DeepSeek-R1 vs Kimi K2 Instruct vs Claude Sonnet 3.7
Claude Sonnet 3.7 comes out ahead, 65 to 56 and 55 on our weighted score, though Kimi K2 Instruct is 6× cheaper per token.
Price in rating: Excluded · Include price
DeepSeek
DeepSeek-R1
56/100- ECI138.6
- Price$1.02 / $5.14
- Context128K
Moonshot AI
Kimi K2 Instruct
55/100- ECI141.3
- Price$0.57 / $2.30
- Context131K
- Our pick
Anthropic
Claude Sonnet 3.7
65/100- ECI141.1
- Price$3.00 / $15.00
- Context200K
Claude Sonnet 3.7 is our pick
Claude Sonnet 3.7 is the better all-round choice, scoring 65/100 against DeepSeek-R1 (56) and Kimi K2 Instruct (55). It leads on inputs & features and context window. The score weighs capability 67%, inputs & features 20%, context window 13%.
- CapabilityKimi K2 InstructCapabilities Index (ECI): Kimi K2 Instruct 141.3 · Claude Sonnet 3.7 141.1 · DeepSeek-R1 138.6
- Lowest priceKimi K2 InstructKimi K2 Instruct $1.00 · DeepSeek-R1 $2.05 · Claude Sonnet 3.7 $6.00 per 1M tokens (3:1 blend)
- Longest contextClaude Sonnet 3.7Claude Sonnet 3.7 200,000 · Kimi K2 Instruct 131,072 · DeepSeek-R1 128,000 tokens
- Widest inputsClaude Sonnet 3.7DeepSeek-R1: Text · Kimi K2 Instruct: Text · Claude Sonnet 3.7: Text, Images, PDFs
- Self-hostingDeepSeek-R1 and Kimi K2 InstructPublishes downloadable weights (Modified MIT)
| Measure | Weight | DeepSeek-R1 | Kimi K2 Instruct | Claude Sonnet 3.7 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 67% | 67 | 69 | 69 |
| Inputs & features | 20% | 35 | 25 | 70 |
| Context window | 13% | 32 | 32 | 39 |
| Overall | 100% | 56/100 | 55/100 | 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 | 141.3 (best) | 141.1 |
| ECI rank | #118 of 158 | #108 of 158 (best) | #110 of 158 |
| GPQA DiamondGraduate-level science questions | 71.7% | — | 79.7% (best) |
| OTIS Mock AIME 2024–2025Competition mathematics | 53.3% | — | 57.8% (best) |
| SWE-bench VerifiedFixing real GitHub issues | — | — | 61.0% |
| Price per million tokens | |||
| Input | $1.02 | $0.57 (best) | $3.00 |
| Output | $5.14 | $2.30 (best) | $15.00 |
| Cached input | — | — | — |
| Blended (3:1) | $2.05 | $1.00 (best) | $6.00 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 12 providers | Median of 11 providers | Median of 3 providers |
| Limits | |||
| Context window | 128,000 tokens | 131,072 tokens | 200,000 tokens (best) |
| Max output | 32,768 tokens | 32,768 tokens | 64,000 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | Yes |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | OpenModified MIT | Proprietary |
| API model ID | — | — | — |
| API providers | 13 (best) | 11 | 4 |
| Released | Jan 20, 2025 | Jul 11, 2025 | Feb 19, 2025 |
| Knowledge cutoff | Jul 2024 | — | 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
Kimi K2 Instruct$10.30
Claude Sonnet 3.7$60.00
Which should you choose?
Which is better: DeepSeek-R1, Kimi K2 Instruct or Claude Sonnet 3.7?
Claude Sonnet 3.7 is the better all-round choice, scoring 65/100 against DeepSeek-R1 (56) 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, Kimi K2 Instruct or Claude Sonnet 3.7?
Kimi K2 Instruct is cheaper at $0.57 input / $2.30 output per million tokens (median across 11 API providers). 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 $1.00 per million tokens for Kimi K2 Instruct versus $2.05 for DeepSeek-R1 (2× as much) and $6.00 for Claude Sonnet 3.7 (6× as much).
Which scores higher on benchmarks?
Kimi K2 Instruct scores higher on the Capabilities Index (ECI): Kimi K2 Instruct 141.3 (#108 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 (138.3–144.0 vs 139.4–142.6), so treat the gap as small.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek-R1 and Kimi K2 Instruct yet, so there is no like-for-like coding score. On overall capability, Kimi K2 Instruct 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 Sonnet 3.7 has the largest context window at 200,000 tokens, against 131,072 for Kimi K2 Instruct and 128,000 for DeepSeek-R1. Maximum output per response: DeepSeek-R1 up to 32,768, Kimi K2 Instruct up to 32,768, Claude Sonnet 3.7 up to 64,000 tokens.
Which can read images, PDFs, audio or video?
DeepSeek-R1 accepts text; Kimi K2 Instruct accepts text; Claude Sonnet 3.7 accepts text, images and PDFs. Claude Sonnet 3.7 handles the widest range of inputs.
Are any of these open source?
DeepSeek-R1 and Kimi K2 Instruct publishes its weights (Modified MIT) and can be self-hosted; Claude Sonnet 3.7 is proprietary.
Which is newer?
Kimi K2 Instruct is the newest, released Jul 11, 2025. Claude Sonnet 3.7 came out Feb 19, 2025; DeepSeek-R1 came out Jan 20, 2025. Knowledge cutoff: DeepSeek-R1 Jul 2024, 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.