Model comparison
GLM-4.7 vs GPT-5-Codex
GLM-4.7 is the stronger model overall, scoring 42.0 to 37.9 on the Noometry Index.
Last verified . 1 shared benchmarks.
Summary
- They share 1 benchmark with published results for both. GLM-4.7 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 30.9 to 24.3.
- The biggest single-benchmark swing is Terminal-Bench: 33.4% for GLM-4.7 and 44.3% for GPT-5-Codex.
- GLM-4.7 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-4.7 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.7 | GPT-5-Codex | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 42.0 | 37.9 |
| Released | 2025-12-22 | 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 | 36 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.7 leads
GLM-4.7: 44.0 (#79), GPT-5-Codex: 42.4 (#103)
| Benchmark | GLM-4.7 | GPT-5-Codex |
|---|---|---|
| LMArena WebDev | 1435 | — |
| SciCode | 45.1% | — |
| WeirdML | — | 54.5% |
| LMArena Coding | 1454 | — |
| ALE-Bench | 399.48 | — |
Agentic & Tool Use GPT-5-Codex leads
GLM-4.7: 26.5 (#103), GPT-5-Codex: 31.0 (#72)
| Benchmark | GLM-4.7 | GPT-5-Codex |
|---|---|---|
| Terminal-Bench | 33.4% | 44.3% |
| Vending-Bench 2 | 2,377 | — |
Reasoning GPT-5-Codex leads
GLM-4.7: 24.3 (#164), GPT-5-Codex: 30.9 (#83)
| Benchmark | GLM-4.7 | GPT-5-Codex |
|---|---|---|
| SimpleBench | 47.7% | — |
| Kagi LLM Benchmark | — | 70.3% |
| CritPt | 1.7% | — |
| Chess Puzzles | 6% | — |
| LMArena Hard Prompts | 1443 | — |
| Epoch Capabilities Index | 143.51 | — |
Math Not comparable
GLM-4.7: 38.6 (#135), GPT-5-Codex: —
| Benchmark | GLM-4.7 | GPT-5-Codex |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | — |
| ProofBench | 6% | — |
| LMArena Math | 1423 | — |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Not comparable
GLM-4.7: 47.0 (#80), GPT-5-Codex: —
| Benchmark | GLM-4.7 | GPT-5-Codex |
|---|---|---|
| GPQA Diamond | 83.3% | — |
| SimpleQA Verified | 32.2% | — |
| Vectara Hallucination Rate | 11.7% | — |
| LMArena Expert | 1424 | — |
Multilingual Not comparable
GLM-4.7: 52.8 (#79), GPT-5-Codex: —
| Benchmark | GLM-4.7 | GPT-5-Codex |
|---|---|---|
| LMArena Non-English | 1417 | — |
| LMArena Chinese | 1495 | — |
| LMArena French | 1432 | — |
| LMArena German | 1424 | — |
| LMArena Japanese | 1439 | — |
| LMArena Korean | 1399 | — |
| LMArena Russian | 1423 | — |
| LMArena Spanish | 1434 | — |
Instruction Following Not comparable
GLM-4.7: 74.4 (#95), GPT-5-Codex: —
| Benchmark | GLM-4.7 | GPT-5-Codex |
|---|---|---|
| LMArena Instruction Following | 1411 | — |
Long Context Not comparable
GLM-4.7: 42.8 (#116), GPT-5-Codex: —
| Benchmark | GLM-4.7 | GPT-5-Codex |
|---|---|---|
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
| LMArena Longer Query | 1432 | — |
Writing & Preference Not comparable
GLM-4.7: 60.9 (#93), GPT-5-Codex: —
| Benchmark | GLM-4.7 | GPT-5-Codex |
|---|---|---|
| LMArena Text | 1435 | — |
| LMArena Creative Writing | 1401 | — |
| EQ-Bench Creative Writing | 1413 | — |
| LMArena Multi-Turn | 1446 | — |
Frequently asked questions
Is GLM-4.7 better than GPT-5-Codex?
GLM-4.7 is the stronger model overall, scoring 42.0 to 37.9 on the Noometry Index.
Which is cheaper, GLM-4.7 or GPT-5-Codex?
GLM-4.7 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-4.7 or GPT-5-Codex better for coding?
GLM-4.7 scores higher on coding benchmarks: 44.0 versus 42.4 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-4.7 and GPT-5-Codex share?
1 benchmark has published results for both models. GLM-4.7 has 36 scored results on Noometry and GPT-5-Codex has 3.