Gemini 2.5 Computer Use Preview vs Gemini 3.1 Pro Preview vs GPT-5-Codex
Gemini 3.1 Pro Preview comes out ahead, 52 to 42 and 35 on our weighted score, though Gemini 2.5 Computer Use Preview is 24% cheaper per token.
GoogleGemini 2.5 Computer Use Preview
35/100- ECI—
- Price$1.25 / $10.00
- Context128K
- Our pickGoogle
Gemini 3.1 Pro Preview
52/100- ECI154.8
- Price$2.00 / $12.00
- Context1.05M
OpenAIGPT-5-Codex
42/100- ECI—
- Price$1.25 / $10.00
- Context400K
Gemini 3.1 Pro Preview is our pick
Gemini 3.1 Pro Preview is the better all-round choice, scoring 52/100 against GPT-5-Codex (42) and Gemini 2.5 Computer Use Preview (35). It leads on inputs & features and context window. 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 · Gemini 3.1 Pro Preview $4.50 per 1M tokens (3:1 blend)
- Longest contextGemini 3.1 Pro PreviewGemini 3.1 Pro Preview 1,048,576 · GPT-5-Codex 400,000 · Gemini 2.5 Computer Use Preview 128,000 tokens
- Widest inputsGemini 3.1 Pro PreviewGemini 2.5 Computer Use Preview: Text, Images · Gemini 3.1 Pro Preview: Text, Images, PDFs, Audio, Video · GPT-5-Codex: Text, Images
- Self-hostingNo open weightsAll three are available only through APIs
| Measure | Weight | Gemini 2.5 Computer Use Preview | Gemini 3.1 Pro Preview | GPT-5-Codex |
|---|---|---|---|---|
| Price | 50% | 24 | 19 | 24 |
| Inputs & features | 30% | 60 | 100 | 70 |
| Context window | 20% | 24 | 61 | 44 |
| Overall | 100% | 35/100 | 52/100 | 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 | Gemini 3.1 Pro PreviewGoogle | GPT-5-CodexOpenAI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | 154.8 | — |
| ECI rank | — | #31 of 148 | — |
| GPQA DiamondGraduate-level science questions | — | 94.4% | — |
| FrontierMath Tiers 1–3Research-level mathematics | — | 59.7% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 95.6% | — |
| SWE-bench VerifiedFixing real GitHub issues | — | 75.6% | — |
| SimpleQA VerifiedShort factual questions | — | 73.5% | — |
| Price per million tokens | |||
| Input | $1.25 (best) | $2.00 | $1.25 (best) |
| Output | $10.00 (best) | $12.00 | $10.00 (best) |
| Cached input | — | $0.20 | — |
| Blended (3:1) | $3.44 (best) | $4.50 | $3.44 (best) |
| Long-context rate | Over 200K: $2.50 / $15.00 | Over 200K: $4.00 / $18.00 | Same rate |
| Price source | Official Google API | Official Google API | Median of 3 providers |
| Limits | |||
| Context window | 128,000 tokens | 1,048,576 tokens (best) | 400,000 tokens |
| Max output | 64,000 tokens | 65,536 tokens | 128,000 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | Yes | No |
| Audio | No | Yes | No |
| Video | No | Yes | No |
| Reasoning | Yes | Yeslow · medium · high | 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 | gemini-3.1-pro-preview | — |
| API providers | 2 | 26 (best) | 3 |
| Released | Oct 7, 2025 | Feb 19, 2026 | Sep 15, 2025 |
| Knowledge cutoff | Jan 2025 | Jan 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
- Gemini 3.1 Pro Preview$44.00
- GPT-5-Codex$32.50
Which should you choose?
Which is better: Gemini 2.5 Computer Use Preview, Gemini 3.1 Pro Preview or GPT-5-Codex?
Gemini 3.1 Pro Preview is the better all-round choice, scoring 52/100 against GPT-5-Codex (42) and Gemini 2.5 Computer Use Preview (35). It leads on inputs & features and context window. 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, Gemini 3.1 Pro Preview 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); Gemini 3.1 Pro Preview costs $2.00 input / $12.00 output per million tokens (official Google API price). 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 $4.50 for Gemini 3.1 Pro Preview (1.3× 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, Gemini 3.1 Pro Preview has an ECI of 154.8 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 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?
Gemini 3.1 Pro Preview has the largest context window at 1,048,576 tokens, against 400,000 for GPT-5-Codex and 128,000 for Gemini 2.5 Computer Use Preview. Maximum output per response: Gemini 2.5 Computer Use Preview up to 64,000, Gemini 3.1 Pro Preview up to 65,536, 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; Gemini 3.1 Pro Preview accepts text, images, PDFs, audio and video; GPT-5-Codex accepts text and images. Gemini 3.1 Pro Preview handles the widest range of inputs.
Are any of these open source?
No. Gemini 2.5 Computer Use Preview, Gemini 3.1 Pro Preview and GPT-5-Codex are proprietary and only available through APIs and apps.
Which is newer?
Gemini 3.1 Pro Preview is the newest, released Feb 19, 2026. 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, Gemini 3.1 Pro Preview Jan 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)
- Gemini 3.1 Pro Preview vs GPT-5.3 CodexOpenAI · ECI 156.8
- Gemini 3.1 Pro Preview vs Qwen3.7 MaxAlibaba (Qwen) · ECI 153.7
- Gemini 3.1 Pro Preview vs Claude Sonnet 4.6Anthropic · ECI 152.3
