DeepSeek-R1 vs Claude Haiku 4.5 vs Claude Sonnet 3.7
Claude Haiku 4.5 comes out ahead, 68 to 65 and 56 on our weighted score, and it is the cheaper option too.
Price in rating: Excluded · Include price
DeepSeek
DeepSeek-R1
56/100- ECI138.6
- Price$1.02 / $5.14
- Context128K
- Our pick
Anthropic
Claude Haiku 4.5
68/100- ECI142.8
- Price$1.00 / $5.00
- Context200K
Anthropic
Claude Sonnet 3.7
65/100- ECI141.1
- Price$3.00 / $15.00
- Context200K
Claude Haiku 4.5 is our pick
Claude Haiku 4.5 is the better all-round choice, scoring 68/100 against Claude Sonnet 3.7 (65) and DeepSeek-R1 (56). It leads on capability and inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.
- CapabilityClaude Haiku 4.5Capabilities Index (ECI): Claude Haiku 4.5 142.8 · Claude Sonnet 3.7 141.1 · DeepSeek-R1 138.6
- Lowest priceClaude Haiku 4.5Claude Haiku 4.5 $2.00 · DeepSeek-R1 $2.05 · Claude Sonnet 3.7 $6.00 per 1M tokens (3:1 blend)
- Longest contextClaude Haiku 4.5 and Claude Sonnet 3.7Claude Haiku 4.5 200,000 · Claude Sonnet 3.7 200,000 · DeepSeek-R1 128,000 tokens
- Widest inputsClaude Haiku 4.5 and Claude Sonnet 3.7DeepSeek-R1: Text · Claude Haiku 4.5: Text, Images, PDFs · Claude Sonnet 3.7: Text, Images, PDFs
- Self-hostingDeepSeek-R1Publishes downloadable weights
| Measure | Weight | DeepSeek-R1 | Claude Haiku 4.5 | Claude Sonnet 3.7 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 67% | 67 | 70 | 69 |
| Inputs & features | 20% | 35 | 80 | 70 |
| Context window | 13% | 32 | 39 | 39 |
| Overall | 100% | 56/100 | 68/100 | 65/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 138.6 | 142.8 (best) | 141.1 |
| ECI rank | #118 of 158 | #102 of 158 (best) | #110 of 158 |
| GPQA DiamondGraduate-level science questions | 71.7% | 71.2% | 79.7% (best) |
| OTIS Mock AIME 2024–2025Competition mathematics | 53.3% | 66.7% (best) | 57.8% |
| SWE-bench VerifiedFixing real GitHub issues | — | — | 61.0% |
| SimpleQA VerifiedShort factual questions | — | 13.2% | — |
| Price per million tokens | |||
| Input | $1.02 | $1.00 (best) | $3.00 |
| Output | $5.14 | $5.00 (best) | $15.00 |
| Cached input | — | $0.10 | — |
| Blended (3:1) | $2.05 | $2.00 (best) | $6.00 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 12 providers | Official Anthropic API | Median of 3 providers |
| Limits | |||
| Context window | 128,000 tokens | 200,000 tokens (best) | 200,000 tokens (best) |
| Max output | 32,768 tokens | 64,000 tokens (best) | 64,000 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | Yes | Yes |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Open | Proprietary | Proprietary |
| API model ID | — | claude-haiku-4-5 | — |
| API providers | 13 | 57 (best) | 4 |
| Released | Jan 20, 2025 | Oct 15, 2025 | Feb 19, 2025 |
| Knowledge cutoff | Jul 2024 | Feb 28, 2025 | Oct 31, 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-R1$20.53
Claude Haiku 4.5$20.00
Claude Sonnet 3.7$60.00
Which should you choose?
Which is better: DeepSeek-R1, Claude Haiku 4.5 or Claude Sonnet 3.7?
Claude Haiku 4.5 is the better all-round choice, scoring 68/100 against Claude Sonnet 3.7 (65) and DeepSeek-R1 (56). It leads on capability and inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.
Which is cheaper, DeepSeek-R1, Claude Haiku 4.5 or Claude Sonnet 3.7?
Claude Haiku 4.5 is cheaper at $1.00 input / $5.00 output per million tokens (official Anthropic API price). DeepSeek-R1 costs $1.02 input / $5.14 output per million tokens (median across 12 API providers); Claude Sonnet 3.7 costs $3.00 input / $15.00 output per million tokens (median across 3 API providers). At a typical mix of three input tokens to one output token, that is $2.00 per million tokens for Claude Haiku 4.5 versus $2.05 for DeepSeek-R1 (1× as much) and $6.00 for Claude Sonnet 3.7 (3× as much).
Which scores higher on benchmarks?
Claude Haiku 4.5 scores higher on the Capabilities Index (ECI): Claude Haiku 4.5 142.8 (#102 of 158), Claude Sonnet 3.7 141.1 (#110 of 158) and DeepSeek-R1 138.6 (#118 of 158). The confidence ranges of the top two overlap (141.2–144.3 vs 139.4–142.6), so treat the gap as small. On individual benchmarks: GPQA Diamond — Claude Sonnet 3.7 79.7%, DeepSeek-R1 71.7%, Claude Haiku 4.5 71.2%; OTIS Mock AIME 2024–2025 — Claude Haiku 4.5 66.7%, Claude Sonnet 3.7 57.8%, DeepSeek-R1 53.3%.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek-R1 and Claude Haiku 4.5 yet, so there is no like-for-like coding score. On overall capability, Claude Haiku 4.5 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?
Claude Haiku 4.5 and Claude Sonnet 3.7 have the largest context windows (200,000 and 200,000 tokens), against 128,000 for DeepSeek-R1. Maximum output per response: DeepSeek-R1 up to 32,768, Claude Haiku 4.5 up to 64,000, Claude Sonnet 3.7 up to 64,000 tokens.
Which can read images, PDFs, audio or video?
DeepSeek-R1 accepts text; Claude Haiku 4.5 accepts text, images and PDFs; Claude Sonnet 3.7 accepts text, images and PDFs. Claude Haiku 4.5 handles the widest range of inputs.
Are any of these open source?
DeepSeek-R1 publishes its weights and can be self-hosted; Claude Haiku 4.5 and Claude Sonnet 3.7 is proprietary.
Which is newer?
Claude Haiku 4.5 is the newest, released Oct 15, 2025. Claude Sonnet 3.7 came out Feb 19, 2025; DeepSeek-R1 came out Jan 20, 2025. Knowledge cutoff: DeepSeek-R1 Jul 2024, Claude Haiku 4.5 Feb 28, 2025, Claude Sonnet 3.7 Oct 31, 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.