GPT-5-Codex vs Aya Vision 32B vs Gemini 2.5 Computer Use Preview
GPT-5-Codex comes out ahead, 60 to 46 and 15 on our weighted score.
- Our pick
OpenAIGPT-5-Codex
60/100- ECI—
- Price$1.25 / $10.00
- Context400K
CohereAya Vision 32B
15/100- ECI—
- Price—
- Context16K
GoogleGemini 2.5 Computer Use Preview
46/100- ECI—
- Price$1.25 / $10.00
- Context128K
GPT-5-Codex is our pick
GPT-5-Codex is the better all-round choice, scoring 60/100 against Gemini 2.5 Computer Use Preview (46) and Aya Vision 32B (15). It leads on inputs & features and context window. The score weighs inputs & features 60%, context window 40%. 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-Codex and Gemini 2.5 Computer Use PreviewGPT-5-Codex $3.44 · Gemini 2.5 Computer Use Preview $3.44 per 1M tokens (3:1 blend) · Aya Vision 32B unpriced
- Longest contextGPT-5-CodexGPT-5-Codex 400,000 · Gemini 2.5 Computer Use Preview 128,000 · Aya Vision 32B 16,000 tokens
- Widest inputsSame inputsGPT-5-Codex: Text, Images · Aya Vision 32B: Text, Images · Gemini 2.5 Computer Use Preview: Text, Images
- Self-hostingAya Vision 32BPublishes downloadable weights (CC-BY-NC-4.0)
| Measure | Weight | GPT-5-Codex | Aya Vision 32B | Gemini 2.5 Computer Use Preview |
|---|---|---|---|---|
| Inputs & features | 60% | 70 | 25 | 60 |
| Context window | 40% | 44 | 0 | 24 |
| Overall | 100% | 60/100 | 15/100 | 46/100 |
Left out because at least one model lacks the data: capability and price. 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-CodexOpenAI | Aya Vision 32BCohere | Gemini 2.5 Computer Use PreviewGoogle |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $1.25 | — | $1.25 |
| Output | $10.00 | — | $10.00 |
| Cached input | — | — | — |
| Blended (3:1) | $3.44 | — | $3.44 |
| Long-context rate | Same rate | — | Over 200K: $2.50 / $15.00 |
| Price source | Median of 3 providers | — | Official Google API |
| Limits | |||
| Context window | 400,000 tokens (best) | 16,000 tokens | 128,000 tokens |
| Max output | 128,000 tokens (best) | 4,000 tokens | 64,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | No | Yes |
| Tool calling | Yes | No | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Proprietary | OpenCC-BY-NC-4.0 | Proprietary |
| API model ID | — | c4ai-aya-vision-32b | gemini-2.5-computer-use-preview-10-2025 |
| API providers | 3 (best) | 1 | 2 |
| Released | Sep 15, 2025 | Mar 4, 2025 | Oct 7, 2025 |
| Knowledge cutoff | 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-Codex$32.50
- Aya Vision 32B—
- Gemini 2.5 Computer Use Preview$32.50
Which should you choose?
Which is better: GPT-5-Codex, Aya Vision 32B or Gemini 2.5 Computer Use Preview?
GPT-5-Codex is the better all-round choice, scoring 60/100 against Gemini 2.5 Computer Use Preview (46) and Aya Vision 32B (15). It leads on inputs & features and context window. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, GPT-5-Codex, Aya Vision 32B or Gemini 2.5 Computer Use Preview?
GPT-5-Codex is cheaper at $1.25 input / $10.00 output per million tokens (median across 3 API providers). Gemini 2.5 Computer Use Preview costs $1.25 input / $10.00 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 GPT-5-Codex versus $3.44 for Gemini 2.5 Computer Use Preview (1× as much). Aya Vision 32B has no published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. GPT-5-Codex has not been scored yet, Aya Vision 32B has not been scored yet and Gemini 2.5 Computer Use Preview has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for GPT-5-Codex, Aya Vision 32B and Gemini 2.5 Computer Use Preview yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Aya Vision 32B does not support tool calling, which most coding agents need.
Which has the bigger context window?
GPT-5-Codex has the largest context window at 400,000 tokens, against 128,000 for Gemini 2.5 Computer Use Preview and 16,000 for Aya Vision 32B. Maximum output per response: GPT-5-Codex up to 128,000, Aya Vision 32B up to 4,000, Gemini 2.5 Computer Use Preview up to 64,000 tokens.
Which can read images, PDFs, audio or video?
GPT-5-Codex accepts text and images; Aya Vision 32B accepts text and images; Gemini 2.5 Computer Use Preview accepts text and images. They handle the same number of input types.
Are any of these open source?
Aya Vision 32B publishes its weights (CC-BY-NC-4.0) and can be self-hosted; GPT-5-Codex and Gemini 2.5 Computer Use Preview is proprietary.
Which is newer?
Gemini 2.5 Computer Use Preview is the newest, released Oct 7, 2025. GPT-5-Codex came out Sep 15, 2025; Aya Vision 32B came out Mar 4, 2025. Knowledge cutoff: GPT-5-Codex Sep 30, 2024, Gemini 2.5 Computer Use 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.
