Model comparison
GLM-4.6 vs GPT-4o
GLM-4.6 is the stronger model overall, scoring 41.4 to 28.6 on the Noometry Index.
Last verified . 21 shared benchmarks.
Summary
- They share 21 benchmarks with published results for both. GLM-4.6 scores higher in 9 categories and GPT-4o in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.6 leads 39.1 to 10.6.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 55.4% for GLM-4.6 and 21.6% for GPT-4o.
- GLM-4.6 is cheaper at $0.60 / $2.20 per million input/output tokens, against $2.50 / $10 for GPT-4o.
- GLM-4.6 accepts more context: 205K tokens versus 128K.
- GLM-4.6 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.6 | GPT-4o | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 41.4 | 28.6 |
| Released | 2025-09-30 | 2024-05-13 |
| Weights | Open | Proprietary |
| Context window | 205K | 128K |
| Max output | 131K | 16K |
| Input $ / M tokens | $0.60 | $2.50 |
| Output $ / M tokens | $2.20 | $10 |
| Results tracked | 29 | 72 |
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-4o: 24.8 (#328)
| Benchmark | GLM-4.6 | GPT-4o |
|---|---|---|
| SWE-bench Verified (bash only) | 55.4% | 21.6% |
| LMArena Coding | 1449 | 1297 |
| SWE-bench Verified | — | 31% |
| Aider Polyglot | — | 45.3% |
| LMArena WebDev | 1340 | — |
| SciCode | 38.4% | — |
| GSO | — | 0% |
| WeirdML | — | 25.1% |
| BigCodeBench Instruct | — | 51.1% |
| LiveBench Coding | — | 51.4% |
| BigCodeBench Complete | — | 61.1% |
| CadEval | — | 26% |
| ALE-Bench | 340.82 | — |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 72.2% |
Agentic & Tool Use GLM-4.6 leads
GLM-4.6: 32.3 (#66), GPT-4o: 21.0 (#141)
| Benchmark | GLM-4.6 | GPT-4o |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| GDPval | — | 9.9% |
| TheAgentCompany | — | 8.6% |
| Cybench | — | 12.5% |
| BALROG | — | 32.3% |
| LMArena Search | — | 1006 |
| METR Time Horizons | — | 40.8% |
Reasoning GLM-4.6 leads
GLM-4.6: 23.7 (#172), GPT-4o: 9.4 (#343)
| Benchmark | GLM-4.6 | GPT-4o |
|---|---|---|
| CritPt | 1.1% | 0% |
| LMArena Hard Prompts | 1440 | 1281 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 17.8% |
| Kagi LLM Benchmark | 47.4% | — |
| ARC-AGI-1 | — | 4.5% |
| Chess Puzzles | — | 13% |
| EnigmaEval | — | 0.8% |
| LiveBench Reasoning | — | 55.8% |
| DTBench | — | 64.5% |
| LiveBench Data Analysis | — | 60.9% |
| LMCA | — | 16.6% |
| Epoch Capabilities Index | — | 128.97 |
| ForecastBench | — | 57.7 |
| LiveBench | — | 55.3% |
Math GLM-4.6 leads
GLM-4.6: 39.1 (#111), GPT-4o: 10.6 (#312)
| Benchmark | GLM-4.6 | GPT-4o |
|---|---|---|
| LMArena Math | 1432 | 1285 |
| FrontierMath (Feb 2025 set) | 3.8% | 0.3% |
| FrontierMath (Tiers 1-3) | — | 0.4% |
| OTIS Mock AIME 2024-2025 | — | 6.4% |
| Omni-MATH | — | 29.3% |
| LiveBench Math | — | 49.5% |
| MATH Level 5 | — | 53.3% |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-4.6 leads
GLM-4.6: 40.2 (#124), GPT-4o: 28.8 (#242)
| Benchmark | GLM-4.6 | GPT-4o |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | 9.6% |
| LMArena Expert | 1431 | 1250 |
| GPQA Diamond | — | 49.2% |
| Humanity's Last Exam | — | 2.7% |
| SimpleQA Verified | — | 26% |
| MMLU-Pro | — | 71.3% |
| Confabulations | — | 15.3% |
| GPQA (HELM) | — | 52% |
| MMLU | — | 88.1% |
Multimodal Not comparable
GLM-4.6: —, GPT-4o: 34.5 (#91)
| Benchmark | GLM-4.6 | GPT-4o |
|---|---|---|
| LMArena Vision | — | 1137 |
| Video-MME | — | 71.9% |
| GeoBench | — | 71% |
| VPCT | — | 40% |
| ScienceQA | — | 88.5% |
Multilingual GLM-4.6 leads
GLM-4.6: 53.5 (#66), GPT-4o: 43.2 (#186)
| Benchmark | GLM-4.6 | GPT-4o |
|---|---|---|
| LMArena Non-English | 1426 | 1283 |
| LMArena Chinese | 1499 | 1277 |
| LMArena French | 1459 | 1304 |
| LMArena German | 1447 | 1282 |
| LMArena Japanese | 1393 | 1257 |
| LMArena Korean | 1400 | 1234 |
| LMArena Russian | 1419 | 1286 |
| LMArena Spanish | 1436 | 1292 |
Instruction Following GLM-4.6 leads
GLM-4.6: 74.3 (#98), GPT-4o: 66.6 (#207)
| Benchmark | GLM-4.6 | GPT-4o |
|---|---|---|
| LMArena Instruction Following | 1410 | 1278 |
| LiveBench Instruction Following | — | 68.6% |
| IFEval | — | 81.7% |
Long Context GLM-4.6 leads
GLM-4.6: 43.4 (#94), GPT-4o: 39.4 (#179)
| Benchmark | GLM-4.6 | GPT-4o |
|---|---|---|
| LMArena Longer Query | 1422 | 1289 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference GLM-4.6 leads
GLM-4.6: 61.1 (#90), GPT-4o: 52.6 (#166)
| Benchmark | GLM-4.6 | GPT-4o |
|---|---|---|
| LMArena Text | 1440 | 1300 |
| LMArena Creative Writing | 1411 | 1292 |
| LMArena Multi-Turn | 1427 | 1302 |
| Short-Story Creative Writing | — | 81.8% |
| EQ-Bench Creative Writing | 1411 | — |
| WildBench | — | 82.8% |
| LiveBench Language | — | 47.6% |
Frequently asked questions
Is GLM-4.6 better than GPT-4o?
GLM-4.6 is the stronger model overall, scoring 41.4 to 28.6 on the Noometry Index.
Which is cheaper, GLM-4.6 or GPT-4o?
GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; GPT-4o lists at $2.50 and $10.
Is GLM-4.6 or GPT-4o better for coding?
GLM-4.6 scores higher on coding benchmarks: 40.1 versus 24.8 in the Noometry coding category.
Which has the bigger context window?
GLM-4.6 does, with 205K tokens against 128K.
How many benchmarks do GLM-4.6 and GPT-4o share?
21 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and GPT-4o has 72.