DeepSeek R1 0528 vs Claude Haiku 3 vs Gemini 2.5 Flash
Gemini 2.5 Flash comes out ahead, 69 to 55 and 52 on our weighted score, though Claude Haiku 3 is 41% cheaper per token.
Price in rating: Included · Exclude price
DeepSeek
DeepSeek R1 0528
55/100- ECI140.8
- Price$0.512 / $2.19
- Context164K
Anthropic
Claude Haiku 3
52/100- ECI117.8
- Price$0.25 / $1.25
- Context200K
- Our pick
Google
Gemini 2.5 Flash
69/100- ECI140.8
- Price$0.30 / $2.50
- Context1.05M
Gemini 2.5 Flash is our pick
Gemini 2.5 Flash is the better all-round choice, scoring 69/100 against DeepSeek R1 0528 (55) and Claude Haiku 3 (52). It leads on inputs & features and context window. Claude Haiku 3 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityGemini 2.5 FlashCapabilities Index (ECI): Gemini 2.5 Flash 140.8 · DeepSeek R1 0528 140.8 · Claude Haiku 3 117.8
- Lowest priceClaude Haiku 3Claude Haiku 3 $0.50 · Gemini 2.5 Flash $0.85 · DeepSeek R1 0528 $0.932 per 1M tokens (3:1 blend)
- Longest contextGemini 2.5 FlashGemini 2.5 Flash 1,048,576 · Claude Haiku 3 200,000 · DeepSeek R1 0528 163,840 tokens
- Widest inputsGemini 2.5 FlashDeepSeek R1 0528: Text · Claude Haiku 3: Text, Images, PDFs · Gemini 2.5 Flash: Text, Images, PDFs, Audio, Video
- Self-hostingDeepSeek R1 0528Publishes downloadable weights (MIT)
| Measure | Weight | DeepSeek R1 0528 | Claude Haiku 3 | Gemini 2.5 Flash |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 69 | 47 | 69 |
| Price | 25% | 49 | 61 | 51 |
| Inputs & features | 15% | 35 | 60 | 100 |
| Context window | 10% | 36 | 39 | 65 |
| Overall | 100% | 55/100 | 52/100 | 69/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 140.8 | 117.8 | 140.8 (best) |
| ECI rank | #113 of 158 | #154 of 158 | #111 of 158 (best) |
| GPQA DiamondGraduate-level science questions | 76.3% (best) | 36.3% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 66.4% (best) | 1.8% | — |
| Price per million tokens | |||
| Input | $0.512 | $0.25 (best) | $0.30 |
| Output | $2.19 | $1.25 (best) | $2.50 |
| Cached input | — | — | $0.03 |
| Blended (3:1) | $0.932 | $0.50 (best) | $0.85 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 16 providers | Median of 3 providers | Official Google API |
| Limits | |||
| Context window | 163,840 tokens | 200,000 tokens | 1,048,576 tokens (best) |
| Max output | 32,768 tokens | 4,096 tokens | 65,536 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | Yes | Yes |
| Audio | No | No | Yes |
| Video | No | No | Yes |
| Reasoning | Yes | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | OpenMIT | Proprietary | Proprietary |
| API model ID | — | — | gemini-2.5-flash |
| API providers | 16 | 3 | 31 (best) |
| Released | May 28, 2025 | Mar 13, 2024 | Jun 17, 2025 |
| Knowledge cutoff | — | Aug 31, 2023 | 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
Claude Haiku 3$5.00
Gemini 2.5 Flash$8.00
Which should you choose?
Which is better: DeepSeek R1 0528, Claude Haiku 3 or Gemini 2.5 Flash?
Gemini 2.5 Flash is the better all-round choice, scoring 69/100 against DeepSeek R1 0528 (55) and Claude Haiku 3 (52). It leads on inputs & features and context window. Claude Haiku 3 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, DeepSeek R1 0528, Claude Haiku 3 or Gemini 2.5 Flash?
Claude Haiku 3 is cheaper at $0.25 input / $1.25 output per million tokens (median across 3 API providers). Gemini 2.5 Flash costs $0.30 input / $2.50 output per million tokens (official Google API price); DeepSeek R1 0528 costs $0.512 input / $2.19 output per million tokens (median across 16 API providers). At a typical mix of three input tokens to one output token, that is $0.50 per million tokens for Claude Haiku 3 versus $0.85 for Gemini 2.5 Flash (1.7× as much) and $0.932 for DeepSeek R1 0528 (1.9× as much).
Which scores higher on benchmarks?
Gemini 2.5 Flash scores higher on the Capabilities Index (ECI): Gemini 2.5 Flash 140.8 (#111 of 158), DeepSeek R1 0528 140.8 (#113 of 158) and Claude Haiku 3 117.8 (#154 of 158). The confidence ranges of the top two overlap (138.4–143.1 vs 138.9–142.5), so treat the gap as small.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek R1 0528, Claude Haiku 3 and Gemini 2.5 Flash yet, so there is no like-for-like coding score. On overall capability, Gemini 2.5 Flash 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 has the largest context window at 1,048,576 tokens, against 200,000 for Claude Haiku 3 and 163,840 for DeepSeek R1 0528. Maximum output per response: DeepSeek R1 0528 up to 32,768, Claude Haiku 3 up to 4,096, Gemini 2.5 Flash up to 65,536 tokens.
Which can read images, PDFs, audio or video?
DeepSeek R1 0528 accepts text; Claude Haiku 3 accepts text, images and PDFs; Gemini 2.5 Flash accepts text, images, PDFs, audio and video. Gemini 2.5 Flash handles the widest range of inputs.
Are any of these open source?
DeepSeek R1 0528 publishes its weights (MIT) and can be self-hosted; Claude Haiku 3 and Gemini 2.5 Flash is proprietary.
Which is newer?
Gemini 2.5 Flash is the newest, released Jun 17, 2025. DeepSeek R1 0528 came out May 28, 2025; Claude Haiku 3 came out Mar 13, 2024. Knowledge cutoff: Claude Haiku 3 Aug 31, 2023, Gemini 2.5 Flash Jan 2025.
How do you decide the winner?
This rating uses 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 Nov 18, 2026.