ResearchLLM Verifications Leaderboard

Data as of · 78 models, 80 questions · reviewed by Suhas Bhairav · methodology

Head to head · tested 27 Oct 2026

Gemini 3.8 Flash vs Gemini 4 Argon: accuracy, speed and price

Similar accuracy; Gemini 3.8 Flash costs less per question.

GoogleGemini 3.8 Flash82.5% score · #3$0.0037 per question142 tok/sGoogleGemini 4 Argon83.8% score · #2$0.0062 per question69 tok/s

Verdict

Built from the measurements below

  • Accuracy is too close to call: Gemini 3.8 Flash scored 82.5% and Gemini 4 Argon 83.8% on the same 80 questions, a gap within what chance alone could produce.
  • Gemini 3.8 Flash is 1.7× cheaper per question as billed ($0.0037 vs $0.0062), reasoning tokens included.
  • Gemini 3.8 Flash generates text 2.1× faster: 142 tokens per second against 69.

Which should you choose?

Choose Gemini 3.8 Flash for the lower cost per correct answer ($0.0045 against $0.0074) and faster streaming. Choose Gemini 4 Argon for shorter outputs (about 558 tokens per question against 925).

Accuracy gap -1.3 points (z = -0.21). A winner is called only when z is at least 1.96, the usual 95% threshold. Speed, latency and price need a 10% margin.

Head to head

Same questions, same prompt, same API

MeasureGemini 3.8 FlashGemini 4 ArgonEdge
Verification scoreHigher is better82.5%83.8%Too close to call
Cost per questionLower is better$0.0037$0.0062Gemini 3.8 Flash
Output speedHigher is better14269Gemini 3.8 Flash
Time to first tokenLower is better3.2 s3.3 sSimilar
End-to-end response timeLower is better5.6 s9.9 sGemini 3.8 Flash
Tokens per questionLower is better925558Gemini 4 Argon
Context windowHigher is better1M1MSimilar

Side by side

Bars are scaled to the larger of the two values. The winner on each measure is marked in bold.

Every measure

Gemini 3.8 Flash first, Gemini 4 Argon second

Verification scorehigher is better
Gemini 3.8 Flash82.5%
Gemini 4 Argon83.8%
Cost per questionlower is better
Gemini 3.8 Flash$0.0037
Gemini 4 Argon$0.0062
Output speedhigher is better
Gemini 3.8 Flash142
Gemini 4 Argon69
Time to first tokenlower is better
Gemini 3.8 Flash3.2 s
Gemini 4 Argon3.3 s
End-to-end response timelower is better
Gemini 3.8 Flash5.6 s
Gemini 4 Argon9.9 s
Tokens per questionlower is better
Gemini 3.8 Flash925
Gemini 4 Argon558
Context windowhigher is better
Gemini 3.8 Flash1M
Gemini 4 Argon1M

Score vs. cost per question

Both models in color, every other model in grey

Most attractive quadrant0255075100$0.00001$0.0001$0.001$0.01$0.10Cost per question (USD, log) →Verification score (%) →Qwen3.8 2.4T A95BCommand AReka Flash 3Gemma 4 26B A4BGemma 4 31BQwen3.5 397B A17BHermes 4 405BMuse WonderGrok 4.7o3gpt-oss-20bMinistral 3 3B 2512Nova Micro 1.0Phi 4Granite 4.2 8BHy3GLM 5.3 FlashSolar Pro 4Trinity Large ThinkingMiniMax M3Mistral Large 4Claude Opus 5.5GPT-6.1 SolGemini 4 ArgonGPT-5.4GPT-6 Lunagpt-oss-120bLlama 4 Maverick

Specifications and pricing

From OpenRouter's catalogue, plus the leaderboard's test dates

SpecificationGemini 3.8 FlashGemini 4 Argon
CreatorGoogleGoogle
Released2 Sept 202613 Oct 2026
Weights——
ReasoningYesYes
Inputtext, image, video, file, audioaudio, file, image, text, video
Outputtexttext
Context window1M tokens1M tokens
Knowledge cutoff——
List price in / out per 1M$0.825 / $4.125$2 / $10
Blended price per 1M (3:1)$1.65$4.00
Cheapest hostGoogle AI Studio · $0.375 / $1.875Google AI Studio · $1 / $5
Hosts on OpenRouter22
Last tested25 Oct 202625 Oct 2026

Compare any two models →

Gemini 3.8 Flash vs Gemini 4 Argon: frequently asked questions

Is Gemini 3.8 Flash better than Gemini 4 Argon?
On accuracy they are statistically tied: Gemini 3.8 Flash scored 82.5% and Gemini 4 Argon 83.8% on the same 80 questions from open datasets. Similar accuracy; Gemini 3.8 Flash costs less per question.
Which is cheaper, Gemini 3.8 Flash or Gemini 4 Argon?
Gemini 3.8 Flash is cheaper: $0.0037 per question as billed, against $0.0062. List prices: Gemini 3.8 Flash $0.825 in / $4.125 out, Gemini 4 Argon $2 in / $10 out per million tokens.
Which is faster, Gemini 3.8 Flash or Gemini 4 Argon?
Gemini 3.8 Flash is faster at 142 output tokens per second, against 69. Time to first token: 3.2 s for Gemini 3.8 Flash, 3.3 s for Gemini 4 Argon.
Which has the larger context window, Gemini 3.8 Flash or Gemini 4 Argon?
Both accept about the same amount of context: 1M and 1M tokens.