Gemini 2.5 Computer Use Preview vs Magistral Medium vs GPT-5-Codex
GPT-5-Codex comes out ahead, 42 to 35 and 30 on our weighted score, though Magistral Medium is 20% cheaper per token.
GoogleGemini 2.5 Computer Use Preview
35/100- ECI—
- Price$1.25 / $10.00
- Context128K
Mistral AIMagistral Medium
30/100- ECI—
- Price$2.00 / $5.00
- Context128K
- Our pick
OpenAIGPT-5-Codex
42/100- ECI—
- Price$1.25 / $10.00
- Context400K
GPT-5-Codex is our pick
GPT-5-Codex is the better all-round choice, scoring 42/100 against Gemini 2.5 Computer Use Preview (35) and Magistral Medium (30). It leads on inputs & features and context window. Magistral Medium 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 priceMagistral MediumMagistral Medium $2.75 · Gemini 2.5 Computer Use Preview $3.44 · GPT-5-Codex $3.44 per 1M tokens (3:1 blend)
- Longest contextGPT-5-CodexGPT-5-Codex 400,000 · Gemini 2.5 Computer Use Preview 128,000 · Magistral Medium 128,000 tokens
- Widest inputsGemini 2.5 Computer Use Preview and GPT-5-CodexGemini 2.5 Computer Use Preview: Text, Images · Magistral Medium: Text · GPT-5-Codex: Text, Images
- Self-hostingNo open weightsAll three are available only through APIs
| Measure | Weight | Gemini 2.5 Computer Use Preview | Magistral Medium | GPT-5-Codex |
|---|---|---|---|---|
| Price | 50% | 24 | 29 | 24 |
| Inputs & features | 30% | 60 | 35 | 70 |
| Context window | 20% | 24 | 24 | 44 |
| Overall | 100% | 35/100 | 30/100 | 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 | Magistral MediumMistral AI | GPT-5-CodexOpenAI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $1.25 (best) | $2.00 | $1.25 (best) |
| Output | $10.00 | $5.00 (best) | $10.00 |
| Cached input | — | — | — |
| Blended (3:1) | $3.44 | $2.75 (best) | $3.44 |
| Long-context rate | Over 200K: $2.50 / $15.00 | Same rate | Same rate |
| Price source | Official Google API | Official Mistral API | Median of 3 providers |
| Limits | |||
| Context window | 128,000 tokens | 128,000 tokens | 400,000 tokens (best) |
| Max output | 64,000 tokens | 16,384 tokens | 128,000 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | Proprietary | Proprietary | Proprietary |
| API model ID | gemini-2.5-computer-use-preview-10-2025 | magistral-medium-latest | — |
| API providers | 2 | 4 (best) | 3 |
| Released | Oct 7, 2025 | Mar 17, 2025 | Sep 15, 2025 |
| Knowledge cutoff | Jan 2025 | Jun 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
- Magistral Medium$30.00
- GPT-5-Codex$32.50
Which should you choose?
Which is better: Gemini 2.5 Computer Use Preview, Magistral Medium or GPT-5-Codex?
GPT-5-Codex is the better all-round choice, scoring 42/100 against Gemini 2.5 Computer Use Preview (35) and Magistral Medium (30). It leads on inputs & features and context window. Magistral Medium 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, Gemini 2.5 Computer Use Preview, Magistral Medium or GPT-5-Codex?
Magistral Medium is cheaper at $2.00 input / $5.00 output per million tokens (official Mistral API price). Gemini 2.5 Computer Use Preview costs $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). At a typical mix of three input tokens to one output token, that is $2.75 per million tokens for Magistral Medium versus $3.44 for Gemini 2.5 Computer Use Preview (1.3× as much) and $3.44 for GPT-5-Codex (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, Magistral Medium 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, Magistral Medium 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-Codex has the largest context window at 400,000 tokens, against 128,000 for Gemini 2.5 Computer Use Preview and 128,000 for Magistral Medium. Maximum output per response: Gemini 2.5 Computer Use Preview up to 64,000, Magistral Medium up to 16,384, 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; Magistral Medium accepts text; GPT-5-Codex accepts text and images. Gemini 2.5 Computer Use Preview handles the widest range of inputs.
Are any of these open source?
No. Gemini 2.5 Computer Use Preview, Magistral Medium and GPT-5-Codex are proprietary and only available through APIs and apps.
Which is newer?
Gemini 2.5 Computer Use Preview is the newest, released Oct 7, 2025. GPT-5-Codex came out Sep 15, 2025; Magistral Medium came out Mar 17, 2025. Knowledge cutoff: Gemini 2.5 Computer Use Preview Jan 2025, Magistral Medium Jun 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)
- Magistral Medium vs Qwen3-Coder 480B-A35B InstructAlibaba (Qwen)
- Magistral Medium vs Sonar Deep ResearchPerplexity
- Magistral Medium vs Command ACohere
