GPT-5.3 Codex Spark vs Command A Plus vs Gemini 2.5 Computer Use Preview
Too close to call on our weighted score (GPT-5.3 Codex Spark 38, Command A Plus 35, Gemini 2.5 Computer Use Preview 35). The right pick depends on what you value most.
OpenAIGPT-5.3 Codex Spark
38/100- ECI—
- Price$1.75 / $14.00
- Context128K
CohereCommand A Plus
35/100- ECI—
- Price$2.50 / $10.00
- Context128K
GoogleGemini 2.5 Computer Use Preview
35/100- ECI—
- Price$1.25 / $10.00
- Context128K
Too close to call
It is close. Our weighted score puts them within 2 points (GPT-5.3 Codex Spark 38/100, Command A Plus 35/100, 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 PreviewGemini 2.5 Computer Use Preview $3.44 · Command A Plus $4.38 · GPT-5.3 Codex Spark $4.81 per 1M tokens (3:1 blend)
- Longest contextAbout the sameGPT-5.3 Codex Spark 128,000 · Command A Plus 128,000 · Gemini 2.5 Computer Use Preview 128,000 tokens
- Widest inputsGPT-5.3 Codex SparkGPT-5.3 Codex Spark: Text, Images, PDFs · Command A Plus: Text, Images · Gemini 2.5 Computer Use Preview: Text, Images
- Self-hostingCommand A PlusPublishes downloadable weights
| Measure | Weight | GPT-5.3 Codex Spark | Command A Plus | Gemini 2.5 Computer Use Preview |
|---|---|---|---|---|
| Price | 50% | 18 | 19 | 24 |
| Inputs & features | 30% | 80 | 70 | 60 |
| Context window | 20% | 24 | 24 | 24 |
| Overall | 100% | 38/100 | 35/100 | 35/100 |
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-5.3 Codex SparkOpenAI | Command A PlusCohere | Gemini 2.5 Computer Use PreviewGoogle |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $1.75 | $2.50 | $1.25 (best) |
| Output | $14.00 | $10.00 (best) | $10.00 (best) |
| Cached input | $0.175 | — | — |
| Blended (3:1) | $4.81 | $4.38 | $3.44 (best) |
| Long-context rate | Same rate | Same rate | Over 200K: $2.50 / $15.00 |
| Price source | Official OpenAI API | Official Cohere API | Official Google API |
| Limits | |||
| Context window | 128,000 tokens | 128,000 tokens | 128,000 tokens |
| Max output | 32,000 tokens | 64,000 tokens (best) | 64,000 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | Yes | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yeslow · medium · high · xhigh | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | No |
| Availability | |||
| Weights | Proprietary | Open | Proprietary |
| API model ID | gpt-5.3-codex-spark | command-a-plus-05-2026 | gemini-2.5-computer-use-preview-10-2025 |
| API providers | 1 | 1 | 2 (best) |
| Released | Feb 5, 2026 | May 20, 2026 | Oct 7, 2025 |
| Knowledge cutoff | Aug 31, 2025 | Apr 1, 2025 | 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-5.3 Codex Spark$45.50
- Command A Plus$45.00
- Gemini 2.5 Computer Use Preview$32.50
Which should you choose?
Which is better: GPT-5.3 Codex Spark, Command A Plus or Gemini 2.5 Computer Use Preview?
It is close. Our weighted score puts them within 2 points (GPT-5.3 Codex Spark 38/100, Command A Plus 35/100, 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, GPT-5.3 Codex Spark, Command A Plus or Gemini 2.5 Computer Use Preview?
Gemini 2.5 Computer Use Preview is cheaper at $1.25 input / $10.00 output per million tokens (official Google API price). Command A Plus costs $2.50 input / $10.00 output per million tokens (official Cohere API price); GPT-5.3 Codex Spark 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 Gemini 2.5 Computer Use Preview versus $4.38 for Command A Plus (1.3× as much) and $4.81 for GPT-5.3 Codex Spark (1.4× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. GPT-5.3 Codex Spark has not been scored yet, Command A Plus 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-5.3 Codex Spark, Command A Plus 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. All three support tool calling for agent workflows.
Which has the bigger context window?
GPT-5.3 Codex Spark, Command A Plus and Gemini 2.5 Computer Use Preview share the same 128,000-token context window. Maximum output per response: GPT-5.3 Codex Spark up to 32,000, Command A Plus up to 64,000, Gemini 2.5 Computer Use Preview up to 64,000 tokens.
Which can read images, PDFs, audio or video?
GPT-5.3 Codex Spark accepts text, images and PDFs; Command A Plus accepts text and images; Gemini 2.5 Computer Use Preview accepts text and images. GPT-5.3 Codex Spark handles the widest range of inputs.
Are any of these open source?
Command A Plus publishes its weights and can be self-hosted; GPT-5.3 Codex Spark and Gemini 2.5 Computer Use Preview is proprietary.
Which is newer?
Command A Plus is the newest, released May 20, 2026. GPT-5.3 Codex Spark came out Feb 5, 2026; Gemini 2.5 Computer Use Preview came out Oct 7, 2025. Knowledge cutoff: GPT-5.3 Codex Spark Aug 31, 2025, Command A Plus Apr 1, 2025, 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.
