Compare / head-to-head
DeepSeek V3vs
Gemini 3 Flash Preview
Gemini 3 Flash Preview leads 7 of 7 shared benchmarks. Gemini 3 Flash Preview 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 – 7
Gemini 3 Flash Preview leads
Cheaper per token
—
list price, input + output
Larger context
Gemini 3 Flash Preview
1.0M tokens
Providers
2 providers
DeepSeek · Google
DeepSeek V3
DeepSeek · released 2024-12-26
text
- Context
- 128K
- Max out
- 8K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 14 · 7 core
Gemini 3 Flash Preview
Google · released 2025-12-17
textvisionaudio
- Context
- 1.0M
- Max out
- 66K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 34 · 12 core
Quality
Benchmark matrix
7 shared · 3 only DeepSeek V3 · 19 only Gemini 3 Flash Preview| Benchmark | DeepSeek V3 | Gemini 3 Flash Preview | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 7 | ||||
| SWE-bench Verified | 42% ↗ | 78% ↗ | -36 pt | Gemini 3 Flash Preview |
| GPQA Diamond | 59.1% ↗ | 90.4% ↗ | -31.3 pt | Gemini 3 Flash Preview |
| AIME 2025 | 25% ↗matharena | 95.2% ↗ | -70.2 pt | Gemini 3 Flash Preview |
| LMArena Elo | 1332.4 ↗ | 1472.7 ↗ | -140.3 | Gemini 3 Flash Preview |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 15.8% ↗epoch run | 95.6% ↗epoch run | -79.8 pt | Gemini 3 Flash Preview |
| SimpleBench (SimpleBench) | 18.9% ↗ | 61.1% ↗ | -42.2 pt | Gemini 3 Flash Preview |
| WeirdML (Håvard Tveit Ihle) | 36.1% ↗ | 61.6% ↗ | -25.5 pt | Gemini 3 Flash Preview |
| Only DeepSeek V3 reports · 3 | ||||
| MMLU | 88.5% ↗ | not reported | — | — |
| MMLU-Pro | 75.9% ↗ | not reported | — | — |
| MATH Level 5 (Epoch AI run) | 75.5% ↗epoch run | not reported | — | — |
| Only Gemini 3 Flash Preview reports · 19 | ||||
| Humanity's Last Exam (no tools) | not reported | 33.7% ↗ | — | — |
| BALROG (BALROG) | not reported | 48.1% ↗ | — | — |
| Chess Puzzles (Epoch AI run) | not reported | 40% ↗epoch run | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | not reported | 17.1% ↗epoch run | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | not reported | 51.2% ↗epoch run | — | — |
| GSO Opt@1 (GSO) | not reported | 7.8% ↗ | — | — |
| LMArena Vision (LMArena) | not reported | 1272.9 ↗ | — | — |
| LMArena WebDev (LMArena) | not reported | 1438.9 ↗ | — | — |
| MMMU-Pro | not reported | 81.2% ↗ | — | — |
| Mystery Game Puzzles (Epoch AI run) | not reported | 26% ↗epoch run | — | — |
| SAGE (Vals AI) | not reported | 51.8% ↗ | — | — |
| SimpleQA Verified | not reported | 68.7% ↗ | — | — |
| SWE-bench Verified (Epoch AI run) | not reported | 75.4% ↗epoch run | — | — |
| tau2-bench Airline (Sierra) | not reported | 82.5% ↗ | — | — |
| tau2-bench Banking Knowledge (Sierra) | not reported | 27.3% ↗ | — | — |
| tau2-bench Retail (Sierra) | not reported | 76.8% ↗ | — | — |
| tau2-bench Telecom (Sierra) | not reported | 91.2% ↗ | — | — |
| Terminal-Bench 2.0 | not reported | 47.6% ↗ | — | — |
| Vending-Bench 2 (Andon Labs) | not reported | 3634.72 ↗ | — | — |
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 minus Gemini 3 Flash Preview 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 | Gemini 3 Flash Preview | Edge |
|---|---|---|---|
| Context window | 128K tokens | 1.0M tokens | Gemini 3 Flash Preview |
| Max output | 8K tokens | 66K tokens | Gemini 3 Flash Preview |
| Input price / 1M | — | — | — |
| Output price / 1M | — | — | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | — | — |
| Modalities | text | text · vision · audio | Gemini 3 Flash Preview |
| Released | 2024-12-26 | 2025-12-17 | — |
| Cited benchmark scores | 14 | 34 | — |
Reliability
Provider status
Live from /statusMore matchups
DeepSeek V3 vs …
Models sharing the most benchmarksMore matchups
Gemini 3 Flash Preview vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run DeepSeek V3 and Gemini 3 Flash Preview on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.