GLM-5.2 vs GPT-5.3 Codex
GLM-5.2 
GPT-5.3 Codex Verdict
- GPT-5.3 Codex (xhigh) leads on quality: 65.4 vs 63.9.
- GLM-5.2 (max) is stronger in coding, composite, human preference, maths.
- GPT-5.3 Codex (xhigh) is stronger in agents & tools, instruction following, knowledge, long context, reasoning, multimodal.
- GLM-5.2 (max) is 2.2× cheaper ($2.15 vs $4.81 per 1M blended).
- GPT-5.3 Codex (xhigh) streams 1.7× faster (125 vs 71 tokens per second).
| Metric | GLM-5.2 (max) | GPT-5.3 Codex (xhigh) |
|---|---|---|
| BenchLeader Index | 63.9 | 65.4 |
| Agents & tools score | 63.8 | 79.8 |
| Coding score | 63.8 | 61.7 |
| Composite score | 72.1 | 70.2 |
| Human preference score | 67.2 | – |
| Instruction following score | 71.6 | 73.4 |
| Knowledge score | 55.5 | 69.4 |
| Long context score | 65.6 | 68.2 |
| Maths score | 59.0 | – |
| Reasoning score | 72.9 | 74.4 |
| Multimodal score | – | 63.0 |
| Blended price $/M | $2.15 | $4.81 |
| Output speed | 71 tok/s | 125 tok/s |
| Time to first answer | 31.6 s | 50.8 s |
| Context window | 1M | 400k |
| GPQA Diamond | 91.9% | – |
| FrontierMath Tiers 1–3 | 59.2% | – |
| FrontierMath Tier 4 | 29.3% | – |
| OTIS Mock AIME | 86.4% | – |
| SWE-bench Verified (Epoch) | 78.7% | – |
| SimpleQA Verified | 34.2% | – |
| SciCode | 50.5% | – |
| WeirdML | 70.1% | 77.9% |
| ProofBench | 35.0% | – |
| LMArena Text | 1472 | – |
| LMArena Hard Prompts | 1493 | – |
| LMArena Coding | 1510 | – |
| LMArena WebDev | 1592 | – |
| LMArena Agent | 4.4 | – |
| AA Intelligence Index | 34.0 | 32.5 |
| IFBench | 73.3% | 75.4% |
| AA-LCR | 78.3% | 83.3% |
| MMMU-Pro | – | 78.5% |
| AA-Omniscience | 4.4 | 10.9 |
| Terminal-Bench Hard | 50.8% | 53.0% |
| GPQA Diamond (AA) | 89.5% | 91.5% |
| Humanity's Last Exam (AA) | 41.1% | 42.5% |
| SciCode (AA) | 51.2% | – |
| τ²-Bench Telecom (AA) | 99.1% | 86.0% |
| LiveCodeBench | – | 87.3% |
| IOI | – | 53.8% |
| Terminal-Bench 2.1 (Vals) | 67.8% | – |
| SWE-bench (Vals) | 82.8% | 78.0% |
| CritPt | 20.9% | 16.9% |
| GDPval (AA) | 45.3% | – |
| τ²-Bench Banking (AA) | 34.6% | – |
| ITBench SRE (AA) | 42.7% | – |
| APEX-Agents (AA) | 33.7% | – |
| Code Migration | 37.9% | – |
| Harvey's Legal Agent Benchmark | 7.1% | – |
| Legal Research Bench | 31.3% | – |
| ProgramBench | 0.5% | – |
| SkillsBench | 45.1% | – |
| SREBench | 0.0% | – |
| Vibe Code Bench v1.1 | 64.0% | 61.8% |
| LMArena Maths | 1480 | – |
| LMArena Creative Writing | 1451 | – |
| LMArena Instruction Following | 1466 | – |
| LMArena Multi-turn | 1469 | – |
| LMArena Longer Queries | 1483 | – |
| Chess Puzzles | 21.0% | – |
| EBR-bench | 9.5% | – |
| PostTrainBench | 31.7% | – |
| DeepSWE | 43.8% | – |
| LMCA | 45.8% | – |
| DTBench | 93.6% | – |
| CursorBench | 55.0% | – |
| ALE-Bench | 1010.2 | 1655.2 |
Data as of 2026-09-19. Best configuration of each model; every score links to its source on the model pages.
GLM-5.2 vs GPT-5.3 Codex: questions
- Is GLM-5.2 better than GPT-5.3 Codex?
- GPT-5.3 Codex (xhigh) leads on quality: 65.4 vs 63.9. The BenchLeader Index combines every independent quality benchmark; GPT-5.3 Codex (xhigh) is ahead overall as of 2026-09-19, but check the category scores for your use.
- Is GLM-5.2 better than GPT-5.3 Codex for coding?
- GLM-5.2 scores higher in coding (64 vs 62 on the category index, where 50 is average).
- Is GLM-5.2 better than GPT-5.3 Codex for agentic tasks?
- GPT-5.3 Codex scores higher in agentic tasks (80 vs 64 on the category index, where 50 is average).
- Which is cheaper, GLM-5.2 or GPT-5.3 Codex?
- GLM-5.2 is cheaper: $2.15 against $4.81 per million tokens, blended at three input tokens per output token.
- Which is faster, GLM-5.2 or GPT-5.3 Codex?
- GPT-5.3 Codex streams faster: 125 against 71 output tokens per second.
- Which has the larger context window?
- GLM-5.2 accepts more context: 1M against 400k tokens.