Gemini 2.5 Computer Use Preview vs GPT-5.1 Chat vs Kimi K2 Thinking
Kimi K2 Thinking comes out ahead, 42 to 38 and 35 on our weighted score, and it is the cheaper option too.
GoogleGemini 2.5 Computer Use Preview
35/100- ECI—
- Price$1.25 / $10.00
- Context128K
OpenAIGPT-5.1 Chat
38/100- ECI—
- Price$1.25 / $10.00
- Context128K
- Our pick
Moonshot AIKimi K2 Thinking
42/100- ECI146.0
- Price$0.60 / $2.50
- Context262K
Kimi K2 Thinking is our pick
Kimi K2 Thinking is the better all-round choice, scoring 42/100 against GPT-5.1 Chat (38) and Gemini 2.5 Computer Use Preview (35). It leads on price and context window. GPT-5.1 Chat wins on inputs & features. 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 priceKimi K2 ThinkingKimi K2 Thinking $1.07 · Gemini 2.5 Computer Use Preview $3.44 · GPT-5.1 Chat $3.44 per 1M tokens (3:1 blend)
- Longest contextKimi K2 ThinkingKimi K2 Thinking 262,144 · Gemini 2.5 Computer Use Preview 128,000 · GPT-5.1 Chat 128,000 tokens
- Widest inputsGemini 2.5 Computer Use Preview and GPT-5.1 ChatGemini 2.5 Computer Use Preview: Text, Images · GPT-5.1 Chat: Text, Images · Kimi K2 Thinking: Text
- Self-hostingKimi K2 ThinkingPublishes downloadable weights
| Measure | Weight | Gemini 2.5 Computer Use Preview | GPT-5.1 Chat | Kimi K2 Thinking |
|---|---|---|---|---|
| Price | 50% | 24 | 24 | 48 |
| Inputs & features | 30% | 60 | 70 | 35 |
| Context window | 20% | 24 | 24 | 37 |
| Overall | 100% | 35/100 | 38/100 | 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-5.1 ChatOpenAI | Kimi K2 ThinkingMoonshot AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | 146.0 |
| ECI rank | — | — | #72 of 148 |
| GPQA DiamondGraduate-level science questions | — | — | 84.2% |
| OTIS Mock AIME 2024–2025Competition mathematics | — | — | 83.1% |
| Price per million tokens | |||
| Input | $1.25 | $1.25 | $0.60 (best) |
| Output | $10.00 | $10.00 | $2.50 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $3.44 | $3.44 | $1.07 (best) |
| Long-context rate | Over 200K: $2.50 / $15.00 | Same rate | Same rate |
| Price source | Official Google API | Median of 2 providers | Median of 10 providers |
| Limits | |||
| Context window | 128,000 tokens | 128,000 tokens | 262,144 tokens (best) |
| Max output | 64,000 tokens | 16,384 tokens | 262,144 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Proprietary | Proprietary | Open |
| API model ID | gemini-2.5-computer-use-preview-10-2025 | — | — |
| API providers | 2 | 2 | 10 (best) |
| Released | Oct 7, 2025 | Nov 13, 2025 | Nov 6, 2025 |
| Knowledge cutoff | Jan 2025 | Sep 30, 2024 | Aug 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-5.1 Chat$32.50
- Kimi K2 Thinking$11.00
Which should you choose?
Which is better: Gemini 2.5 Computer Use Preview, GPT-5.1 Chat or Kimi K2 Thinking?
Kimi K2 Thinking is the better all-round choice, scoring 42/100 against GPT-5.1 Chat (38) and Gemini 2.5 Computer Use Preview (35). It leads on price and context window. GPT-5.1 Chat wins on inputs & features. 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-5.1 Chat or Kimi K2 Thinking?
Kimi K2 Thinking is cheaper at $0.60 input / $2.50 output per million tokens (median across 10 API providers). Gemini 2.5 Computer Use Preview costs $1.25 input / $10.00 output per million tokens (official Google API price); GPT-5.1 Chat costs $1.25 input / $10.00 output per million tokens (median across 2 API providers). At a typical mix of three input tokens to one output token, that is $1.07 per million tokens for Kimi K2 Thinking versus $3.44 for Gemini 2.5 Computer Use Preview (3.2× as much) and $3.44 for GPT-5.1 Chat (3.2× 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-5.1 Chat has not been scored yet and Kimi K2 Thinking has an ECI of 146.0.
Which is better for coding?
There are no published SWE-bench Verified results for Gemini 2.5 Computer Use Preview, GPT-5.1 Chat and Kimi K2 Thinking 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?
Kimi K2 Thinking has the largest context window at 262,144 tokens, against 128,000 for Gemini 2.5 Computer Use Preview and 128,000 for GPT-5.1 Chat. Maximum output per response: Gemini 2.5 Computer Use Preview up to 64,000, GPT-5.1 Chat up to 16,384, Kimi K2 Thinking up to 262,144 tokens.
Which can read images, PDFs, audio or video?
Gemini 2.5 Computer Use Preview accepts text and images; GPT-5.1 Chat accepts text and images; Kimi K2 Thinking accepts text. Gemini 2.5 Computer Use Preview handles the widest range of inputs.
Are any of these open source?
Kimi K2 Thinking publishes its weights and can be self-hosted; Gemini 2.5 Computer Use Preview and GPT-5.1 Chat is proprietary.
Which is newer?
GPT-5.1 Chat is the newest, released Nov 13, 2025. Kimi K2 Thinking came out Nov 6, 2025; Gemini 2.5 Computer Use Preview came out Oct 7, 2025. Knowledge cutoff: Gemini 2.5 Computer Use Preview Jan 2025, GPT-5.1 Chat Sep 30, 2024, Kimi K2 Thinking Aug 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 GPT-5-CodexOpenAI
- 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-5.1 Chat vs Jamba LargeAI21 Labs
- GPT-5.1 Chat vs Command A TranslateCohere
