Gemini 3.5 Flash vs GPT-5.2-Codex
Gemini 3.5 Flash 
GPT-5.2-Codex Verdict
- Gemini 3.5 Flash (medium) leads on quality: 64.1 vs 60.8.
- Gemini 3.5 Flash (medium) is stronger in agents & tools, coding, composite, human preference, knowledge, multimodal, reasoning.
- GPT-5.2-Codex is stronger in instruction following, long context.
- Gemini 3.5 Flash (medium) is 1.4× cheaper ($3.38 vs $4.81 per 1M blended).
- Gemini 3.5 Flash (medium) streams 8.7× faster (217 vs 25 tokens per second).
| Metric | Gemini 3.5 Flash (medium) | GPT-5.2-Codex |
|---|---|---|
| BenchLeader Index | 64.1 | 60.8 |
| Agents & tools score | 68.0 | 63.5 |
| Coding score | 58.9 | 55.7 |
| Composite score | 71.5 | 56.8 |
| Human preference score | 67.8 | – |
| Instruction following score | 72.5 | 75.1 |
| Knowledge score | 74.0 | 63.1 |
| Long context score | 63.6 | 67.8 |
| Multimodal score | 67.6 | 60.7 |
| Reasoning score | 67.1 | – |
| Blended price $/M | $3.38 | $4.81 |
| Output speed | 217 tok/s | 25 tok/s |
| Time to first answer | 15.5 s | 6.7 s |
| Context window | 1M | 400k |
| Terminal-Bench | – | 66.5% |
| APEX-Agents | – | 27.6% |
| LMArena Text | 1476 | – |
| LMArena Hard Prompts | 1493 | – |
| LMArena Coding | 1503 | – |
| LMArena WebDev | 1491 | 1339 |
| LMArena Vision | 1306 | – |
| 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 | 33.6 | 28.5 |
| IFBench | 74.6% | 77.6% |
| AA-LCR | 74.3% | 82.3% |
| MMMU-Pro | 83.9% | 76.3% |
| AA-Omniscience | 20.8 | -2.2 |
| Terminal-Bench Hard | 39.4% | 37.1% |
| GPQA Diamond (AA) | 92.1% | 89.9% |
| Humanity's Last Exam (AA) | 41.3% | 35.7% |
| τ²-Bench Telecom (AA) | 95.6% | 92.1% |
| 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.
Gemini 3.5 Flash vs GPT-5.2-Codex: questions
- Is Gemini 3.5 Flash better than GPT-5.2-Codex?
- Gemini 3.5 Flash (medium) leads on quality: 64.1 vs 60.8. The BenchLeader Index combines every independent quality benchmark; Gemini 3.5 Flash (medium) is ahead overall as of 2026-09-10, but check the category scores for your use.
- Is Gemini 3.5 Flash better than GPT-5.2-Codex for coding?
- Gemini 3.5 Flash scores higher in coding (59 vs 56 on the category index, where 50 is average).
- Is Gemini 3.5 Flash better than GPT-5.2-Codex for agentic tasks?
- Gemini 3.5 Flash scores higher in agentic tasks (68 vs 64 on the category index, where 50 is average).
- Which is cheaper, Gemini 3.5 Flash or GPT-5.2-Codex?
- Gemini 3.5 Flash is cheaper: $3.38 against $4.81 per million tokens, blended at three input tokens per output token.
- Which is faster, Gemini 3.5 Flash or GPT-5.2-Codex?
- Gemini 3.5 Flash streams faster: 217 against 25 output tokens per second.
- Which has the larger context window?
- Gemini 3.5 Flash accepts more context: 1M against 400k tokens.