← All Comparisons
GPT-5.2 Codex vs Gemini 3 Pro
A detailed comparison of GPT-5.2 Codex (OpenAI) and Gemini 3 Pro (Google) across pricing, performance, and features.
Pricing Comparison
| Metric | GPT-5.2 Codex | Gemini 3 Pro | Difference |
|---|---|---|---|
| Input / 1M tokens | $1.75 | $2.00 | +14% |
| Output / 1M tokens | $14.00 | $12.00 | -14% |
| Context window | 200K | 1M | — |
| Max output | 65.536K | 65.536K | — |
Benchmark Comparison
| Benchmark | GPT-5.2 Codex | Gemini 3 Pro |
|---|---|---|
| MMLU-Pro | 89% | 89.8% |
| HumanEval | 95.5% | 94% |
| GPQA | 76% | 77% |
Capabilities
| Capability | GPT-5.2 Codex | Gemini 3 Pro |
|---|---|---|
| audio | ✗ | ✓ |
| code | ✓ | ✓ |
| reasoning | ✓ | ✓ |
| text | ✓ | ✓ |
| tool-use | ✓ | ✓ |
| vision | ✓ | ✓ |
GPT-5.2 Codex Strengths
- ✓Strong coding performance
- ✓Available via API now
- ✓200K context window
GPT-5.2 Codex Weaknesses
- ✗Being superseded by 5.3
- ✗Higher output cost than some competitors
Gemini 3 Pro Strengths
- ✓Stable and well-tested
- ✓1M token context window
- ✓Strong multimodal with audio
Gemini 3 Pro Weaknesses
- ✗Being superseded by 3.1 Pro
- ✗Context-tiered pricing ($4/$18 above 200K)
Quick Verdict
Best value: Gemini 3 Pro is the more affordable option at $2/$12 per 1M tokens.
Higher benchmarks: Gemini 3 Pro scores higher on average across available benchmarks (86.9% avg).
Larger context: Gemini 3 Pro supports 1M tokens.
Choose Gemini 3 Pro if cost matters most. Choose GPT-5.2 Codex if you need the best possible quality for complex tasks.