Compare / head-to-head
Dola Seed 2.0 ProvsGemini 3.8 Flash
Dola Seed 2.0 Pro and Gemini 3.8 Flash split their 2 shared benchmarks evenly. Dola Seed 2.0 Pro is 1.3x cheaper per token. Gemini 3.8 Flash has the larger context window (1.0M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
1 – 1
even split
Cheaper per token
Dola Seed 2.0 Pro
1.3x cheaper, input + output
Larger context
Gemini 3.8 Flash
1.0M tokens
Provider uptime (30d)
— · 100%
ByteDance Seed · Google
Dola Seed 2.0 Pro
ByteDance Seed · released 2026-02-16
textvisionvideo
Gemini 3.8 Flash
Google · released 2026-09-02
textvisionaudio
Quality
Benchmark matrix
2 shared · 12 only Dola Seed 2.0 Pro · 13 only Gemini 3.8 Flash| Benchmark | Dola Seed 2.0 Pro | Gemini 3.8 Flash | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 2 | ||||
| GPQA Diamond | 92.4% ↗ | 95.3% ↗ | -2.9 pt | Gemini 3.8 Flash |
| HLE-Verified | 73.6% ↗ | 54.9% ↗ | +18.7 pt | Dola Seed 2.0 Pro |
| Only Dola Seed 2.0 Pro reports · 12 | ||||
| SWE-bench Verified | 76.5% ↗ | not reported | — | — |
| MMLU-Pro | 90.1% ↗ | not reported | — | — |
| AIME 2025 | 99% ↗ | not reported | — | — |
| Humanity's Last Exam (no tools) | 33.3% ↗ | not reported | — | — |
| LMArena Elo | 1447.6 ↗ | not reported | — | — |
| BFCL v4 | 73.4% ↗ | not reported | — | — |
| BrowseComp | 77.3% ↗ | not reported | — | — |
| DeepResearchBench | 53.3% ↗ | not reported | — | — |
| SciCode | 48.5% ↗ | not reported | — | — |
| SWE-bench Multilingual | 71.7% ↗ | not reported | — | — |
| SWE-bench Pro | 46.9% ↗ | not reported | — | — |
| Terminal-Bench 2.0 | 55.8% ↗ | not reported | — | — |
| Only Gemini 3.8 Flash reports · 13 | ||||
| CharXiv Reasoning (no tools) | not reported | 86.2% ↗ | — | — |
| DeepSWE v1.1 | not reported | 73.7% ↗ | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | not reported | 22% ↗epoch | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | not reported | 68.4% ↗epoch | — | — |
| GDPVal-AA v2 | not reported | 1545 ↗ | — | — |
| Harvey's Legal Agent Benchmark | not reported | 10% ↗ | — | — |
| LABBench2 | not reported | 86.2% ↗ | — | — |
| OSWorld-2.0 | not reported | 59% ↗ | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | not reported | 98.9% ↗epoch | — | — |
| SimpleQA Verified | not reported | 69.7% ↗epoch | — | — |
| Terminal-bench 2.1 | not reported | 89.4% ↗ | — | — |
| Terminal-bench 4.0 | not reported | 19.1% ↗ | — | — |
| Vals Finance Agent v2 | not reported | 61.4% ↗ | — | — |
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 Dola Seed 2.0 Pro minus Gemini 3.8 Flash 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 | Dola Seed 2.0 Pro | Gemini 3.8 Flash | Edge |
|---|---|---|---|
| Context window | 256K tokens | 1.0M tokens | Gemini 3.8 Flash |
| Max output | — | 66K tokens | — |
| Input price / 1M | $0.5 ↗ | $0.75 ↗ | Dola Seed 2.0 Pro |
| Output price / 1M | $3 ↗ | $3.75 ↗ | Dola Seed 2.0 Pro |
| Cached input / 1M | — | $0.075 ↗ | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $3.5 | $4.5 | Dola Seed 2.0 Pro |
| Modalities | text · vision · video | text · vision · audio | Tie |
| Released | 2026-02-16 | 2026-09-02 | — |
| Cited benchmark scores | 14 | 16 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Dola Seed 2.0 Pro vs …
Models sharing the most benchmarksMore matchups
Gemini 3.8 Flash vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Dola Seed 2.0 Pro and Gemini 3.8 Flash on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.