Model comparison
GLM-5.1 vs GPT-5.2 Codex
GLM-5.1 is the stronger model overall, scoring 47.6 to 42.2 on the Noometry Index.
Last verified . 2 shared benchmarks.
Summary
- They share 2 benchmarks with published results for both. GLM-5.1 scores higher in 1 category and GPT-5.2 Codex in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where GPT-5.2 Codex leads 40.7 to 24.8.
- GLM-5.1 is cheaper at $1.40 / $4.40 per million input/output tokens, against $1.75 / $14 for GPT-5.2 Codex.
- GPT-5.2 Codex accepts more context: 400K tokens versus 200K.
- GLM-5.1 has downloadable open weights; the other is API-only.
Side by side
| GLM-5.1 | GPT-5.2 Codex | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 47.6 | 42.2 |
| Released | 2026-04-07 | 2025-12-18 |
| Weights | Open | Proprietary |
| Context window | 200K | 400K |
| Max output | 131K | 128K |
| Input $ / M tokens | $1.40 | $1.75 |
| Output $ / M tokens | $4.40 | $14 |
| Results tracked | 41 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
GLM-5.1: 48.5 (#52), GPT-5.2 Codex: 45.4 (#66)
| Benchmark | GLM-5.1 | GPT-5.2 Codex |
|---|---|---|
| LMArena WebDev | 1509 | 1339 |
| ALE-Bench | 887.1 | 1,300 |
| SWE-bench Verified | 74.2% | — |
| SWE-bench Verified (bash only) | — | 72.8% |
| SWE-bench Multilingual | — | 66.3% |
| SciCode | 43.8% | — |
| WeirdML | 57.1% | — |
| LMArena Coding | 1486 | — |
Agentic & Tool Use GPT-5.2 Codex leads
GLM-5.1: 24.8 (#106), GPT-5.2 Codex: 40.7 (#20)
| Benchmark | GLM-5.1 | GPT-5.2 Codex |
|---|---|---|
| Terminal-Bench | — | 66.5% |
| APEX-Agents | 40.9% | — |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |
Reasoning Not comparable
GLM-5.1: 38.2 (#57), GPT-5.2 Codex: —
| Benchmark | GLM-5.1 | GPT-5.2 Codex |
|---|---|---|
| SimpleBench | 55.1% | — |
| NYT Connections (extended) | 77.7% | — |
| CritPt | 4.6% | — |
| Chess Puzzles | 19% | — |
| Thematic Generalization | 69.8% | — |
| LMArena Hard Prompts | 1472 | — |
| Epoch Capabilities Index | 149.86 | — |
Math Not comparable
GLM-5.1: 49.0 (#48), GPT-5.2 Codex: —
| Benchmark | GLM-5.1 | GPT-5.2 Codex |
|---|---|---|
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |
| ProofBench | 22.2% | — |
| LMArena Math | 1472 | — |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge Not comparable
GLM-5.1: 55.0 (#45), GPT-5.2 Codex: —
| Benchmark | GLM-5.1 | GPT-5.2 Codex |
|---|---|---|
| GPQA Diamond | 89.9% | — |
| SimpleQA Verified | 34% | — |
| LMArena Expert | 1477 | — |
Multilingual Not comparable
GLM-5.1: 55.2 (#34), GPT-5.2 Codex: —
| Benchmark | GLM-5.1 | GPT-5.2 Codex |
|---|---|---|
| LMArena Non-English | 1448 | — |
| LMArena Chinese | 1516 | — |
| LMArena French | 1478 | — |
| LMArena German | 1466 | — |
| LMArena Japanese | 1436 | — |
| LMArena Korean | 1423 | — |
| LMArena Russian | 1453 | — |
| LMArena Spanish | 1467 | — |
Instruction Following Not comparable
GLM-5.1: 76.5 (#41), GPT-5.2 Codex: —
| Benchmark | GLM-5.1 | GPT-5.2 Codex |
|---|---|---|
| LMArena Instruction Following | 1451 | — |
Long Context Not comparable
GLM-5.1: 44.9 (#51), GPT-5.2 Codex: —
| Benchmark | GLM-5.1 | GPT-5.2 Codex |
|---|---|---|
| LMArena Longer Query | 1467 | — |
Writing & Preference Not comparable
GLM-5.1: 67.2 (#29), GPT-5.2 Codex: —
| Benchmark | GLM-5.1 | GPT-5.2 Codex |
|---|---|---|
| LMArena Text | 1462 | — |
| LMArena Creative Writing | 1454 | — |
| EQ-Bench Creative Writing | 1592 | — |
| LMArena Multi-Turn | 1473 | — |
Frequently asked questions
Is GLM-5.1 better than GPT-5.2 Codex?
GLM-5.1 is the stronger model overall, scoring 47.6 to 42.2 on the Noometry Index.
Which is cheaper, GLM-5.1 or GPT-5.2 Codex?
GLM-5.1 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; GPT-5.2 Codex lists at $1.75 and $14.
Is GLM-5.1 or GPT-5.2 Codex better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.5 versus 45.4 in the Noometry coding category.
Which has the bigger context window?
GPT-5.2 Codex does, with 400K tokens against 200K.
How many benchmarks do GLM-5.1 and GPT-5.2 Codex share?
2 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and GPT-5.2 Codex has 5.