ResearchLLM Verifications Leaderboard

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

Head to head · tested 27 Oct 2026

Gemma 4 26B A4B vs Reka Flash 3: accuracy, speed and price

Gemma 4 26B A4B is more accurate; Reka Flash 3 is cheaper.

GoogleGemma 4 26B A4B15.0% score · #71$0.0011 per question172 tok/srekaaiReka Flash 31.2% score · #72$0.0008 per question101 tok/s

Verdict

Built from the measurements below

  • Gemma 4 26B A4B is more accurate: 15.0% against 1.2% on the same 80 questions, a 13.7-point gap that is statistically significant.
  • Reka Flash 3 is 1.3× cheaper per question as billed ($0.0008 vs $0.0011), reasoning tokens included.
  • Gemma 4 26B A4B generates text 1.7× faster: 172 tokens per second against 101.
  • Reka Flash 3 starts answering sooner: 0.5 s to the first token, against 0.7 s for Gemma 4 26B A4B.
  • Gemma 4 26B A4B accepts more context: 262k tokens against 66k.

Which should you choose?

Choose Gemma 4 26B A4B for the most accurate answers of the two, the lower cost per correct answer ($0.0072 against $0.067), faster streaming, a 262k-token context window and more hosts to choose from on OpenRouter (15 against 1). Choose Reka Flash 3 for a quicker first token. The widest subject gap is in economics: Gemma 4 26B A4B answered 4 of 9 correctly, Reka Flash 3 0 of 9. With so few questions per subject, treat this as a lead to test on your own prompts, not a result.

Accuracy gap +13.7 points (z = 3.18). 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

MeasureGemma 4 26B A4BReka Flash 3Edge
Verification scoreHigher is better15.0%1.2%Gemma 4 26B A4B
Cost per questionLower is better$0.0011$0.0008Reka Flash 3
Output speedHigher is better172101Gemma 4 26B A4B
Time to first tokenLower is better0.7 s0.5 sReka Flash 3
End-to-end response timeLower is better4.8 s7.4 sGemma 4 26B A4B
Tokens per questionLower is better3,7223,855Similar
Context windowHigher is better262k66kGemma 4 26B A4B

Side by side

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

Every measure

Gemma 4 26B A4B first, Reka Flash 3 second

Verification scorehigher is better
Gemma 4 26B A4B15.0%
Reka Flash 31.2%
Cost per questionlower is better
Gemma 4 26B A4B$0.0011
Reka Flash 3$0.0008
Output speedhigher is better
Gemma 4 26B A4B172
Reka Flash 3101
Time to first tokenlower is better
Gemma 4 26B A4B0.7 s
Reka Flash 30.5 s
End-to-end response timelower is better
Gemma 4 26B A4B4.8 s
Reka Flash 37.4 s
Tokens per questionlower is better
Gemma 4 26B A4B3,722
Reka Flash 33,855
Context windowhigher is better
Gemma 4 26B A4B262k
Reka Flash 366k

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

SpecificationGemma 4 26B A4BReka Flash 3
CreatorGooglerekaai
Released3 Apr 202612 Mar 2025
WeightsOpen weightsOpen weights
ReasoningYesYes
Inputimage, text, videotext
Outputtexttext
Context window262k tokens66k tokens
Knowledge cutoff—31 Jan 2025
List price in / out per 1M$0.09 / $0.3$0.1 / $0.2
Blended price per 1M (3:1)$0.14$0.13
Cheapest hostDarkbloom · $0.042 / $0.22Reka · $0.1 / $0.2
Hosts on OpenRouter151
Last tested27 Oct 202627 Oct 2026

Compare any two models →

Gemma 4 26B A4B vs Reka Flash 3: frequently asked questions

Is Gemma 4 26B A4B better than Reka Flash 3?
Gemma 4 26B A4B is more accurate: it answered 12 of 80 questions correctly (15.0%) against 1 of 80 (1.2%) for Reka Flash 3. Gemma 4 26B A4B is more accurate; Reka Flash 3 is cheaper.
Which is cheaper, Gemma 4 26B A4B or Reka Flash 3?
Reka Flash 3 is cheaper: $0.0008 per question as billed, against $0.0011. List prices: Gemma 4 26B A4B $0.09 in / $0.3 out, Reka Flash 3 $0.1 in / $0.2 out per million tokens.
Which is faster, Gemma 4 26B A4B or Reka Flash 3?
Gemma 4 26B A4B is faster at 172 output tokens per second, against 101. Time to first token: 0.7 s for Gemma 4 26B A4B, 0.5 s for Reka Flash 3.
Which has the larger context window, Gemma 4 26B A4B or Reka Flash 3?
Gemma 4 26B A4B, with 262k tokens against 66k.