Qwen3 32B vs GPT-4.1 vs DeepSeek R1 0528
DeepSeek R1 0528 comes out ahead, 59 to 55 and 52 on our weighted score, and it is the cheaper option too.Too close to call on our weighted score (GPT-4.1 65, DeepSeek R1 0528 63, Qwen3 32B 60). The right pick depends on what you value most.
Alibaba (Qwen)
Qwen3 32B
55/100- ECI136.9
- Price$0.70 / $2.80
- Context131K
OpenAI
GPT-4.1
52/100- ECI136.1
- Price$2.00 / $8.00
- Context1.05M
- Our pick
DeepSeek
DeepSeek R1 0528
59/100- ECI140.7
- Price$0.571 / $2.29
- Context164K
Alibaba (Qwen)
Qwen3 32B
60/100- ECI136.9
- Price$0.70 / $2.80
- Context131K
OpenAI
GPT-4.1
65/100- ECI136.1
- Price$2.00 / $8.00
- Context1.05M
DeepSeek
DeepSeek R1 0528
63/100- ECI140.7
- Price$0.571 / $2.29
- Context164K
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 GPT-4.1 (52). It leads on capability and price. GPT-4.1 wins on context window. The score weighs capability 59%, price 29%, context window 12%.It is close. Our weighted score puts them within 1 points (GPT-4.1 65/100, DeepSeek R1 0528 63/100, Qwen3 32B 60/100), so choose by what matters most for your work: DeepSeek R1 0528 for raw capability and GPT-4.1 for long inputs. The score weighs capability 83%, context window 17%.
- CapabilityDeepSeek R1 0528Capabilities Index (ECI): DeepSeek R1 0528 140.7 · Qwen3 32B 136.9 · GPT-4.1 136.1
- Lowest priceDeepSeek R1 0528DeepSeek R1 0528 $1 · Qwen3 32B $1.23 · GPT-4.1 $3.50 per 1M tokens (3:1 blend)
- Longest contextGPT-4.1GPT-4.1 1,047,576 · DeepSeek R1 0528 163,840 · Qwen3 32B 131,072 tokens
- Widest inputsGPT-4.1Qwen3 32B: Text · GPT-4.1: Text, Images, PDFs · DeepSeek R1 0528: Text
- Self-hostingQwen3 32B and DeepSeek R1 0528Publishes downloadable weights (MIT)
| Measure | Weight | Qwen3 32B | GPT-4.1 | DeepSeek R1 0528 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 59% | 65 | 65 | 69 |
| Price | 29% | 44 | 23 | 48 |
| Context window | 12% | 32 | 65 | 36 |
| Overall | 100% | 55/100 | 52/100 | 59/100 |
Left out because at least one model lacks the data: inputs & features. The remaining weights were rescaled.
| Measure | Weight | Qwen3 32B | GPT-4.1 | DeepSeek R1 0528 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 83% | 65 | 65 | 69 |
| Context window | 17% | 32 | 65 | 36 |
| Overall | 100% | 60/100 | 65/100 | 63/100 |
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) | 136.9 | 136.1 | 140.7 (best) |
| ECI rank | #122 of 159 | #124 of 159 | #114 of 159 (best) |
| ECI confidence interval | 134.4–139.1 | 134.2–138.0 | 138.9–142.4 |
| ECI evaluation date | Apr 29, 2025 | Apr 14, 2025 | May 28, 2025 |
| Documented capabilities | Dense open Qwen model for self-hosted chat, reasoning, and coding | Long-lived GPT workhorse for coding, instruction following, and production apps | May 2025 DeepSeek R1 update with improved mathematics, coding, and reasoning |
| Model parameters | Not published | Not published | Not published |
| Output modalities | Text | Text | Text |
| GPQA DiamondGraduate-level science questions | 65.7% | 66.9% | 76.3% (best) |
| FrontierMath Tiers 1–3Research-level mathematics | Not published | 6.0% | Not published |
| OTIS Mock AIME 2024–2025Competition mathematics | 66.9% (best) | 38.3% | 66.4% |
| SWE-bench VerifiedFixing real GitHub issues | Not published | 48.5% | Not published |
| SimpleQA VerifiedShort factual questions | Not published | 31.1% | Not published |
| Publisher-reported benchmarks | |||
| Aider PolyglotPublisher-reported result | 40percent correctReported resultMay 8, 2025 | 52.4percent correctReported resultApr 14, 2025 | Not published |
