DeepSeek V4 Pro vs Gemini 3 Pro Preview vs GPT-5.1
Gemini 3 Pro Preview comes out ahead, 80 to 73 and 67 on our weighted score, though DeepSeek V4 Pro is 2.2× cheaper per token.
Price in rating: Excluded · Include price
DeepSeek
DeepSeek V4 Pro
67/100- ECI150.2
- Price$1.60 / $3.33
- Context1M
- Our pick
Google
Gemini 3 Pro Preview
80/100- ECI153.0
- Price$2.00 / $12.00
- Context1.05M
OpenAI
GPT-5.1
73/100- ECI151.0
- Price$1.25 / $10.00
- Context400K
Gemini 3 Pro Preview is our pick
Gemini 3 Pro Preview is the better all-round choice, scoring 80/100 against GPT-5.1 (73) and DeepSeek V4 Pro (67). It leads on capability and inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.
- CapabilityGemini 3 Pro PreviewCapabilities Index (ECI): Gemini 3 Pro Preview 153.0 · GPT-5.1 151.0 · DeepSeek V4 Pro 150.2
- Lowest priceDeepSeek V4 ProDeepSeek V4 Pro $2.03 · GPT-5.1 $3.44 · Gemini 3 Pro Preview $4.50 per 1M tokens (3:1 blend)
- Longest contextGemini 3 Pro PreviewGemini 3 Pro Preview 1,048,576 · DeepSeek V4 Pro 1,000,000 · GPT-5.1 400,000 tokens
- Widest inputsGemini 3 Pro PreviewDeepSeek V4 Pro: Text · Gemini 3 Pro Preview: Text, Images, PDFs, Audio, Video · GPT-5.1: Text, Images
- Self-hostingDeepSeek V4 ProPublishes downloadable weights
| Measure | Weight | DeepSeek V4 Pro | Gemini 3 Pro Preview | GPT-5.1 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 67% | 77 | 80 | 78 |
| Inputs & features | 20% | 35 | 90 | 70 |
| Context window | 13% | 64 | 65 | 50 |
| Overall | 100% | 67/100 | 80/100 | 73/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 150.2 | 153.0 (best) | 151.0 |
| ECI rank | #67 of 158 | #55 of 158 (best) | #64 of 158 |
| GPQA DiamondGraduate-level science questions | 90.9% | 92.6% (best) | 87.6% |
| FrontierMath Tiers 1–3Research-level mathematics | 45.3% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 96.7% (best) | 91.4% | 88.6% |
| SWE-bench VerifiedFixing real GitHub issues | 77.6% (best) | 72.9% | 68.0% |
| SimpleQA VerifiedShort factual questions | 47.0% | — | 48.0% (best) |
| Price per million tokens | |||
| Input | $1.60 | $2.00 | $1.25 (best) |
| Output | $3.33 (best) | $12.00 | $10.00 |
| Cached input | — | — | $0.125 |
| Blended (3:1) | $2.03 (best) | $4.50 | $3.44 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 65 providers | Median of 6 providers | Official OpenAI API |
| Limits | |||
| Context window | 1,000,000 tokens | 1,048,576 tokens (best) | 400,000 tokens |
| Max output | 384,000 tokens (best) | 65,536 tokens | 128,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | Yes | No |
| Audio | No | Yes | No |
| Video | No | Yes | No |
| Reasoning | Yes | Yes | Yeslow · medium · high |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | Open | Proprietary | Proprietary |
| API model ID | — | — | gpt-5.1 |
| API providers | 67 (best) | 8 | 32 |
| Released | Apr 24, 2026 | Nov 18, 2025 | Nov 13, 2025 |
| Knowledge cutoff | May 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.
DeepSeek V4 Pro$22.66
Gemini 3 Pro Preview$44.00
GPT-5.1$32.50
Which should you choose?
Which is better: DeepSeek V4 Pro, Gemini 3 Pro Preview or GPT-5.1?
Gemini 3 Pro Preview is the better all-round choice, scoring 80/100 against GPT-5.1 (73) and DeepSeek V4 Pro (67). It leads on capability and inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.
Which is cheaper, DeepSeek V4 Pro, Gemini 3 Pro Preview or GPT-5.1?
DeepSeek V4 Pro is cheaper at $1.60 input / $3.33 output per million tokens (median across 65 API providers). GPT-5.1 costs $1.25 input / $10.00 output per million tokens (official OpenAI API price); Gemini 3 Pro Preview costs $2.00 input / $12.00 output per million tokens (median across 6 API providers). At a typical mix of three input tokens to one output token, that is $2.03 per million tokens for DeepSeek V4 Pro versus $3.44 for GPT-5.1 (1.7× as much) and $4.50 for Gemini 3 Pro Preview (2.2× as much).
Which scores higher on benchmarks?
Gemini 3 Pro Preview scores higher on the Capabilities Index (ECI): Gemini 3 Pro Preview 153.0 (#55 of 158), GPT-5.1 151.0 (#64 of 158) and DeepSeek V4 Pro 150.2 (#67 of 158). The confidence ranges of the top two overlap (151.5–154.8 vs 149.4–152.6), so treat the gap as small. On individual benchmarks: GPQA Diamond — Gemini 3 Pro Preview 92.6%, DeepSeek V4 Pro 90.9%, GPT-5.1 87.6%; OTIS Mock AIME 2024–2025 — DeepSeek V4 Pro 96.7%, Gemini 3 Pro Preview 91.4%, GPT-5.1 88.6%; SWE-bench Verified — DeepSeek V4 Pro 77.6%, Gemini 3 Pro Preview 72.9%, GPT-5.1 68.0%.
Which is better for coding?
DeepSeek V4 Pro resolves more real GitHub issues on SWE-bench Verified: DeepSeek V4 Pro 77.6%, Gemini 3 Pro Preview 72.9% and GPT-5.1 68.0%. All three support tool calling for agent workflows.
Which has the bigger context window?
Gemini 3 Pro Preview has the largest context window at 1,048,576 tokens, against 1,000,000 for DeepSeek V4 Pro and 400,000 for GPT-5.1. Maximum output per response: DeepSeek V4 Pro up to 384,000, Gemini 3 Pro Preview up to 65,536, GPT-5.1 up to 128,000 tokens.
Which can read images, PDFs, audio or video?
DeepSeek V4 Pro accepts text; Gemini 3 Pro Preview accepts text, images, PDFs, audio and video; GPT-5.1 accepts text and images. Gemini 3 Pro Preview handles the widest range of inputs.
Are any of these open source?
DeepSeek V4 Pro publishes its weights and can be self-hosted; Gemini 3 Pro Preview and GPT-5.1 is proprietary.
Which is newer?
DeepSeek V4 Pro is the newest, released Apr 24, 2026. Gemini 3 Pro Preview came out Nov 18, 2025; GPT-5.1 came out Nov 13, 2025. Knowledge cutoff: DeepSeek V4 Pro May 2025, Gemini 3 Pro Preview Jan 2025, GPT-5.1 Sep 30, 2024.
How do you decide the winner?
This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, 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 Nov 18, 2026.