ResearchLLM Verifications Leaderboard

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

GoogleOpen weightsReleased 3 Apr 2026

Gemma 4 26B A4B benchmarks, speed and API pricing

Reviewed by Suhas Bhairav · Tested

Compare

Available through OpenRouter on

  • Darkbloom$0.042 in · $0.22 out
  • AkashML$0.07 in · $0.24 out
  • Makora$0.07 in · $0.24 out
  • NextBit$0.09 in · $0.3 out
  • PrimeIntellect$0.1 in · $0.3 out
  • CoreWeave$0.1 in · $0.3 out
  • Cloudflare$0.1 in · $0.3 out
  • Io Net$0.09 in · $0.31 out
  • DekaLLM$0.06 in · $0.33 out
  • DeepInfra$0.07 in · $0.34 out
  • Venice$0.13 in · $0.4 out
  • Parasail$0.13 in · $0.4 out
  • Novita$0.13 in · $0.4 out
  • SiliconFlow$0.14 in · $0.4 out
  • Google$0.15 in · $0.6 out
Intelligence15.0% correct#71 of 72
Speed172tok/s#11 of 72
Cost$0.0011per question#27 of 72List $0.09 in · $0.3 out per 1M
Verbosity3,722tokens per question#69 of 72

Summary

  • Answers 12 of 80 verification questions correctly (15.0%), placing #71 of 72 models tested on the current suite.
  • Generates 172 output tokens per second, faster than 86% of the models the leaderboard measures.
  • Starts responding after 0.7 s (median time to first token), including thinking time.
  • Costs $0.0011 per question as billed, #12 cheapest of 12 models priced under $0.15 per 1M tokens.

Specifications

Reasoning
Yes
Input
image, text, video
Output
text
Context window
262k tokens
Knowledge cutoff
—
OpenRouter ID
google/gemma-4-26b-a4b-it
Last tested
27 Oct 2026

Peer group: 13 models with a blended list price under $0.15 per 1M tokens (3 input : 1 output). Charts below compare Gemma 4 26B A4B with all models; cost and speed charts focus on this peer group.

Intelligence

Verification score: the share of 80 questions from open datasets answered correctly. See the benchmark datasets.

Score vs. cost per question

Gemma 4 26B A4B circled; dashed line joins models no cheaper model beats

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-20bGranite 4.0 MicroNova Micro 1.0Mercury 2.5Phi 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-120b

Score vs. end-to-end response time

Gemma 4 26B A4B circled · accurate and quick sits top left

Most attractive quadrant02550751000 s25 s50 s75 s100 sEnd-to-end response time (s) →Verification score (%) →Qwen3.8 2.4T A95BCommand AReka Flash 3Llama 4 ScoutGemma 4 26B A4BLing 3.1 FlashHermes 4 405BMuse WonderSolar Pro 4DeepSeek V4 Pro 0813Mistral Large 4Claude Opus 5.5Llama 4 MaverickKimi K3.1 Pro

Score vs. tokens per question

Gemma 4 26B A4B circled · output tokens, reasoning included

Most attractive quadrant02550751001001,00010,000Output tokens per question (log) →Verification score (%) →Command AReka Flash 3Llama 4 ScoutQwen3.7 PlusGemma 4 26B A4BGemma 4 31BQwen3.5 397B A17BClaude Fable 5.1GPT-6 AstraMuse WonderGrok 4.7o3gpt-oss-20bGranite 4.0 MicroMinistral 3 3B 2512Nova Micro 1.0Mercury 2.5Granite 4.2 8BMinistral 3 14B 2512Hy3GLM 5.3 FlashSolar Pro 4Qwen3.6 35B A3BInkling SmallNemotron 3 UltraClaude Opus 5.5Gemini 4 ArgonGPT-5.4GPT-6 SolMiMo-V2.6-Pro

Verification score

All models tested on the current suite

  1. 1Claude Opus 5.585.0
  2. 2Gemini 4 Argon83.8
  3. 3GPT-5.3-Codex82.5
  4. 3Gemini 3.8 Flash82.5
  5. 5Claude Fable 5.181.2
  6. 6Grok 4.780.0
  7. 7Muse Wonder78.8
  8. 7Claude Sonnet 5.578.8
  9. 9Gemini 3.1 Pro Preview77.5
  10. 9Muse Spark Open77.5
  11. 71Gemma 4 26B A4B15.0

61 more models · see the full leaderboard

6 of 78 tested models have no verification score

Cost

Average cost of one question, split into input, reasoning and answer tokens at each model's list price. Reasoning tokens are billed as output.

