ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

DeepSeek V4 ProvsGemini 3.1 Flash-Lite

DeepSeek V4 Pro leads 4 of 4 shared benchmarks. DeepSeek V4 Pro is 1.3x cheaper per token. Gemini 3.1 Flash-Lite has the larger context window (1.0M tokens).

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
4 – 0
DeepSeek V4 Pro leads
Cheaper per token
DeepSeek V4 Pro
1.3x cheaper, input + output
Larger context
Gemini 3.1 Flash-Lite
1.0M tokens
Provider uptime (30d)
100% · 100%
DeepSeek · Google
DeepSeek V4 Pro
DeepSeek · released 2026-08-13
text
Context
1M
Max out
384K
Input /1M
$0.435
Output /1M
$0.87
Cached /1M
$0.004
Scores
11 · 9 core
Gemini 3.1 Flash-Lite
Google · released 2026-03-03
textvisionaudio
Context
1.0M
Max out
66K
Input /1M
$0.25
Output /1M
$1.5
Cached /1M
$0.025
Scores
10 · 5 core
Quality

Benchmark matrix

BenchmarkDeepSeek V4 ProGemini 3.1 Flash-LiteΔEdge
Reported by both · 4
GPQA Diamond90.9% epoch86.9% +4 ptDeepSeek V4 Pro
FrontierMath Tiers 1-3 v2 (Epoch AI run)45.3% epoch27.7% epoch+17.6 ptDeepSeek V4 Pro
OTIS Mock AIME 2024-2025 (Epoch AI run)96.7% epoch80% epoch+16.7 ptDeepSeek V4 Pro
SimpleQA Verified47% epoch43.3% +3.7 ptDeepSeek V4 Pro
Only DeepSeek V4 Pro reports · 7
AIME 202696.7% matharenanot reported
LMArena Elo1450.6 not reported
DeepSWE v1.162.7% not reported
FrontierMath Tier 4 v2 (Epoch AI run)2.4% epochnot reported
Humanity's Last Exam (with tools)60% not reported
SWE-bench Verified (Epoch AI run)77.6% epochnot reported
Terminal-Bench 2.187.9% not reported
Only Gemini 3.1 Flash-Lite reports · 5
Humanity's Last Exam (no tools)not reported16%
LiveCodeBenchnot reported72%
MMMLUnot reported88.9%
MMMU-Pronot reported76.8%
MRCR v2 (128k average)not reported60.1%
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 Pro minus Gemini 3.1 Flash-Lite 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

SpecDeepSeek V4 ProGemini 3.1 Flash-LiteEdge
Context window1M tokens1.0M tokensGemini 3.1 Flash-Lite
Max output384K tokens66K tokensDeepSeek V4 Pro
Input price / 1M$0.435 $0.25 Gemini 3.1 Flash-Lite
Output price / 1M$0.87 $1.5 DeepSeek V4 Pro
Cached input / 1M$0.004 $0.025 DeepSeek V4 Pro
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$1.31$1.75DeepSeek V4 Pro
Modalitiestexttext · vision · audioGemini 3.1 Flash-Lite
Released2026-08-132026-03-03
Cited benchmark scores1110
Reliability

Provider status

All providers
More matchups

DeepSeek V4 Pro vs …

More matchups

Gemini 3.1 Flash-Lite vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run DeepSeek V4 Pro and Gemini 3.1 Flash-Lite on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.