GPT-5.2 vs GPT-5-Codex vs Gemini 3 Pro Preview
Gemini 3 Pro Preview comes out ahead, 52 to 42 and 39 on our weighted score, though GPT-5-Codex is 24% cheaper per token.
OpenAIGPT-5.2
39/100- ECI153.5
- Price$1.75 / $14.00
- Context400K
- OpenAI
GPT-5-Codex
42/100- ECI—
- Price$1.25 / $10.00
- Context400K
- Our pick
GoogleGemini 3 Pro Preview
52/100- ECI153.0
- Price$2.00 / $12.00
- Context1.05M
Gemini 3 Pro Preview is our pick
Gemini 3 Pro Preview is the better all-round choice, scoring 52/100 against GPT-5-Codex (42) and GPT-5.2 (39). It leads on inputs & features and context window. GPT-5-Codex wins on price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceGPT-5-CodexGPT-5-Codex $3.44 · Gemini 3 Pro Preview $4.50 · GPT-5.2 $4.81 per 1M tokens (3:1 blend)
- Longest contextGemini 3 Pro PreviewGemini 3 Pro Preview 1,048,576 · GPT-5.2 400,000 · GPT-5-Codex 400,000 tokens
- Widest inputsGemini 3 Pro PreviewGPT-5.2: Text, Images · GPT-5-Codex: Text, Images · Gemini 3 Pro Preview: Text, Images, PDFs, Audio, Video
- Self-hostingNo open weightsAll three are available only through APIs
| Measure | Weight | GPT-5.2 | GPT-5-Codex | Gemini 3 Pro Preview |
|---|---|---|---|---|
| Price | 50% | 18 | 24 | 19 |
| Inputs & features | 30% | 70 | 70 | 100 |
| Context window | 20% | 44 | 44 | 61 |
| Overall | 100% | 39/100 | 42/100 | 52/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | GPT-5.2OpenAI | GPT-5-CodexOpenAI | Gemini 3 Pro PreviewGoogle |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 153.5 (best) | — | 153.0 |
| ECI rank | #38 of 148 (best) | — | #39 of 148 |
| GPQA DiamondGraduate-level science questions | 91.4% | — | 92.6% (best) |
| FrontierMath Tiers 1–3Research-level mathematics | 67.4% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 96.1% (best) | — | 91.4% |
| SWE-bench VerifiedFixing real GitHub issues | 73.8% (best) | — | 72.9% |
| SimpleQA VerifiedShort factual questions | 37.1% | — | — |
| Price per million tokens | |||
| Input | $1.75 | $1.25 (best) | $2.00 |
| Output | $14.00 | $10.00 (best) | $12.00 |
| Cached input | $0.175 | — | — |
| Blended (3:1) | $4.81 | $3.44 (best) | $4.50 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official OpenAI API | Median of 3 providers | Median of 2 providers |
| Limits | |||
| Context window | 400,000 tokens | 400,000 tokens | 1,048,576 tokens (best) |
| Max output | 128,000 tokens (best) | 128,000 tokens (best) | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | No | Yes |
| Audio | No | No | Yes |
| Video | No | No | Yes |
| Reasoning | Yeslow · medium · high · xhigh | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| Availability | |||
| Weights | Proprietary | Proprietary | Proprietary |
| API model ID | gpt-5.2 | — | — |
| API providers | 21 (best) | 3 | 3 |
| Released | Dec 11, 2025 | Sep 15, 2025 | Nov 18, 2025 |
| Knowledge cutoff | Aug 31, 2025 | Sep 30, 2024 | Jan 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- GPT-5.2$45.50
- GPT-5-Codex$32.50
- Gemini 3 Pro Preview$44.00
Which should you choose?
Which is better: GPT-5.2, GPT-5-Codex or Gemini 3 Pro Preview?
Gemini 3 Pro Preview is the better all-round choice, scoring 52/100 against GPT-5-Codex (42) and GPT-5.2 (39). It leads on inputs & features and context window. GPT-5-Codex wins on price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, GPT-5.2, GPT-5-Codex or Gemini 3 Pro Preview?
GPT-5-Codex is cheaper at $1.25 input / $10.00 output per million tokens (median across 3 API providers). Gemini 3 Pro Preview costs $2.00 input / $12.00 output per million tokens (median across 2 API providers); GPT-5.2 costs $1.75 input / $14.00 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $3.44 per million tokens for GPT-5-Codex versus $4.50 for Gemini 3 Pro Preview (1.3× as much) and $4.81 for GPT-5.2 (1.4× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. GPT-5.2 has an ECI of 153.5, GPT-5-Codex has not been scored yet and Gemini 3 Pro Preview has an ECI of 153.0.
Which is better for coding?
There are no published SWE-bench Verified results for GPT-5-Codex yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Gemini 3 Pro Preview has the largest context window at 1,048,576 tokens, against 400,000 for GPT-5.2 and 400,000 for GPT-5-Codex. Maximum output per response: GPT-5.2 up to 128,000, GPT-5-Codex up to 128,000, Gemini 3 Pro Preview up to 65,536 tokens.
Which can read images, PDFs, audio or video?
GPT-5.2 accepts text and images; GPT-5-Codex accepts text and images; Gemini 3 Pro Preview accepts text, images, PDFs, audio and video. Gemini 3 Pro Preview handles the widest range of inputs.
Are any of these open source?
No. GPT-5.2, GPT-5-Codex and Gemini 3 Pro Preview are proprietary and only available through APIs and apps.
Which is newer?
GPT-5.2 is the newest, released Dec 11, 2025. Gemini 3 Pro Preview came out Nov 18, 2025; GPT-5-Codex came out Sep 15, 2025. Knowledge cutoff: GPT-5.2 Aug 31, 2025, GPT-5-Codex Sep 30, 2024, Gemini 3 Pro Preview Jan 2025.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.