Cost per question, as billed

All models · lower is better

  1. 1Granite 4.0 Micro$0.000051
  2. 2gpt-oss-20b$0.000066
  3. 3Granite 4.2 8B$0.000077
  4. 4Nova Micro 1.0$0.000087
  5. 5Mercury 2.5$0.00011
  6. 6Phi 4$0.00012
  7. 7gpt-oss-120b$0.00013
  8. 8GLM 5.3 Flash$0.00015
  9. 9Ministral 3 3B 2512$0.00019
  10. 10GPT-6 Luna$0.00025
  11. 27Gemma 4 26B A4B$0.0011

61 more models · see the full leaderboard

6 of 78 tested models have no cost per question
  • LFM2.5-2.6B: no verification score (80 of 80 questions failed on the host's side)
  • Ling 3.0 Flash VL: no verification score (not yet run on the current question suite)
  • Qwen3.5-122B-A10B: no verification score (not yet run on the current question suite)
  • Qwen3 Next 80B A3B Thinking: no verification score (not yet run on the current question suite)
  • Nova Premier 1.0: no verification score (not yet run on the current question suite)
  • GPT-5.5 Pro: no verification score (not yet run on the current question suite)

Speed and latency

Median of 3 streamed runs of the same prompt, measured 25 Oct 2026.

Latency vs. output speed

Gemma 4 26B A4B circled · quick to start and fast sits top left

Most attractive quadrant02004006008000.0 s5.0 s10.0 s15.0 s20.0 sTime to first token (s) →Output speed (tok/s) →Nemotron 3.5 Super VLGemma 4 26B A4BMuse WonderMinistral 3 3B 2512Trinity Large ThinkingGemini 3.5 Flash LiteGemini 3.1 Pro PreviewGemini 4 Argon

Results by category

Questions answered correctly in each category

Science4/30
Engineering0/15
Medicine1/11
Economics4/9
Law1/6
Humanities & social science2/9

More from Google

Google#2Gemini 4 Argon83.8% verification score69 tok/s3.3 s first token$0.0062 / questionGoogle#3Gemini 3.8 Flash82.5% verification score142 tok/s3.2 s first token$0.0037 / questionGoogle#9Gemini 3.1 Pro Preview77.5% verification score124 tok/s3.4 s first token$0.017 / question

All Google models →

Compare Gemma 4 26B A4B

Head to head with its closest rivals, other Google models and the top models overall.

Hosts and prices

Every host serving this model through OpenRouter, from OpenRouter's catalogue

HostInput / 1MOutput / 1MContextMax outputQuantization
Darkbloom$0.042$0.22131k33k—
AkashML$0.07$0.24131k118kfp4
Makora$0.07$0.24256k128k—
NextBit$0.09$0.3262k236kbf16
PrimeIntellect$0.1$0.3262k33kbf16
CoreWeave$0.1$0.3262k236kbf16
Cloudflare$0.1$0.3256k230k—
Io Net$0.09$0.31262k236kbf16
DekaLLM$0.06$0.33262k236kbf16
DeepInfra$0.07$0.34262k16kfp8
Venice$0.13$0.4256k8kbf16
Parasail$0.13$0.4262k236kbf16
Novita$0.13$0.4262k131kbf16
SiliconFlow$0.14$0.4262k236kfp8
Google$0.15$0.6262k236k—

Gemma 4 26B A4B: frequently asked questions

How accurate is Gemma 4 26B A4B?
Gemma 4 26B A4B answered 12 of 80 questions correctly (15.0%) in the 2026-10-27 run, ranking #71 of 78 models.
How fast is Gemma 4 26B A4B?
Gemma 4 26B A4B generated a median of 172 output tokens per second in the 2026-10-27 run, ranking #11 of 78. Median time to first token was 0.7 s.
What is the latency of Gemma 4 26B A4B?
Gemma 4 26B A4B had a median time to first token of 0.7 s in the 2026-10-27 run, ranking #34 of 78 models.
How much does Gemma 4 26B A4B cost?
Gemma 4 26B A4B cost $0.0011 per question on average as billed in the 2026-10-27 run, reasoning tokens included.
What is Gemma 4 26B A4B API pricing?
Gemma 4 26B A4B is listed at $0.09 per million input tokens and $0.3 per million output tokens on OpenRouter.
What is the context window of Gemma 4 26B A4B?
Gemma 4 26B A4B accepts up to 262,144 tokens of context, according to OpenRouter's model catalogue.
Is Gemma 4 26B A4B open source?
Yes. Gemma 4 26B A4B is an open-weights model: Google publishes the weights, so you can run it yourself as well as through an API.
Who makes Gemma 4 26B A4B?
Gemma 4 26B A4B is made by Google. The LLM Verifications Leaderboard tested it through OpenRouter using the model ID google/gemma-4-26b-a4b-it.
Where can I use Gemma 4 26B A4B via API?
Through OpenRouter, Gemma 4 26B A4B is served by 14 hosts: AkashML, Cloudflare, CoreWeave, Darkbloom, DeepInfra, DekaLLM, Io Net, Makora, NextBit, Novita, Parasail, PrimeIntellect, SiliconFlow, Venice.