Compare / head-to-head
DeepSeek V4 Flashvs
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads 13 of 21 shared benchmarks. Gemini 3.1 Pro 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
7 – 13
Gemini 3.1 Pro Preview leads · 1 tied
Cheaper per token
—
list price, input + output
Larger context
Gemini 3.1 Pro Preview
1.0M tokens
Providers
2 providers
DeepSeek · Google
DeepSeek V4 Flash
DeepSeek · released 2026-07-31
text
- Context
- 1M
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 28 · 7 core
Gemini 3.1 Pro Preview
Google · released 2026-02-19
textvisionaudio
Quality
Benchmark matrix
21 shared · 7 only DeepSeek V4 Flash · 15 only Gemini 3.1 Pro Preview| Benchmark | DeepSeek V4 Flash | Gemini 3.1 Pro Preview | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 21 | ||||
| GPQA Diamond | 91% ↗epoch run | 94.3% ↗ | -3.3 pt | Gemini 3.1 Pro Preview |
| LMArena Elo | 1436 ↗ | 1480.1 ↗ | -44.1 | Gemini 3.1 Pro Preview |
| Chess Puzzles (Epoch AI run) | 33% ↗epoch run | 55% ↗epoch run | -22 pt | Gemini 3.1 Pro Preview |
| DeepSWE v1.1 (Datacurve) | 53.3% ↗ | 11.7% ↗ | +41.6 pt | DeepSeek V4 Flash |
| FrontierMath Tier 4 v2 (Epoch AI run) | 24.4% ↗epoch run | 26.8% ↗epoch run | -2.4 pt | Gemini 3.1 Pro Preview |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 57.5% ↗epoch run | 59.6% ↗epoch run | -2.1 pt | Gemini 3.1 Pro Preview |
| LiveBench Agentic Coding (LiveBench) | 46.8% ↗ | 44.1% ↗ | +2.7 pt | DeepSeek V4 Flash |
| LiveBench Coding (LiveBench) | 75% ↗ | 76.5% ↗ | -1.5 pt | Gemini 3.1 Pro Preview |
| LiveBench Data Analysis (LiveBench) | 79.3% ↗ | 78.5% ↗ | +0.8 pt | DeepSeek V4 Flash |
| LiveBench Instruction Following (LiveBench) | 65.5% ↗ | 79.1% ↗ | -13.6 pt | Gemini 3.1 Pro Preview |
| LiveBench Language (LiveBench) | 79.2% ↗ | 85.4% ↗ | -6.2 pt | Gemini 3.1 Pro Preview |
| LiveBench Mathematics (LiveBench) | 86.8% ↗ | 91% ↗ | -4.2 pt | Gemini 3.1 Pro Preview |
| LiveBench Reasoning (LiveBench) | 86.6% ↗ | 84% ↗ | +2.6 pt | DeepSeek V4 Flash |
| LMArena WebDev (LMArena) | 1581 ↗ | 1446.2 ↗ | +134.8 | DeepSeek V4 Flash |
| Mystery Game Puzzles (Epoch AI run) | 34% ↗epoch run | 34% ↗epoch run | 0 | Tie |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 94.4% ↗epoch run | 95.6% ↗epoch run | -1.2 pt | Gemini 3.1 Pro Preview |
| SimpleBench (SimpleBench) | 61.1% ↗ | 79.6% ↗ | -18.5 pt | Gemini 3.1 Pro Preview |
| SimpleQA Verified | 33.6% ↗epoch run | 73.5% ↗epoch run | -39.9 pt | Gemini 3.1 Pro Preview |
| Terminal-Bench 4.0 (Vals AI) | 18.7% ↗ | 2.5% ↗ | +16.2 pt | DeepSeek V4 Flash |
| Toolathlon-Verified (HKUST) | 70.7% ↗ | 61.1% ↗ | +9.6 pt | DeepSeek V4 Flash |
| WeirdML (Håvard Tveit Ihle) | 63% ↗ | 72.1% ↗ | -9.1 pt | Gemini 3.1 Pro Preview |
| Only DeepSeek V4 Flash reports · 7 | ||||
| Agents' Last Exam | 25.2% ↗ | not reported | — | — |
| AutomationBench Public | 25.1% ↗ | not reported | — | — |
| Cybergym | 76.7% ↗ | not reported | — | — |
| DeepSWE | 54.4% ↗ | not reported | — | — |
| NL2Repo | 54.2% ↗ | not reported | — | — |
| Terminal Bench 2.1 | 82.7% ↗ | not reported | — | — |
| Toolathlon-Verified | 70.3% ↗ | not reported | — | — |
| Only Gemini 3.1 Pro Preview reports · 15 | ||||
| AIME 2026 | not reported | 98.3% ↗matharena ⚠ | — | — |
| APEX-Agents (Mercor) | not reported | 35.3% ↗ | — | — |
| ARC-AGI-2 | not reported | 77.1% ↗ | — | — |
| BALROG (BALROG) | not reported | 57% ↗ | — | — |
| EBR-bench (Epoch AI run) | not reported | 14.3% ↗epoch run | — | — |
| Furniture Assembly (Epoch AI run) | not reported | 26.7% ↗epoch run | — | — |
| GSO Opt@1 (GSO) | not reported | 21.6% ↗ | — | — |
| LMArena Agent (LMArena) | not reported | -0.0771 ↗ | — | — |
| LMArena Vision (LMArena) | not reported | 1279.3 ↗ | — | — |
| MirrorCode (Epoch AI run) | not reported | 8.9% ↗epoch run | — | — |
| SAGE (Vals AI) | not reported | 48.7% ↗ | — | — |
| SWE-Bench Pro | not reported | 54.2% ↗ | — | — |
| SWE-bench Verified (Epoch AI run) | not reported | 75.6% ↗epoch run | — | — |
| tau2-bench Banking Knowledge (Sierra) | not reported | 26% ↗ | — | — |
| Vending-Bench 2 (Andon Labs) | not reported | 3774.25 ↗ | — | — |
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 V4 Flash minus Gemini 3.1 Pro 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 V4 Flash | Gemini 3.1 Pro Preview | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1.0M tokens | Gemini 3.1 Pro Preview |
| Max output | — | 66K tokens | — |
| Input price / 1M | — | $2 ↗ | — |
| Output price / 1M | — | $12 ↗ | — |
| Cached input / 1M | — | $0.2 ↗ | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | $14 | — |
| Modalities | text | text · vision · audio | Gemini 3.1 Pro Preview |
| Released | 2026-07-31 | 2026-02-19 | — |
| Cited benchmark scores | 28 | 43 | — |
Reliability
Provider status
Live from /statusMore matchups
DeepSeek V4 Flash vs …
Models sharing the most benchmarksMore matchups
Gemini 3.1 Pro Preview vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run DeepSeek V4 Flash and Gemini 3.1 Pro Preview on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.