Gemini 3.7 Flash vs GPT-5.2-Codex
Gemini 3.7 Flash 
GPT-5.2-Codex Verdict
- Gemini 3.7 Flash (medium) leads on quality: 64.5 vs 60.8.
- Gemini 3.7 Flash (medium) is stronger in coding, composite, knowledge, long context, multimodal, reasoning.
- GPT-5.2-Codex is stronger in agents & tools, instruction following.
- Gemini 3.7 Flash (medium) is 3.2× cheaper ($1.50 vs $4.81 per 1M blended).
- Gemini 3.7 Flash (medium) streams 10.9× faster (272 vs 25 tokens per second).
| Metric | Gemini 3.7 Flash (medium) | GPT-5.2-Codex |
|---|---|---|
| BenchLeader Index | 64.5 | 60.8 |
| Coding score | 68.5 | 55.7 |
| Composite score | 79.1 | 56.8 |
| Knowledge score | 75.4 | 63.1 |
| Long context score | 68.1 | 67.8 |
| Multimodal score | 69.4 | 60.7 |
| Reasoning score | 63.5 | – |
| Agents & tools score | – | 63.5 |
| Instruction following score | – | 75.1 |
| Blended price $/M | $1.50 | $4.81 |
| Output speed | 272 tok/s | 25 tok/s |
| Time to first answer | 4.6 s | 6.7 s |
| Context window | 1M | 400k |
| Terminal-Bench | – | 66.5% |
| SciCode | 57.9% | – |
| 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 | 39.6 | 28.5 |
| IFBench | – | 77.6% |
| AA-LCR | 83.0% | 82.3% |
| MMMU-Pro | 84.7% | 76.3% |
| AA-Omniscience | 23.7 | -2.2 |
| Terminal-Bench Hard | – | 37.1% |
| GPQA Diamond (AA) | 92.1% | 89.9% |
| Humanity's Last Exam (AA) | 39.0% | 35.7% |
| SciCode (AA) | 59.8% | – |
| τ²-Bench Telecom (AA) | – | 92.1% |
| LiveCodeBench | – | 88.0% |
| SWE-Bench Pro | – | 41.0% |
| SWE-bench Verified (bash only) | – | 72.8% |
| SWE-bench Verified (any scaffold) | – | 72.8% |
| ARC-AGI-1 | 91.2% | – |
| ARC-AGI-2 | 63.8% | – |
Data as of 2026-09-10. Best configuration of each model; every score links to its source on the model pages.
Gemini 3.7 Flash vs GPT-5.2-Codex: questions
- Is Gemini 3.7 Flash better than GPT-5.2-Codex?
- Gemini 3.7 Flash (medium) leads on quality: 64.5 vs 60.8. The BenchLeader Index combines every independent quality benchmark; Gemini 3.7 Flash (medium) is ahead overall as of 2026-09-10, but check the category scores for your use.
- Is Gemini 3.7 Flash better than GPT-5.2-Codex for coding?
- Gemini 3.7 Flash scores higher in coding (69 vs 56 on the category index, where 50 is average).
- Which is cheaper, Gemini 3.7 Flash or GPT-5.2-Codex?
- Gemini 3.7 Flash is cheaper: $1.50 against $4.81 per million tokens, blended at three input tokens per output token.
- Which is faster, Gemini 3.7 Flash or GPT-5.2-Codex?
- Gemini 3.7 Flash streams faster: 272 against 25 output tokens per second.
- Which has the larger context window?
- Gemini 3.7 Flash accepts more context: 1M against 400k tokens.