GPT-5.1 Codex mini (high) vs Gemini 3 Pro Preview (high)
Comparing 2 AI models · 5 benchmarks · OpenAI, Google
Composite Indices
Intelligence, Coding, Math
Standard Benchmarks
Academic and industry benchmarks
Benchmark Winners
GPT-5.1 Codex mini (high)
No clear wins
Gemini 3 Pro Preview (high)
- GPQA
- MMLU Pro
- HLE
- LiveCodeBench
- AIME 2025
| Metric | Op GPT-5.1 Codex mini (high) | Go Gemini 3 Pro Preview (high) |
|---|---|---|
| Pricing Per 1M tokens | ||
| Input Cost | $0.25/1M | $2.00/1M |
| Output Cost | $2.00/1M | $12.00/1M |
| Blended Cost 3:1 input/output ratio | $0.69/1M | $4.50/1M |
| Specifications | ||
| Organization Model creator | OpenAI | |
| Release Date Launch date | Nov 13, 2025 | Nov 18, 2025 |
| Performance & Speed | ||
| Throughput Output speed | 156.0 tok/s | 121.6 tok/s |
| Time to First Token (TTFT) Initial response delay | 9416ms | 32614ms |
| Latency Time to first answer token | 9416ms | 32614ms |
| Composite Indices | ||
| Intelligence Index Overall reasoning capability | 38.0 | 47.9 |
| Coding Index Programming ability | 35.0 | 44.7 |
| Math Index Mathematical reasoning | 91.7 | 95.7 |
| Standard Benchmarks | ||
| GPQA Graduate-level reasoning | 81.3% | 90.8% |
| MMLU Pro Advanced knowledge | 82.0% | 89.8% |
| HLE Hard language evaluation | 16.9% | 37.2% |
| LiveCodeBench Real-world coding tasks | 83.6% | 91.7% |
| MATH 500 Mathematical problems | — | — |
| AIME 2025 Advanced math competition | 91.7% | 95.7% |
| AIME (Original) Math olympiad problems | — | — |
| SciCode Scientific code generation | 42.6% | 56.1% |
| LCR Code review capability | 62.7% | 70.7% |
| IFBench Instruction-following | 67.9% | 70.4% |
| TAU-bench v2 Tool use & agentic tasks | 62.9% | 87.1% |
| TerminalBench Hard CLI command generation | 31.2% | 39.0% |
Key Takeaways
GPT-5.1 Codex mini (high) offers the best value at $0.25/1M, making it ideal for high-volume applications and cost-conscious projects.
Gemini 3 Pro Preview (high) leads in reasoning capabilities with a 90.8% GPQA score, excelling at complex analytical tasks and problem-solving.
Gemini 3 Pro Preview (high) achieves a 44.7 coding index, making it the top choice for software development and code generation tasks.
All models support context windows of ∞+ tokens, suitable for processing lengthy documents and maintaining extended conversations.
When to Choose Each Model
GPT-5.1 Codex mini (high)
- Cost-sensitive applications
- High-volume processing
Gemini 3 Pro Preview (high)
- Complex reasoning tasks
- Research & analysis
- Code generation
- Software development
Try Models for Free
Try GPT-5.1 Codex mini (high) for FREE
No credit card or account required.
Try Gemini 3 Pro Preview (high) for FREE
No credit card or account required.
Cost Calculator
GPT-5.1 Codex mini (high) Gemini 3 Pro Preview (high) Costs are estimates based on API pricing. Actual costs may vary based on caching, batch processing, and volume discounts.