| Price per million tokens | |||
| Input | $0.70 | $2.00 | $0.571 (best) |
| Output | $2.80 | $8.00 | $2.29 (best) |
| Cached input | Not published | $0.50 | Not published |
| Blended (3:1) | $1.23 | $3.50 | $1 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Alibaba API | Official OpenAI API | Median of 16 providers |
| Limits | |||
| Context window | 131,072 tokens | 1,047,576 tokens (best) | 163,840 tokens |
| Max input | Not published | Not published | Not published |
| Max output | 16,384 tokens | 32,768 tokens (best) | 32,768 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | Yes | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Not published | Yes | Not published |
| File attachments | No | Yes | No |
| Temperature control | Yes | Yes | Yes |
| Reasoning control | budget | Not published | always |
| Availability | |||
| Weights | Open | Proprietary | OpenMIT |
| API model ID | qwen3-32b | gpt-4.1 | Not published |
| API providers | 19 | 32 (best) | 16 |
| Released | Apr 28, 2025 | Apr 14, 2025 | May 28, 2025 |
| Knowledge cutoff | Apr 2025 | Apr 2024 | Not published |
| Publisher documentation | Publisher documentation · Model weights | Publisher documentation | Model weights |
| Source metadata updated | Apr 28, 2025 | Apr 14, 2025 | May 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.
Qwen3 32B$12.60
GPT-4.1$36.00
DeepSeek R1 0528$10.28
Which should you choose?
Which is better: Qwen3 32B, GPT-4.1 or DeepSeek R1 0528?
DeepSeek R1 0528 is the better all-round choice, scoring 59/100 against Qwen3 32B (55) and GPT-4.1 (52). It leads on capability and price. GPT-4.1 wins on context window. The score weighs capability 59%, price 29%, context window 12%.It is close. Our weighted score puts them within 1 points (GPT-4.1 65/100, DeepSeek R1 0528 63/100, Qwen3 32B 60/100), so choose by what matters most for your work: DeepSeek R1 0528 for raw capability and GPT-4.1 for long inputs. The score weighs capability 83%, context window 17%.
Which is cheaper, Qwen3 32B, GPT-4.1 or DeepSeek R1 0528?
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); GPT-4.1 costs $2.00 input / $8.00 output per million tokens (official OpenAI API price). 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 $3.50 for GPT-4.1 (3.5× 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), Qwen3 32B 136.9 (#122 of 159) and GPT-4.1 136.1 (#124 of 159). The confidence ranges of the top two overlap (138.9–142.4 vs 134.4–139.1), so treat the gap as small. On individual benchmarks: GPQA Diamond — DeepSeek R1 0528 76.3%, GPT-4.1 66.9%, Qwen3 32B 65.7%; OTIS Mock AIME 2024–2025 — Qwen3 32B 66.9%, DeepSeek R1 0528 66.4%, GPT-4.1 38.3%.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen3 32B and DeepSeek R1 0528 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?
GPT-4.1 has the largest context window at 1,047,576 tokens, against 163,840 for DeepSeek R1 0528 and 131,072 for Qwen3 32B. Maximum output per response: Qwen3 32B up to 16,384, GPT-4.1 up to 32,768, DeepSeek R1 0528 up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Qwen3 32B accepts text; GPT-4.1 accepts text, images and PDFs; DeepSeek R1 0528 accepts text. GPT-4.1 handles the widest range of inputs.
Are any of these open source?
Qwen3 32B and DeepSeek R1 0528 publishes its weights (MIT) and can be self-hosted; GPT-4.1 is proprietary.
Which is newer?
DeepSeek R1 0528 is the newest, released May 28, 2025. Qwen3 32B came out Apr 28, 2025; GPT-4.1 came out Apr 14, 2025. Knowledge cutoff: Qwen3 32B Apr 2025, GPT-4.1 Apr 2024.
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.