Compare / head-to-head
DeepSeek V3.1-Terminusvs
Dola Seed 2.0 Pro
Dola Seed 2.0 Pro leads 5 of 5 shared benchmarks. Dola Seed 2.0 Pro has the larger context window (256K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 5
Dola Seed 2.0 Pro leads
Cheaper per token
—
list price, input + output
Larger context
Dola Seed 2.0 Pro
256K tokens
Providers
2 providers
DeepSeek · ByteDance Seed
DeepSeek V3.1-Terminus
DeepSeek · released 2025-09-22
text
- Context
- 128K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 12 · 5 core
Dola Seed 2.0 Pro
ByteDance Seed · released 2026-02-16
textvisionvideo
Quality
Benchmark matrix
5 shared · 7 only DeepSeek V3.1-Terminus · 10 only Dola Seed 2.0 Pro| Benchmark | DeepSeek V3.1-Terminus | Dola Seed 2.0 Pro | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 5 | ||||
| MMLU-Pro | 85% ↗ | 90.1% ↗ | -5.1 pt | Dola Seed 2.0 Pro |
| Humanity's Last Exam (no tools) | 21.7% ↗ | 33.3% ↗ | -11.6 pt | Dola Seed 2.0 Pro |
| LMArena Elo | 1417.2 ↗ | 1447.6 ↗ | -30.4 | Dola Seed 2.0 Pro |
| BrowseComp | 38.5% ↗ | 77.3% ↗ | -38.8 pt | Dola Seed 2.0 Pro |
| SWE-bench Multilingual | 57.8% ↗ | 71.7% ↗ | -13.9 pt | Dola Seed 2.0 Pro |
| Only DeepSeek V3.1-Terminus reports · 7 | ||||
| Aider-Polyglot | 76.1% ↗ | not reported | — | — |
| BrowseComp-zh | 45% ↗ | not reported | — | — |
| GPQA-Diamond | 80.7% ↗ | not reported | — | — |
| LiveCodeBench | 74.9% ↗ | not reported | — | — |
| SimpleQA (agentic tool use) | 96.8% ↗ | not reported | — | — |
| SWE Verified | 68.4% ↗ | not reported | — | — |
| Terminal-bench | 36.7% ↗ | not reported | — | — |
| Only Dola Seed 2.0 Pro reports · 10 | ||||
| SWE-bench Verified | not reported | 76.5% ↗ | — | — |
| GPQA Diamond | not reported | 92.4% ↗ | — | — |
| AIME 2025 | not reported | 99% ↗ | — | — |
| BFCL v4 | not reported | 73.4% ↗ | — | — |
| DeepResearchBench | not reported | 53.3% ↗ | — | — |
| HLE-Verified | not reported | 73.6% ↗ | — | — |
| LMArena Vision (LMArena) | not reported | 1256.6 ↗ | — | — |
| SciCode | not reported | 48.5% ↗ | — | — |
| SWE-bench Pro | not reported | 46.9% ↗ | — | — |
| Terminal-Bench 2.0 | not reported | 55.8% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is DeepSeek V3.1-Terminus minus Dola Seed 2.0 Pro in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | DeepSeek V3.1-Terminus | Dola Seed 2.0 Pro | Edge |
|---|---|---|---|
| Context window | 128K tokens | 256K tokens | Dola Seed 2.0 Pro |
| Max output | — | — | — |
| Input price / 1M | — | $0.5 ↗ | — |
| Output price / 1M | — | $3 ↗ | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | $3.5 | — |
| Modalities | text | text · vision · video | Dola Seed 2.0 Pro |
| Released | 2025-09-22 | 2026-02-16 | — |
| Cited benchmark scores | 12 | 16 | — |
Reliability
Provider status
Live from /statusMore matchups
DeepSeek V3.1-Terminus vs …
Models sharing the most benchmarksMore matchups
Dola Seed 2.0 Pro vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run DeepSeek V3.1-Terminus and Dola Seed 2.0 Pro on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.