ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

DeepSeek V3vsGemini 2.5 Flash-Lite

Gemini 2.5 Flash-Lite leads 2 of 3 shared benchmarks. Gemini 2.5 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
1 – 2
Gemini 2.5 Flash-Lite leads
Cheaper per token
list price, input + output
Larger context
Gemini 2.5 Flash-Lite
1.0M tokens
Provider uptime (30d)
100% · 100%
DeepSeek · Google
DeepSeek V3
DeepSeek · released 2024-12-26
text
Context
128K
Max out
8K
Input /1M
Output /1M
Cached /1M
Scores
8 · 7 core
Gemini 2.5 Flash-Lite
Google · released 2025-07-22
textvisionaudio
Context
1.0M
Max out
66K
Input /1M
$0.1
Output /1M
$0.4
Cached /1M
$0.01
Scores
4 · 4 core
Quality

Benchmark matrix

BenchmarkDeepSeek V3Gemini 2.5 Flash-LiteΔEdge
Reported by both · 3
SWE-bench Verified42% 27.6% +14.4 ptDeepSeek V3
GPQA Diamond59.1% 66.7% -7.6 ptGemini 2.5 Flash-Lite
AIME 202525% matharena63.1% -38.1 ptGemini 2.5 Flash-Lite
Only DeepSeek V3 reports · 4
MMLU88.5% not reported
MMLU-Pro75.9% not reported
LMArena Elo1332.4 not reported
OTIS Mock AIME 2024-2025 (Epoch AI run)15.8% epochnot reported
Only Gemini 2.5 Flash-Lite reports · 1
Humanity's Last Exam (no tools)not reported6.9%
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 2.5 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 V3Gemini 2.5 Flash-LiteEdge
Context window128K tokens1.0M tokensGemini 2.5 Flash-Lite
Max output8K tokens66K tokensGemini 2.5 Flash-Lite
Input price / 1M$0.1
Output price / 1M$0.4
Cached input / 1M$0.01
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$0.5
Modalitiestexttext · vision · audioGemini 2.5 Flash-Lite
Released2024-12-262025-07-22
Cited benchmark scores84
Reliability

Provider status

All providers
More matchups

DeepSeek V3 vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run DeepSeek V3 and Gemini 2.5 Flash-Lite on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.