431 | 1321 |
| GPQA Diamond | — | 69.4% |
| SimpleQA Verified | — | 11.7% |
| MMLU-Pro | — | 77.8% |
| GPQA (HELM) | — | 67.9% |
Multimodal Not comparable
GLM-4.6: —, GPT-5 Nano: 31.3 (#108)
| Benchmark | GLM-4.6 | GPT-5 Nano |
|---|---|---|
| LMArena Vision | — | 1159 |
| VPCT | — | 37.2% |
Multilingual GLM-4.6 leads
GLM-4.6: 53.5 (#66), GPT-5 Nano: 45.3 (#172)
| Benchmark | GLM-4.6 | GPT-5 Nano |
|---|---|---|
| LMArena Non-English | 1426 | 1313 |
| LMArena Chinese | 1499 | 1356 |
| LMArena German | 1447 | 1327 |
| LMArena Japanese | 1393 | 1226 |
| LMArena Korean | 1400 | 1269 |
| LMArena Russian | 1419 | 1296 |
| LMArena Spanish | 1436 | 1360 |
| LMArena French | 1459 | — |
Instruction Following Too close to call
GLM-4.6: 74.3 (#98), GPT-5 Nano: 75.0 (#79)
| Benchmark | GLM-4.6 | GPT-5 Nano |
|---|---|---|
| LMArena Instruction Following | 1410 | 1306 |
| IFEval | — | 93.2% |
Long Context GLM-4.6 leads
GLM-4.6: 43.4 (#94), GPT-5 Nano: 31.3 (#281)
| Benchmark | GLM-4.6 | GPT-5 Nano |
|---|---|---|
| LMArena Longer Query | 1422 | 1312 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference GLM-4.6 leads
GLM-4.6: 61.1 (#90), GPT-5 Nano: 39.1 (#249)
| Benchmark | GLM-4.6 | GPT-5 Nano |
|---|---|---|
| LMArena Text | 1440 | 1320 |
| LMArena Creative Writing | 1411 | 1249 |
| EQ-Bench Creative Writing | 1411 | 705 |
| LMArena Multi-Turn | 1427 | 1311 |
| WildBench | — | 80.6% |
Frequently asked questions
Is GLM-4.6 better than GPT-5 Nano?
GLM-4.6 is the stronger model overall, scoring 41.4 to 33.5 on the Noometry Index. GPT-5 Nano costs 7.3× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.
Which is cheaper, GLM-4.6 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-4.6 lists at $0.60 and $2.20.
Is GLM-4.6 or GPT-5 Nano better for coding?
GLM-4.6 scores higher on coding benchmarks: 40.1 versus 33.6 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Nano does, with 400K tokens against 205K.
How many benchmarks do GLM-4.6 and GPT-5 Nano share?
25 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and GPT-5 Nano has 49.