Baichuan M2 32B vs DeepSeek-R1 vs Kimi K2 Instruct
Baichuan M2 32B comes out ahead, 58 to 36 and 34 on our weighted score, and it is the cheaper option too.
- Our pick
BaichuanBaichuan M2 32B
58/100- ECI—
- Price$0.07 / $0.07
- Context131K
DeepSeekDeepSeek-R1
34/100- ECI138.8
- Price$0.70 / $4.88
- Context128K
Moonshot AIKimi K2 Instruct
36/100- ECI139.9
- Price$0.57 / $2.30
- Context131K
Baichuan M2 32B is our pick
Baichuan M2 32B is the better all-round choice, scoring 58/100 against Kimi K2 Instruct (36) and DeepSeek-R1 (34). It leads on price. DeepSeek-R1 wins on inputs & features. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceBaichuan M2 32BBaichuan M2 32B $0.07 · Kimi K2 Instruct $1.00 · DeepSeek-R1 $1.75 per 1M tokens (3:1 blend)
- Longest contextBaichuan M2 32B and Kimi K2 InstructBaichuan M2 32B 131,072 · Kimi K2 Instruct 131,072 · DeepSeek-R1 128,000 tokens
- Widest inputsSame inputsBaichuan M2 32B: Text · DeepSeek-R1: Text · Kimi K2 Instruct: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Baichuan M2 32B | DeepSeek-R1 | Kimi K2 Instruct |
|---|---|---|---|---|
| Price | 50% | 100 | 37 | 48 |
| Inputs & features | 30% | 10 | 35 | 25 |
| Context window | 20% | 25 | 24 | 25 |
| Overall | 100% | 58/100 | 34/100 | 36/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Baichuan M2 32BBaichuan | DeepSeek-R1DeepSeek | Kimi K2 InstructMoonshot AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | 138.8 | 139.9 (best) |
| ECI rank | — | #119 of 165 | #112 of 165 (best) |
| GPQA DiamondGraduate-level science questions | — | 71.7% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 53.3% | — |
| Price per million tokens | |||
| Input | $0.07 (best) | $0.70 | $0.57 |
| Output | $0.07 (best) | $4.88 | $2.30 |
| Cached input | — | — | — |
| Blended (3:1) | $0.07 (best) | $1.75 | $1.00 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Median of 11 providers | Median of 11 providers |
| Limits | |||
| Context window | 131,072 tokens (best) | 128,000 tokens | 131,072 tokens (best) |
| Max output | 131,072 tokens (best) | 32,768 tokens | 32,768 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | Yes | No |
| Tool calling | No | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenApache-2.0 | Open | OpenModified MIT |
| API model ID | — | — | — |
| API providers | 1 | 12 (best) | 11 |
| Released | Aug 13, 2025 | Jan 20, 2025 | Jul 11, 2025 |
| Knowledge cutoff | — | Jul 2024 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Baichuan M2 32B$0.84
- DeepSeek-R1$16.76
- Kimi K2 Instruct$10.30
Which should you choose?
Which is better: Baichuan M2 32B, DeepSeek-R1 or Kimi K2 Instruct?
Baichuan M2 32B is the better all-round choice, scoring 58/100 against Kimi K2 Instruct (36) and DeepSeek-R1 (34). It leads on price. DeepSeek-R1 wins on inputs & features. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Baichuan M2 32B, DeepSeek-R1 or Kimi K2 Instruct?
Baichuan M2 32B is cheaper at $0.07 input / $0.07 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); DeepSeek-R1 costs $0.70 input / $4.88 output per million tokens (median across 11 API providers). At a typical mix of three input tokens to one output token, that is $0.07 per million tokens for Baichuan M2 32B versus $1.00 for Kimi K2 Instruct (14× as much) and $1.75 for DeepSeek-R1 (25× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Baichuan M2 32B has not been scored yet, DeepSeek-R1 has an ECI of 138.8 and Kimi K2 Instruct has an ECI of 139.9.
Which is better for coding?
There are no published SWE-bench Verified results for Baichuan M2 32B, DeepSeek-R1 and Kimi K2 Instruct yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Baichuan M2 32B does not support tool calling, which most coding agents need.
Which has the bigger context window?
Baichuan M2 32B and Kimi K2 Instruct have the largest context windows (131,072 and 131,072 tokens), against 128,000 for DeepSeek-R1. Maximum output per response: Baichuan M2 32B up to 131,072, DeepSeek-R1 up to 32,768, Kimi K2 Instruct up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Baichuan M2 32B accepts text; DeepSeek-R1 accepts text; Kimi K2 Instruct accepts text. They handle the same number of input types.
Are any of these open source?
Yes, all three publish their weights (Apache-2.0 and Modified MIT), so you can self-host them.
Which is newer?
Baichuan M2 32B is the newest, released Aug 13, 2025. Kimi K2 Instruct came out Jul 11, 2025; DeepSeek-R1 came out Jan 20, 2025. Knowledge cutoff: DeepSeek-R1 Jul 2024.
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 Nov 2, 2026.
