DeepSeek-R1 vs DeepSeek R1 0528 vs Qwen3 32B
DeepSeek R1 0528 comes out ahead, 59 to 55 and 53 on our weighted score, and it is the cheaper option too.Too close to call on our weighted score (DeepSeek R1 0528 63, DeepSeek-R1 61, Qwen3 32B 60). The right pick depends on what you value most.
DeepSeek
DeepSeek-R1
53/100- ECI138.6
- Price$1.02 / $5.14
- Context128K
- Our pick
DeepSeek
DeepSeek R1 0528
59/100- ECI140.7
- Price$0.571 / $2.29
- Context164K
Alibaba (Qwen)
Qwen3 32B
55/100- ECI136.9
- Price$0.70 / $2.80
- Context131K
DeepSeek
DeepSeek-R1
61/100- ECI138.6
- Price$1.02 / $5.14
- Context128K
DeepSeek
DeepSeek R1 0528
63/100- ECI140.7
- Price$0.571 / $2.29
- Context164K
Alibaba (Qwen)
Qwen3 32B
60/100- ECI136.9
- Price$0.70 / $2.80
- Context131K
DeepSeek R1 0528 is our pickToo close to call
DeepSeek R1 0528 is the better all-round choice, scoring 59/100 against Qwen3 32B (55) and DeepSeek-R1 (53). It leads on capability, price and context window. The score weighs capability 59%, price 29%, context window 12%.It is close. Our weighted score puts them within 2 points (DeepSeek R1 0528 63/100, DeepSeek-R1 61/100, Qwen3 32B 60/100), so choose by what matters most for your work: DeepSeek R1 0528 for raw capability. The score weighs capability 83%, context window 17%.
- CapabilityDeepSeek R1 0528Capabilities Index (ECI): DeepSeek R1 0528 140.7 · DeepSeek-R1 138.6 · Qwen3 32B 136.9
- Lowest priceDeepSeek R1 0528DeepSeek R1 0528 $1 · Qwen3 32B $1.23 · DeepSeek-R1 $2.05 per 1M tokens (3:1 blend)
- Longest contextDeepSeek R1 0528DeepSeek R1 0528 163,840 · Qwen3 32B 131,072 · DeepSeek-R1 128,000 tokens
- Widest inputsSame inputsDeepSeek-R1: Text · DeepSeek R1 0528: Text · Qwen3 32B: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | DeepSeek-R1 | DeepSeek R1 0528 | Qwen3 32B |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 59% | 67 | 69 | 65 |
| Price | 29% | 34 | 48 | 44 |
| Context window | 12% | 32 | 36 | 32 |
| Overall | 100% | 53/100 | 59/100 | 55/100 |
Left out because at least one model lacks the data: inputs & features. The remaining weights were rescaled.
| Measure | Weight | DeepSeek-R1 | DeepSeek R1 0528 | Qwen3 32B |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 83% | 67 | 69 | 65 |
| Context window | 17% | 32 | 36 | 32 |
| Overall | 100% | 61/100 | 63/100 | 60/100 |
Left out because at least one model lacks the data: inputs & features. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Unavailable specifications are marked “Not published”. Publisher results include their evaluation settings and source.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 138.6 | 140.7 (best) | 136.9 |
| ECI rank | #119 of 159 | #114 of 159 (best) | #122 of 159 |
| ECI confidence interval | 136.6–140.5 | 138.9–142.4 | 134.4–139.1 |
| ECI evaluation date | Jan 20, 2025 | May 28, 2025 | Apr 29, 2025 |
| Documented capabilities | Classic open reasoning model for transparent math, coding, and deliberate problem solving | May 2025 DeepSeek R1 update with improved mathematics, coding, and reasoning | Dense open Qwen model for self-hosted chat, reasoning, and coding |
| Model parameters | Not published | Not published | Not published |
| Output modalities | Text | Text | Text |
| GPQA DiamondGraduate-level science questions | 71.7% | 76.3% (best) | 65.7% |
| OTIS Mock AIME 2024–2025Competition mathematics | 53.3% | 66.4% | 66.9% (best) |
| Publisher-reported benchmarks | |||
| Aider PolyglotPublisher-reported result | 56.9percent correctReported resultJan 20, 2025 | Not published | 40percent correctReported resultMay 8, 2025 |
| Artificial Analysis Coding IndexPublisher-reported result | 15.9indexReported resultMar 11, 2026 | Not published | Not published |
| SciCodePublisher-reported result | 35.7percent correctReported resultMar 11, 2026 | Not published | Not published |
| Terminal-Bench HardPublisher-reported result | 6.1success rateReported resultMar 11, 2026 | Not published | Not published |
| Price per million tokens | |||
| Input | $1.02 | $0.571 (best) | $0.70 |
| Output | $5.14 | $2.29 (best) | $2.80 |
| Cached input | Not published | Not published | Not published |
| Blended (3:1) | $2.05 | $1 (best) | $1.23 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 12 providers | Median of 16 providers | Official Alibaba API |
