Model comparison
GLM-4.6 vs GPT-5-Codex
GLM-4.6 is the stronger model overall, scoring 40.9 to 37.3 on the Noometry Index.
Last verified . 2 shared benchmarks.
Summary
- They share 2 benchmarks with published results for both. GLM-4.6 scores higher in 1 category and GPT-5-Codex in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5-Codex leads 30.0 to 23.1.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 47.4% for GLM-4.6 and 70.3% for GPT-5-Codex.
- GLM-4.6 is cheaper at $0.60 / $2.20 per million input/output tokens, against $1.25 / $10 for GPT-5-Codex.
- GPT-5-Codex 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-Codex | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 40.9 | 37.3 |
| Released | 2025-09-30 | 2025-09-15 |
| Weights | Open | Proprietary |
| Context window | 205K | 400K |
| Max output | 131K | 128K |
| Input $ / M tokens | $0.60 | $1.25 |
| Output $ / M tokens | $2.20 | $10 |
| Results tracked | 29 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5-Codex leads
GLM-4.6: 39.9 (#137), GPT-5-Codex: 41.9 (#100)
| Benchmark | GLM-4.6 | GPT-5-Codex |
|---|---|---|
| SWE-bench Verified (bash only) | 55.4% | — |
| LMArena WebDev | 1339 | — |
| SciCode | 38.4% | — |
| WeirdML | — | 54.5% |
| LMArena Coding | 1449 | — |
| ALE-Bench | 340.82 | — |
Agentic & Tool Use GLM-4.6 leads
GLM-4.6: 32.1 (#60), GPT-5-Codex: 30.8 (#66)
| Benchmark | GLM-4.6 | GPT-5-Codex |
|---|---|---|
| Terminal-Bench | 24.5% | 44.3% |
| Berkeley Function Calling Leaderboard | 72.4% | — |
Reasoning GPT-5-Codex leads
GLM-4.6: 23.1 (#168), GPT-5-Codex: 30.0 (#80)
| Benchmark | GLM-4.6 | GPT-5-Codex |
|---|---|---|
| Kagi LLM Benchmark | 47.4% | 70.3% |
| CritPt | 1.1% | — |
| LMArena Hard Prompts | 1440 | — |
Math Not comparable
GLM-4.6: 36.4 (#115), GPT-5-Codex: —
| Benchmark | GLM-4.6 | GPT-5-Codex |
|---|---|---|
| LMArena Math | 1431 | — |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Not comparable
GLM-4.6: 39.6 (#118), GPT-5-Codex: —
| Benchmark | GLM-4.6 | GPT-5-Codex |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | — |
| LMArena Expert | 1432 | — |
Multilingual Not comparable
GLM-4.6: 53.6 (#62), GPT-5-Codex: —
| Benchmark | GLM-4.6 | GPT-5-Codex |
|---|---|---|
| LMArena Non-English | 1426 | — |
| LMArena Chinese | 1500 | — |
| LMArena French | 1459 | — |
| LMArena German | 1447 | — |
| LMArena Japanese | 1394 | — |
| LMArena Korean | 1401 | — |
| LMArena Russian | 1418 | — |
| LMArena Spanish | 1436 | — |
Instruction Following Not comparable
GLM-4.6: 74.5 (#93), GPT-5-Codex: —
| Benchmark | GLM-4.6 | GPT-5-Codex |
|---|---|---|
| LMArena Instruction Following | 1410 | — |
Long Context Not comparable
GLM-4.6: 43.4 (#91), GPT-5-Codex: —
| Benchmark | GLM-4.6 | GPT-5-Codex |
|---|---|---|
| LMArena Longer Query | 1423 | — |
Writing & Preference Not comparable
GLM-4.6: 61.3 (#86), GPT-5-Codex: —
| Benchmark | GLM-4.6 | GPT-5-Codex |
|---|---|---|
| LMArena Text | 1440 | — |
| LMArena Creative Writing | 1411 | — |
| EQ-Bench Creative Writing | 1411 | — |
| LMArena Multi-Turn | 1427 | — |
Frequently asked questions
Is GLM-4.6 better than GPT-5-Codex?
GLM-4.6 is the stronger model overall, scoring 40.9 to 37.3 on the Noometry Index.
Which is cheaper, GLM-4.6 or GPT-5-Codex?
GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; GPT-5-Codex lists at $1.25 and $10.
Is GLM-4.6 or GPT-5-Codex better for coding?
GPT-5-Codex scores higher on coding benchmarks: 41.9 versus 39.9 in the Noometry coding category.
Which has the bigger context window?
GPT-5-Codex does, with 400K tokens against 205K.
How many benchmarks do GLM-4.6 and GPT-5-Codex share?
2 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and GPT-5-Codex has 3.