DeepSeek-R1 vs Gemini 2.5 Pro vs Claude Sonnet 4
Gemini 2.5 Pro comes out ahead, 63 to 51 and 51 on our weighted score, though DeepSeek-R1 is 2.9× cheaper per token.
DeepSeekDeepSeek-R1
51/100- ECI139.0
- Price$0.70 / $2.60
- Context128K
- Our pick
GoogleGemini 2.5 Pro
63/100- ECI145.3
- Price$1.25 / $10.00
- Context1.05M
AnthropicClaude Sonnet 4
51/100- ECI141.7
- Price$3.00 / $15.00
- Context200K
Gemini 2.5 Pro is our pick
Gemini 2.5 Pro is the better all-round choice, scoring 63/100 against DeepSeek-R1 (51) and Claude Sonnet 4 (51). It leads on capability, inputs & features and context window. DeepSeek-R1 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityGemini 2.5 ProCapabilities Index (ECI): Gemini 2.5 Pro 145.3 · Claude Sonnet 4 141.7 · DeepSeek-R1 139.0
- Lowest priceDeepSeek-R1DeepSeek-R1 $1.18 · Gemini 2.5 Pro $3.44 · Claude Sonnet 4 $6.00 per 1M tokens (3:1 blend)
- Longest contextGemini 2.5 ProGemini 2.5 Pro 1,048,576 · Claude Sonnet 4 200,000 · DeepSeek-R1 128,000 tokens
- Widest inputsGemini 2.5 ProDeepSeek-R1: Text · Gemini 2.5 Pro: Text, Images, PDFs, Audio, Video · Claude Sonnet 4: Text, Images, PDFs
- Self-hostingDeepSeek-R1Publishes downloadable weights
| Measure | Weight | DeepSeek-R1 | Gemini 2.5 Pro | Claude Sonnet 4 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 64 | 72 | 68 |
| Price | 25% | 47 | 24 | 13 |
| Inputs & features | 15% | 35 | 100 | 70 |
| Context window | 10% | 24 | 61 | 32 |
| Overall | 100% | 51/100 | 63/100 | 51/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | DeepSeek-R1DeepSeek | Gemini 2.5 ProGoogle | Claude Sonnet 4Anthropic |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 139.0 | 145.3 (best) | 141.7 |
| ECI rank | #104 of 148 | #78 of 148 (best) | #94 of 148 |
| GPQA DiamondGraduate-level science questions | 71.7% | 85.3% (best) | 79.2% |
| FrontierMath Tiers 1–3Research-level mathematics | — | 24.6% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 53.3% | 84.7% (best) | 71.1% |
| SWE-bench VerifiedFixing real GitHub issues | — | 57.6% | — |
| Price per million tokens | |||
| Input | $0.70 (best) | $1.25 | $3.00 |
| Output | $2.60 (best) | $10.00 | $15.00 |
| Cached input | — | $0.125 | — |
| Blended (3:1) | $1.18 (best) | $3.44 | $6.00 |
| Long-context rate | Same rate | Over 200K: $2.50 / $15.00 | Same rate |
| Price source | Median of 11 providers | Official Google API | Median of 9 providers |
| Limits | |||
| Context window | 128,000 tokens | 1,048,576 tokens (best) | 200,000 tokens |
| Max output | 32,768 tokens | 65,536 tokens (best) | 64,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | Yes | Yes |
| Audio | No | Yes | No |
| Video | No | Yes | No |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Open | Proprietary | Proprietary |
| API model ID | — | gemini-2.5-pro | — |
| API providers | 12 | 22 (best) | 9 |
| Released | Jan 20, 2025 | Jun 17, 2025 | May 22, 2025 |
| Knowledge cutoff | Jul 2024 | Jan 2025 | Mar 31, 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- DeepSeek-R1$12.20
- Gemini 2.5 Pro$32.50
- Claude Sonnet 4$60.00
Which should you choose?
Which is better: DeepSeek-R1, Gemini 2.5 Pro or Claude Sonnet 4?
Gemini 2.5 Pro is the better all-round choice, scoring 63/100 against DeepSeek-R1 (51) and Claude Sonnet 4 (51). It leads on capability, inputs & features and context window. DeepSeek-R1 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, DeepSeek-R1, Gemini 2.5 Pro or Claude Sonnet 4?
DeepSeek-R1 is cheaper at $0.70 input / $2.60 output per million tokens (median across 11 API providers). Gemini 2.5 Pro costs $1.25 input / $10.00 output per million tokens (official Google API price); Claude Sonnet 4 costs $3.00 input / $15.00 output per million tokens (median across 9 API providers). At a typical mix of three input tokens to one output token, that is $1.18 per million tokens for DeepSeek-R1 versus $3.44 for Gemini 2.5 Pro (2.9× as much) and $6.00 for Claude Sonnet 4 (5.1× as much).
Which scores higher on benchmarks?
Gemini 2.5 Pro scores higher on the Capabilities Index (ECI): Gemini 2.5 Pro 145.3 (#78 of 148), Claude Sonnet 4 141.7 (#94 of 148) and DeepSeek-R1 139.0 (#104 of 148). Their confidence ranges do not overlap (143.6–146.9 vs 139.2–142.9), so the gap is a real one. On individual benchmarks: GPQA Diamond — Gemini 2.5 Pro 85.3%, Claude Sonnet 4 79.2%, DeepSeek-R1 71.7%; OTIS Mock AIME 2024–2025 — Gemini 2.5 Pro 84.7%, Claude Sonnet 4 71.1%, DeepSeek-R1 53.3%.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek-R1 and Claude Sonnet 4 yet, so there is no like-for-like coding score. On overall capability, Gemini 2.5 Pro leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.
Which has the bigger context window?
Gemini 2.5 Pro has the largest context window at 1,048,576 tokens, against 200,000 for Claude Sonnet 4 and 128,000 for DeepSeek-R1. Maximum output per response: DeepSeek-R1 up to 32,768, Gemini 2.5 Pro up to 65,536, Claude Sonnet 4 up to 64,000 tokens.
Which can read images, PDFs, audio or video?
DeepSeek-R1 accepts text; Gemini 2.5 Pro accepts text, images, PDFs, audio and video; Claude Sonnet 4 accepts text, images and PDFs. Gemini 2.5 Pro handles the widest range of inputs.
Are any of these open source?
DeepSeek-R1 publishes its weights and can be self-hosted; Gemini 2.5 Pro and Claude Sonnet 4 is proprietary.
Which is newer?
Gemini 2.5 Pro is the newest, released Jun 17, 2025. Claude Sonnet 4 came out May 22, 2025; DeepSeek-R1 came out Jan 20, 2025. Knowledge cutoff: DeepSeek-R1 Jul 2024, Gemini 2.5 Pro Jan 2025, Claude Sonnet 4 Mar 31, 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.
