DeepSeek R1 0528 vs Grok 4.20 (Reasoning) vs Seed 2.1 Pro
Too close to call on our weighted score (Seed 2.1 Pro 86, Grok 4.20 (Reasoning) 85, DeepSeek R1 0528 59). The right pick depends on what you value most.
Price in rating: Excluded · Include price
DeepSeek
DeepSeek R1 0528
59/100- ECI140.8
- Price$0.512 / $2.19
- Context164K
xAI
Grok 4.20 (Reasoning)
85/100- ECI152.3
- Price$1.25 / $2.50
- Context1M
ByteDance Seed
Seed 2.1 Pro
86/100- ECI—
- Price$0.891 / $4.45
- Context1.02M
Too close to call
It is close. Our weighted score puts them within 1 points (Seed 2.1 Pro 86/100, Grok 4.20 (Reasoning) 85/100, DeepSeek R1 0528 59/100), so choose by what matters most for your work: Seed 2.1 Pro for raw capability and DeepSeek R1 0528 on price. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Seed 2.1 Pro has no Capabilities Index score yet.
- CapabilitySeed 2.1 ProShared benchmarks: Seed 2.1 Pro 92.4% · Grok 4.20 (Reasoning) 90.8% · DeepSeek R1 0528 71.4%
- Lowest priceDeepSeek R1 0528DeepSeek R1 0528 $0.932 · Grok 4.20 (Reasoning) $1.56 · Seed 2.1 Pro $1.78 per 1M tokens (3:1 blend)
- Longest contextSeed 2.1 ProSeed 2.1 Pro 1,024,000 · Grok 4.20 (Reasoning) 1,000,000 · DeepSeek R1 0528 163,840 tokens
- Widest inputsGrok 4.20 (Reasoning) and Seed 2.1 ProDeepSeek R1 0528: Text · Grok 4.20 (Reasoning): Text, Images, PDFs · Seed 2.1 Pro: Text, Images, Video
- Self-hostingDeepSeek R1 0528Publishes downloadable weights (MIT)
| Measure | Weight | DeepSeek R1 0528 | Grok 4.20 (Reasoning) | Seed 2.1 Pro |
|---|---|---|---|---|
| CapabilityShared benchmarks | 67% | 71 | 91 | 92 |
| Inputs & features | 20% | 35 | 80 | 80 |
| Context window | 13% | 36 | 64 | 65 |
| Overall | 100% | 59/100 | 85/100 | 86/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 140.8 | 152.3 (best) | — |
| ECI rank | #113 of 158 | #59 of 158 (best) | — |
| GPQA DiamondGraduate-level science questions | 76.3% | 89.3% (best) | 89.3% (best) |
| FrontierMath Tiers 1–3Research-level mathematics | — | 44.9% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 66.4% | 92.2% | 95.6% (best) |
| SimpleQA VerifiedShort factual questions | — | 30.2% | 44.7% (best) |
| Price per million tokens | |||
| Input | $0.512 (best) | $1.25 | $0.891 |
| Output | $2.19 (best) | $2.50 | $4.45 |
| Cached input | — | $0.20 | $0.178 (best) |
| Blended (3:1) | $0.932 (best) | $1.56 | $1.78 |
| Long-context rate | Same rate | Over 200K: $2.50 / $5.00 | Same rate |
| Price source | Median of 16 providers | Official xAI API | Official Volcengine Ark API |
| Limits | |||
| Context window | 163,840 tokens | 1,000,000 tokens | 1,024,000 tokens (best) |
| Max output | 32,768 tokens | 30,000 tokens | 256,000 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | Yes | No |
| Audio | No | No | No |
| Video | No | No | Yes |
| Reasoning | Yes | Yes | Yesminimal · low · medium · high · xhigh · max |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | Yes |
| Availability | |||
| Weights | OpenMIT | Proprietary | Proprietary |
| API model ID | — | grok-4.20-0309-reasoning | doubao-seed-2-1-pro-260628 |
| API providers | 16 (best) | 14 | 3 |
| Released | May 28, 2025 | Mar 9, 2026 | Jun 23, 2026 |
| Knowledge cutoff | — | — | — |
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 0528$9.50
Grok 4.20 (Reasoning)$17.50
Seed 2.1 Pro$17.81
Which should you choose?
Which is better: DeepSeek R1 0528, Grok 4.20 (Reasoning) or Seed 2.1 Pro?
It is close. Our weighted score puts them within 1 points (Seed 2.1 Pro 86/100, Grok 4.20 (Reasoning) 85/100, DeepSeek R1 0528 59/100), so choose by what matters most for your work: Seed 2.1 Pro for raw capability and DeepSeek R1 0528 on price. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Seed 2.1 Pro has no Capabilities Index score yet.
Which is cheaper, DeepSeek R1 0528, Grok 4.20 (Reasoning) or Seed 2.1 Pro?
DeepSeek R1 0528 is cheaper at $0.512 input / $2.19 output per million tokens (median across 16 API providers). Grok 4.20 (Reasoning) costs $1.25 input / $2.50 output per million tokens (official xAI API price); Seed 2.1 Pro costs $0.891 input / $4.45 output per million tokens (official Volcengine Ark API price). At a typical mix of three input tokens to one output token, that is $0.932 per million tokens for DeepSeek R1 0528 versus $1.56 for Grok 4.20 (Reasoning) (1.7× as much) and $1.78 for Seed 2.1 Pro (1.9× as much).
Which scores higher on benchmarks?
Not every model here has a Capabilities Index score, so we compare the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025): Seed 2.1 Pro 92.4%, Grok 4.20 (Reasoning) 90.8% and DeepSeek R1 0528 71.4%. On individual benchmarks: GPQA Diamond — Grok 4.20 (Reasoning) 89.3%, Seed 2.1 Pro 89.3%, DeepSeek R1 0528 76.3%; OTIS Mock AIME 2024–2025 — Seed 2.1 Pro 95.6%, Grok 4.20 (Reasoning) 92.2%, DeepSeek R1 0528 66.4%.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek R1 0528, Grok 4.20 (Reasoning) and Seed 2.1 Pro yet, so there is no like-for-like coding score. On overall capability, Seed 2.1 Pro 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?
Seed 2.1 Pro has the largest context window at 1,024,000 tokens, against 1,000,000 for Grok 4.20 (Reasoning) and 163,840 for DeepSeek R1 0528. Maximum output per response: DeepSeek R1 0528 up to 32,768, Grok 4.20 (Reasoning) up to 30,000, Seed 2.1 Pro up to 256,000 tokens.
Which can read images, PDFs, audio or video?
DeepSeek R1 0528 accepts text; Grok 4.20 (Reasoning) accepts text, images and PDFs; Seed 2.1 Pro accepts text, images and video. Grok 4.20 (Reasoning) handles the widest range of inputs.
Are any of these open source?
DeepSeek R1 0528 publishes its weights (MIT) and can be self-hosted; Grok 4.20 (Reasoning) and Seed 2.1 Pro is proprietary.
Which is newer?
Seed 2.1 Pro is the newest, released Jun 23, 2026. Grok 4.20 (Reasoning) came out Mar 9, 2026; DeepSeek R1 0528 came out May 28, 2025.
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.