GPT-5.2-Codex vs Grok 4.3
GPT-5.2-Codex 
Grok 4.3 Verdict
- GPT-5.2-Codex and Grok 4.3 (medium) are level on quality (60.8 vs 60.7).
- GPT-5.2-Codex is stronger in agents & tools, coding, long context, multimodal.
- Grok 4.3 (medium) is stronger in composite, instruction following, knowledge.
- Grok 4.3 (medium) is 3.1× cheaper ($1.56 vs $4.81 per 1M blended).
- Grok 4.3 (medium) streams 4.5× faster (112 vs 25 tokens per second).
| Metric | GPT-5.2-Codex | Grok 4.3 (medium) |
|---|---|---|
| BenchLeader Index | 60.8 | 60.7 |
| Agents & tools score | 63.5 | 60.1 |
| Coding score | 55.7 | – |
| Composite score | 56.8 | 60.3 |
| Instruction following score | 75.1 | 80.0 |
| Knowledge score | 63.1 | 72.1 |
| Long context score | 67.8 | 64.0 |
| Multimodal score | 60.7 | 60.2 |
| Blended price $/M | $4.81 | $1.56 |
| Output speed | 25 tok/s | 112 tok/s |
| Time to first answer | 6.7 s | 12.1 s |
| Context window | 400k | 1M |
| Terminal-Bench | 66.5% | – |
| APEX-Agents | 27.6% | – |
| LMArena WebDev | 1339 | – |
| LiveBench | 74.0% | – |
| LiveBench Reasoning | 77.7% | – |
| LiveBench Coding | 83.6% | – |
| LiveBench Agentic Coding | 49.4% | – |
| LiveBench Mathematics | 88.8% | – |
| LiveBench Data Analysis | 78.2% | – |
| LiveBench Language | 73.7% | – |
| AA Intelligence Index | 28.5 | 24.8 |
| IFBench | 77.6% | 83.3% |
| AA-LCR | 82.3% | 75.0% |
| MMMU-Pro | 76.3% | 75.8% |
| AA-Omniscience | -2.2 | 16.7 |
| Terminal-Bench Hard | 37.1% | 30.3% |
| GPQA Diamond (AA) | 89.9% | 89.0% |
| Humanity's Last Exam (AA) | 35.7% | 30.0% |
| τ²-Bench Telecom (AA) | 92.1% | 91.2% |
| LiveCodeBench | 88.0% | – |
| SWE-Bench Pro | 41.0% | – |
| SWE-bench Verified (bash only) | 72.8% | – |
| SWE-bench Verified (any scaffold) | 72.8% | – |
Data as of 2026-09-10. Best configuration of each model; every score links to its source on the model pages.
GPT-5.2-Codex vs Grok 4.3: questions
- Is GPT-5.2-Codex better than Grok 4.3?
- GPT-5.2-Codex and Grok 4.3 (medium) are level on quality (60.8 vs 60.7). The BenchLeader Index combines every independent quality benchmark; GPT-5.2-Codex is ahead overall as of 2026-09-10, but check the category scores for your use.
- Is GPT-5.2-Codex better than Grok 4.3 for agentic tasks?
- GPT-5.2-Codex scores higher in agentic tasks (64 vs 60 on the category index, where 50 is average).
- Which is cheaper, GPT-5.2-Codex or Grok 4.3?
- Grok 4.3 is cheaper: $1.56 against $4.81 per million tokens, blended at three input tokens per output token.
- Which is faster, GPT-5.2-Codex or Grok 4.3?
- Grok 4.3 streams faster: 112 against 25 output tokens per second.
- Which has the larger context window?
- Grok 4.3 accepts more context: 1M against 400k tokens.