| Limits | |||
| Context window | 128,000 tokens | 163,840 tokens (best) | 131,072 tokens |
| Max input | Not published | Not published | Not published |
| Max output | 32,768 tokens (best) | 32,768 tokens (best) | 16,384 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 | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Not published | Not published | Not published |
| File attachments | No | No | No |
| Temperature control | Yes | Yes | Yes |
| Reasoning control | always | always | budget |
| Availability | |||
| Weights | Open | OpenMIT | Open |
| API model ID | Not published | Not published | qwen3-32b |
| API providers | 13 | 16 | 19 (best) |
| Released | Jan 20, 2025 | May 28, 2025 | Apr 28, 2025 |
| Knowledge cutoff | Jul 2024 | Not published | Apr 2025 |
| Publisher documentation | Model weights | Model weights | Publisher documentation · Model weights |
| Source metadata updated | May 29, 2025 | May 28, 2025 | Apr 28, 2025 |
| Data sources | models.dev · Epoch AI | models.dev · Epoch AI | models.dev · Epoch AI |
| Catalog checked | Nov 22, 2026 | Nov 22, 2026 | Nov 22, 2026 |
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
DeepSeek R1 0528$10.28
Qwen3 32B$12.60
Which should you choose?
Which is better: DeepSeek-R1, DeepSeek R1 0528 or Qwen3 32B?
DeepSeek R1 0528 is the better all-round choice, scoring 59/100 against Qwen3 32B (55) and DeepSeek-R1 (53). It leads on capability, price and context window. The score weighs capability 59%, price 29%, context window 12%.It is close. Our weighted score puts them within 2 points (DeepSeek R1 0528 63/100, DeepSeek-R1 61/100, Qwen3 32B 60/100), so choose by what matters most for your work: DeepSeek R1 0528 for raw capability. The score weighs capability 83%, context window 17%.
Which is cheaper, DeepSeek-R1, DeepSeek R1 0528 or Qwen3 32B?
DeepSeek R1 0528 is cheaper at $0.571 input / $2.29 output per million tokens (median across 16 API providers). Qwen3 32B costs $0.70 input / $2.80 output per million tokens (official Alibaba API price); DeepSeek-R1 costs $1.02 input / $5.14 output per million tokens (median across 12 API providers). At a typical mix of three input tokens to one output token, that is $1 per million tokens for DeepSeek R1 0528 versus $1.23 for Qwen3 32B (1.2× as much) and $2.05 for DeepSeek-R1 (2.1× as much).
Which scores higher on benchmarks?
DeepSeek R1 0528 scores higher on the Capabilities Index (ECI): DeepSeek R1 0528 140.7 (#114 of 159), DeepSeek-R1 138.6 (#119 of 159) and Qwen3 32B 136.9 (#122 of 159). The confidence ranges of the top two overlap (138.9–142.4 vs 136.6–140.5), so treat the gap as small. On individual benchmarks: GPQA Diamond — DeepSeek R1 0528 76.3%, DeepSeek-R1 71.7%, Qwen3 32B 65.7%; OTIS Mock AIME 2024–2025 — Qwen3 32B 66.9%, DeepSeek R1 0528 66.4%, DeepSeek-R1 53.3%.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek-R1, DeepSeek R1 0528 and Qwen3 32B yet, so there is no like-for-like coding score. On overall capability, DeepSeek R1 0528 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?
DeepSeek R1 0528 has the largest context window at 163,840 tokens, against 131,072 for Qwen3 32B and 128,000 for DeepSeek-R1. Maximum output per response: DeepSeek-R1 up to 32,768, DeepSeek R1 0528 up to 32,768, Qwen3 32B up to 16,384 tokens.
Which can read images, PDFs, audio or video?
DeepSeek-R1 accepts text; DeepSeek R1 0528 accepts text; Qwen3 32B accepts text. They handle the same number of input types.
Are any of these open source?
Yes, all three publish their weights (MIT), so you can self-host them.
Which is newer?
DeepSeek R1 0528 is the newest, released May 28, 2025. Qwen3 32B came out Apr 28, 2025; DeepSeek-R1 came out Jan 20, 2025. Knowledge cutoff: DeepSeek-R1 Jul 2024, Qwen3 32B Apr 2025.
How do you decide the winner?
This rating uses capability (59%, independent benchmark results); price (29%, blended price per million tokens (3 input : 1 output), log scale); context window (12%, 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 22, 2026.This rating uses capability (83%, independent benchmark results); context window (17%, 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 22, 2026.