Gemini 2.5 Computer Use Preview vs GPT-5.2 Codex vs GPT-5-Codex
Too close to call on our weighted score (GPT-5-Codex 42, GPT-5.2 Codex 42, Gemini 2.5 Computer Use Preview 35). The right pick depends on what you value most.
GoogleGemini 2.5 Computer Use Preview
35/100- ECI—
- Price$1.25 / $10.00
- Context128K
OpenAIGPT-5.2 Codex
42/100- ECI—
- Price$1.75 / $14.00
- Context400K
- OpenAI
GPT-5-Codex
42/100- ECI—
- Price$1.25 / $10.00
- Context400K
Too close to call
It is close. Our weighted score puts them within a point (GPT-5-Codex 42/100, GPT-5.2 Codex 42/100, Gemini 2.5 Computer Use Preview 35/100), so choose by what matters most for your work: Gemini 2.5 Computer Use Preview 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 priceGemini 2.5 Computer Use Preview and GPT-5-CodexGemini 2.5 Computer Use Preview $3.44 · GPT-5-Codex $3.44 · GPT-5.2 Codex $4.81 per 1M tokens (3:1 blend)
- Longest contextGPT-5.2 Codex and GPT-5-CodexGPT-5.2 Codex 400,000 · GPT-5-Codex 400,000 · Gemini 2.5 Computer Use Preview 128,000 tokens
- Widest inputsGPT-5.2 CodexGemini 2.5 Computer Use Preview: Text, Images · GPT-5.2 Codex: Text, Images, PDFs · GPT-5-Codex: Text, Images
- Self-hostingNo open weightsAll three are available only through APIs
| Measure | Weight | Gemini 2.5 Computer Use Preview | GPT-5.2 Codex | GPT-5-Codex |
|---|---|---|---|---|
| Price | 50% | 24 | 18 | 24 |
| Inputs & features | 30% | 60 | 80 | 70 |
| Context window | 20% | 24 | 44 | 44 |
| Overall | 100% | 35/100 | 42/100 | 42/100 |
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 | Gemini 2.5 Computer Use PreviewGoogle | GPT-5.2 CodexOpenAI | GPT-5-CodexOpenAI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $1.25 (best) | $1.75 | $1.25 (best) |
| Output | $10.00 (best) | $14.00 | $10.00 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $3.44 (best) | $4.81 | $3.44 (best) |
| Long-context rate | Over 200K: $2.50 / $15.00 | Same rate | Same rate |
| Price source | Official Google API | Median of 11 providers | Median of 3 providers |
| Limits | |||
| Context window | 128,000 tokens | 400,000 tokens (best) | 400,000 tokens (best) |
| Max output | 64,000 tokens | 128,000 tokens (best) | 128,000 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | Yes | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | Yes |
| Availability | |||
| Weights | Proprietary | Proprietary | Proprietary |
| API model ID | gemini-2.5-computer-use-preview-10-2025 | — | — |
| API providers | 2 | 11 (best) | 3 |
| Released | Oct 7, 2025 | Dec 11, 2025 | Sep 15, 2025 |
| Knowledge cutoff | Jan 2025 | Aug 31, 2025 | Sep 30, 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Gemini 2.5 Computer Use Preview$32.50
- GPT-5.2 Codex$45.50
- GPT-5-Codex$32.50
Which should you choose?
Which is better: Gemini 2.5 Computer Use Preview, GPT-5.2 Codex or GPT-5-Codex?
It is close. Our weighted score puts them within a point (GPT-5-Codex 42/100, GPT-5.2 Codex 42/100, Gemini 2.5 Computer Use Preview 35/100), so choose by what matters most for your work: Gemini 2.5 Computer Use Preview 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, Gemini 2.5 Computer Use Preview, GPT-5.2 Codex or GPT-5-Codex?
Gemini 2.5 Computer Use Preview is cheaper at $1.25 input / $10.00 output per million tokens (official Google API price). GPT-5-Codex costs $1.25 input / $10.00 output per million tokens (median across 3 API providers); GPT-5.2 Codex costs $1.75 input / $14.00 output per million tokens (median across 11 API providers). At a typical mix of three input tokens to one output token, that is $3.44 per million tokens for Gemini 2.5 Computer Use Preview versus $3.44 for GPT-5-Codex (1× as much) and $4.81 for GPT-5.2 Codex (1.4× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Gemini 2.5 Computer Use Preview has not been scored yet, GPT-5.2 Codex has not been scored yet and GPT-5-Codex has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Gemini 2.5 Computer Use Preview, GPT-5.2 Codex and 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?
GPT-5.2 Codex and GPT-5-Codex have the largest context windows (400,000 and 400,000 tokens), against 128,000 for Gemini 2.5 Computer Use Preview. Maximum output per response: Gemini 2.5 Computer Use Preview up to 64,000, GPT-5.2 Codex up to 128,000, GPT-5-Codex up to 128,000 tokens.
Which can read images, PDFs, audio or video?
Gemini 2.5 Computer Use Preview accepts text and images; GPT-5.2 Codex accepts text, images and PDFs; GPT-5-Codex accepts text and images. GPT-5.2 Codex handles the widest range of inputs.
Are any of these open source?
No. Gemini 2.5 Computer Use Preview, GPT-5.2 Codex and GPT-5-Codex are proprietary and only available through APIs and apps.
Which is newer?
GPT-5.2 Codex is the newest, released Dec 11, 2025. Gemini 2.5 Computer Use Preview came out Oct 7, 2025; GPT-5-Codex came out Sep 15, 2025. Knowledge cutoff: Gemini 2.5 Computer Use Preview Jan 2025, GPT-5.2 Codex Aug 31, 2025, GPT-5-Codex Sep 30, 2024.
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.
Related comparisons
- Gemini 2.5 Computer Use Preview vs Jamba LargeAI21 Labs
- Gemini 2.5 Computer Use Preview vs Command A TranslateCohere
- Gemini 2.5 Computer Use Preview vs Qwen3-Next 80B-A3B (Thinking)Alibaba (Qwen)
- GPT-5.2 Codex vs Command A TranslateCohere
- GPT-5.2 Codex vs Jamba LargeAI21 Labs
- GPT-5.2 Codex vs Kimi K2.7 Code HighspeedMoonshot AI
