DeepSeek R1 0528 vs Gemini 2.5 Flash Preview 05-20 vs Kimi K2 Instruct
Gemini 2.5 Flash Preview 05-20 comes out ahead, 73 to 57 and 55 on our weighted score.
Price in rating: Excluded · Include price
DeepSeek
DeepSeek R1 0528
57/100- ECI140.8
- Price$0.512 / $2.19
- Context164K
- Our pick
Google
Gemini 2.5 Flash Preview 05-20
73/100- ECI141.6
- Price$0.142 / $3.33
- Context1.05M
Moonshot AI
Kimi K2 Instruct
55/100- ECI141.3
- Price$0.57 / $2.30
- Context131K
Gemini 2.5 Flash Preview 05-20 is our pick
Gemini 2.5 Flash Preview 05-20 is the better all-round choice, scoring 73/100 against DeepSeek R1 0528 (57) and Kimi K2 Instruct (55). It leads on inputs & features and context window. The score weighs capability 67%, inputs & features 20%, context window 13%.
- CapabilityGemini 2.5 Flash Preview 05-20Capabilities Index (ECI): Gemini 2.5 Flash Preview 05-20 141.6 · Kimi K2 Instruct 141.3 · DeepSeek R1 0528 140.8
- Lowest priceDeepSeek R1 0528DeepSeek R1 0528 $0.932 · Gemini 2.5 Flash Preview 05-20 $0.938 · Kimi K2 Instruct $1.00 per 1M tokens (3:1 blend)
- Longest contextGemini 2.5 Flash Preview 05-20Gemini 2.5 Flash Preview 05-20 1,048,576 · DeepSeek R1 0528 163,840 · Kimi K2 Instruct 131,072 tokens
- Widest inputsGemini 2.5 Flash Preview 05-20DeepSeek R1 0528: Text · Gemini 2.5 Flash Preview 05-20: Text, Images, PDFs, Audio, Video · Kimi K2 Instruct: Text
- Self-hostingDeepSeek R1 0528 and Kimi K2 InstructPublishes downloadable weights (MIT and Modified MIT)
| Measure | Weight | DeepSeek R1 0528 | Gemini 2.5 Flash Preview 05-20 | Kimi K2 Instruct |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 67% | 69 | 69 | 69 |
| Inputs & features | 20% | 35 | 90 | 25 |
| Context window | 13% | 36 | 65 | 32 |
| Overall | 100% | 57/100 | 73/100 | 55/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 140.8 | 141.6 (best) | 141.3 |
| ECI rank | #113 of 158 | #106 of 158 (best) | #108 of 158 |
| GPQA DiamondGraduate-level science questions | 76.3% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 66.4% | 70.8% (best) | — |
| Price per million tokens | |||
| Input | $0.512 | $0.142 (best) | $0.57 |
| Output | $2.19 (best) | $3.33 | $2.30 |
| Cached input | — | — | — |
| Blended (3:1) | $0.932 (best) | $0.938 | $1.00 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 16 providers | Median of 1 providers | Median of 11 providers |
| Limits | |||
| Context window | 163,840 tokens | 1,048,576 tokens (best) | 131,072 tokens |
| Max output | 32,768 tokens | 65,536 tokens (best) | 32,768 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | Yes | No |
| Audio | No | Yes | No |
| Video | No | Yes | No |
| Reasoning | Yes | Yes | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenMIT | Proprietary | OpenModified MIT |
| API model ID | — | — | — |
| API providers | 16 (best) | 1 | 11 |
| Released | May 28, 2025 | May 20, 2025 | Jul 11, 2025 |
| Knowledge cutoff | — | 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.
DeepSeek R1 0528$9.50
Gemini 2.5 Flash Preview 05-20$8.07
Kimi K2 Instruct$10.30
Which should you choose?
Which is better: DeepSeek R1 0528, Gemini 2.5 Flash Preview 05-20 or Kimi K2 Instruct?
Gemini 2.5 Flash Preview 05-20 is the better all-round choice, scoring 73/100 against DeepSeek R1 0528 (57) and Kimi K2 Instruct (55). It leads on inputs & features and context window. The score weighs capability 67%, inputs & features 20%, context window 13%.
Which is cheaper, DeepSeek R1 0528, Gemini 2.5 Flash Preview 05-20 or Kimi K2 Instruct?
DeepSeek R1 0528 is cheaper at $0.512 input / $2.19 output per million tokens (median across 16 API providers). Gemini 2.5 Flash Preview 05-20 costs $0.142 input / $3.33 output per million tokens (median across 1 API provider); Kimi K2 Instruct costs $0.57 input / $2.30 output per million tokens (median across 11 API providers). At a typical mix of three input tokens to one output token, that is $0.932 per million tokens for DeepSeek R1 0528 versus $0.938 for Gemini 2.5 Flash Preview 05-20 (1× as much) and $1.00 for Kimi K2 Instruct (1.1× as much).
Which scores higher on benchmarks?
Gemini 2.5 Flash Preview 05-20 scores higher on the Capabilities Index (ECI): Gemini 2.5 Flash Preview 05-20 141.6 (#106 of 158), Kimi K2 Instruct 141.3 (#108 of 158) and DeepSeek R1 0528 140.8 (#113 of 158). The confidence ranges of the top two overlap (139.4–143.6 vs 138.3–144.0), so treat the gap as small.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek R1 0528, Gemini 2.5 Flash Preview 05-20 and Kimi K2 Instruct yet, so there is no like-for-like coding score. On overall capability, Gemini 2.5 Flash Preview 05-20 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 Flash Preview 05-20 has the largest context window at 1,048,576 tokens, against 163,840 for DeepSeek R1 0528 and 131,072 for Kimi K2 Instruct. Maximum output per response: DeepSeek R1 0528 up to 32,768, Gemini 2.5 Flash Preview 05-20 up to 65,536, Kimi K2 Instruct up to 32,768 tokens.
Which can read images, PDFs, audio or video?
DeepSeek R1 0528 accepts text; Gemini 2.5 Flash Preview 05-20 accepts text, images, PDFs, audio and video; Kimi K2 Instruct accepts text. Gemini 2.5 Flash Preview 05-20 handles the widest range of inputs.
Are any of these open source?
DeepSeek R1 0528 and Kimi K2 Instruct publishes its weights (MIT and Modified MIT) and can be self-hosted; Gemini 2.5 Flash Preview 05-20 is proprietary.
Which is newer?
Kimi K2 Instruct is the newest, released Jul 11, 2025. DeepSeek R1 0528 came out May 28, 2025; Gemini 2.5 Flash Preview 05-20 came out May 20, 2025. Knowledge cutoff: Gemini 2.5 Flash Preview 05-20 Jan 2025.
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.