ResearchLLM Verifications Leaderboard

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

Head to head · tested 27 Oct 2026

Gemini 4 Argon vs Gemma 4 31B: accuracy, speed and price

Gemini 4 Argon is more accurate; Gemma 4 31B is cheaper.

GoogleGemini 4 Argon83.8% score · #2$0.0062 per question69 tok/sGoogleGemma 4 31B30.0% score · #64$0.0014 per question58 tok/s

Verdict

Built from the measurements below

  • Gemini 4 Argon is more accurate: 83.8% against 30.0% on the same 80 questions, a 53.8-point gap that is statistically significant.
  • Gemma 4 31B is 4.4× cheaper per question as billed ($0.0014 vs $0.0062), reasoning tokens included.
  • Gemini 4 Argon generates text 1.2× faster: 69 tokens per second against 58.
  • Gemma 4 31B starts answering sooner: 0.6 s to the first token, against 3.3 s for Gemini 4 Argon.
  • Gemini 4 Argon accepts more context: 1M tokens against 262k.

Which should you choose?

Choose Gemini 4 Argon for the most accurate answers of the two, faster streaming, shorter outputs (about 558 tokens per question against 3,307) and a 1M-token context window. Choose Gemma 4 31B for the lower cost per correct answer ($0.0046 against $0.0074), a quicker first token, open weights you can run yourself and more hosts to choose from on OpenRouter (13 against 2). The widest subject gap is in engineering: Gemini 4 Argon answered 13 of 15 correctly, Gemma 4 31B 0 of 15. With so few questions per subject, treat this as a lead to test on your own prompts, not a result.

Accuracy gap +53.8 points (z = 6.86). 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 4 ArgonGemma 4 31BEdge
Verification scoreHigher is better83.8%30.0%Gemini 4 Argon
Cost per questionLower is better$0.0062$0.0014Gemma 4 31B
Output speedHigher is better6958Gemini 4 Argon
Time to first tokenLower is better3.3 s0.6 sGemma 4 31B
End-to-end response timeLower is better9.9 s12.6 sGemini 4 Argon
Tokens per questionLower is better5583,307Gemini 4 Argon
Context windowHigher is better1M262kGemini 4 Argon

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 4 Argon first, Gemma 4 31B second

Verification scorehigher is better
Gemini 4 Argon83.8%
Gemma 4 31B30.0%
Cost per questionlower is better
Gemini 4 Argon$0.0062
Gemma 4 31B$0.0014
Output speedhigher is better
Gemini 4 Argon69
Gemma 4 31B58
Time to first tokenlower is better
Gemini 4 Argon3.3 s
Gemma 4 31B0.6 s
End-to-end response timelower is better
Gemini 4 Argon9.9 s
Gemma 4 31B12.6 s
Tokens per questionlower is better
Gemini 4 Argon558
Gemma 4 31B3,307
Context windowhigher is better
Gemini 4 Argon1M
Gemma 4 31B262k

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 4 ArgonGemma 4 31B
CreatorGoogleGoogle
Released13 Oct 20262 Apr 2026
Weights—Open weights
ReasoningYesYes
Inputaudio, file, image, text, videoimage, text, video
Outputtexttext
Context window1M tokens262k tokens
Knowledge cutoff——
List price in / out per 1M$2 / $10$0.2 / $0.4
Blended price per 1M (3:1)$4.00$0.25
Cheapest hostGoogle AI Studio · $1 / $5DeepInfra · $0.16 / $0.32
Hosts on OpenRouter213
Last tested25 Oct 202627 Oct 2026

Compare any two models →

Gemini 4 Argon vs Gemma 4 31B: frequently asked questions

Is Gemini 4 Argon better than Gemma 4 31B?
Gemini 4 Argon is more accurate: it answered 67 of 80 questions correctly (83.8%) against 24 of 80 (30.0%) for Gemma 4 31B. Gemini 4 Argon is more accurate; Gemma 4 31B is cheaper.
Which is cheaper, Gemini 4 Argon or Gemma 4 31B?
Gemma 4 31B is cheaper: $0.0014 per question as billed, against $0.0062. List prices: Gemini 4 Argon $2 in / $10 out, Gemma 4 31B $0.2 in / $0.4 out per million tokens.
Which is faster, Gemini 4 Argon or Gemma 4 31B?
Gemini 4 Argon is faster at 69 output tokens per second, against 58. Time to first token: 3.3 s for Gemini 4 Argon, 0.6 s for Gemma 4 31B.
Which has the larger context window, Gemini 4 Argon or Gemma 4 31B?
Gemini 4 Argon, with 1M tokens against 262k.