Compare / head-to-head
Dola Seed 2.0 Minivs
Gemini 3.5 Flash
Gemini 3.5 Flash leads 5 of 5 shared benchmarks. Dola Seed 2.0 Mini is 21x cheaper per token. Gemini 3.5 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
0 – 5
Gemini 3.5 Flash leads
Cheaper per token
Dola Seed 2.0 Mini
21x cheaper, input + output
Larger context
Gemini 3.5 Flash
1.0M tokens
Providers
2 providers
ByteDance Seed · Google
Dola Seed 2.0 Mini
ByteDance Seed · released 2026-02-14
textvisionaudiovideo
Gemini 3.5 Flash
Google · released 2026-05-19
textvisionaudio
Quality
Benchmark matrix
5 shared · 10 only Dola Seed 2.0 Mini · 31 only Gemini 3.5 Flash| Benchmark | Dola Seed 2.0 Mini | Gemini 3.5 Flash | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 5 | ||||
| GPQA Diamond | 79% ↗ | 92.8% ↗epoch run | -13.8 pt | Gemini 3.5 Flash |
| AIME 2026 | 86.7% ↗ | 95% ↗matharena ⚠ | -8.3 pt | Gemini 3.5 Flash |
| ARC-AGI-2 | 2.3% ↗ | 72.1% ↗ | -69.8 pt | Gemini 3.5 Flash |
| MMMU-Pro | 71.4% ↗ | 83.6% ↗ | -12.2 pt | Gemini 3.5 Flash |
| SimpleQA Verified | 18.9% ↗ | 66.2% ↗epoch run | -47.3 pt | Gemini 3.5 Flash |
| Only Dola Seed 2.0 Mini reports · 10 | ||||
| MMLU-Pro | 83.6% ↗ | not reported | — | — |
| AIME 2025 | 87% ↗ | not reported | — | — |
| HLE (no tool, text only) | 13.3% ↗ | not reported | — | — |
| IMOAnswerBench (no tool) | 71.6% ↗ | not reported | — | — |
| LiveCodeBench (v6) | 64.1% ↗ | not reported | — | — |
| LongBench v2 (128K) | 52.3% ↗ | not reported | — | — |
| MathVista | 85.5% ↗ | not reported | — | — |
| MMMU | 79.7% ↗ | not reported | — | — |
| MultiChallenge | 61.1% ↗ | not reported | — | — |
| SuperGPQA | 61.6% ↗ | not reported | — | — |
| Only Gemini 3.5 Flash reports · 31 | ||||
| LMArena Elo | not reported | 1477.4 ↗ | — | — |
| APEX-Agents (Mercor) | not reported | 27.5% ↗ | — | — |
| Chess Puzzles (Epoch AI run) | not reported | 50% ↗epoch run | — | — |
| DeepSWE v1.1 (Datacurve) | not reported | 36.1% ↗ | — | — |
| EBR-bench (Epoch AI run) | not reported | 4.8% ↗epoch run | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | not reported | 26.8% ↗epoch run | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | not reported | 62.8% ↗epoch run | — | — |
| GDPVal-AA | not reported | 1656 ↗ | — | — |
| Humanity's Last Exam (full set, text + MM) | not reported | 40.2% ↗ | — | — |
| LiveBench Agentic Coding (LiveBench) | not reported | 49% ↗ | — | — |
| LiveBench Coding (LiveBench) | not reported | 78.2% ↗ | — | — |
| LiveBench Data Analysis (LiveBench) | not reported | 64.9% ↗ | — | — |
| LiveBench Instruction Following (LiveBench) | not reported | 75.6% ↗ | — | — |
| LiveBench Language (LiveBench) | not reported | 84.6% ↗ | — | — |
| LiveBench Mathematics (LiveBench) | not reported | 88.2% ↗ | — | — |
| LiveBench Reasoning (LiveBench) | not reported | 82% ↗ | — | — |
| LMArena Vision (LMArena) | not reported | 1284.4 ↗ | — | — |
| LMArena WebDev (LMArena) | not reported | 1499 ↗ | — | — |
| MCP Atlas | not reported | 83.6% ↗ | — | — |
| Mystery Game Puzzles (Epoch AI run) | not reported | 32% ↗epoch run | — | — |
| OSWorld-Verified | not reported | 78.4% ↗ | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | not reported | 95.6% ↗epoch run | — | — |
| SAGE (Vals AI) | not reported | 49.9% ↗ | — | — |
| SimpleBench (SimpleBench) | not reported | 76.7% ↗ | — | — |
| SWE-Bench Pro (Public) | not reported | 55.1% ↗ | — | — |
| SWE-bench Verified (Epoch AI run) | not reported | 79.3% ↗epoch run | — | — |
| Terminal-bench 2.1 | not reported | 76.2% ↗ | — | — |
| Terminal-Bench 4.0 (Vals AI) | not reported | 6.1% ↗ | — | — |
| Toolathlon-Verified (HKUST) | not reported | 67.3% ↗ | — | — |
| Vending-Bench 2 (Andon Labs) | not reported | 5396.42 ↗ | — | — |
| WeirdML (Håvard Tveit Ihle) | not reported | 62.6% ↗ | — | — |
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 Mini minus Gemini 3.5 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 Mini | Gemini 3.5 Flash | Edge |
|---|---|---|---|
| Context window | 256K tokens | 1.0M tokens | Gemini 3.5 Flash |
| Max output | 128K tokens | 66K tokens | Dola Seed 2.0 Mini |
| Input price / 1M | $0.1 ↗ | $1.5 ↗ | Dola Seed 2.0 Mini |
| Output price / 1M | $0.4 ↗ | $9 ↗ | Dola Seed 2.0 Mini |
| Cached input / 1M | $0.02 ↗ | $0.15 ↗ | Dola Seed 2.0 Mini |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $0.5 | $10.5 | Dola Seed 2.0 Mini |
| Modalities | text · vision · audio · video | text · vision · audio | Dola Seed 2.0 Mini |
| Released | 2026-02-14 | 2026-05-19 | — |
| Cited benchmark scores | 15 | 42 | — |
Reliability
Provider status
Live from /statusMore matchups
Dola Seed 2.0 Mini vs …
Models sharing the most benchmarksMore matchups
Gemini 3.5 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 Mini and Gemini 3.5 Flash on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.