ResearchLLM Verifications Leaderboard

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

Head to head · tested 27 Oct 2026

Qwen3.7 Plus vs Qwen3.8 2.4T A95B: accuracy, speed and price

Similar accuracy; Qwen3.7 Plus costs less per question.

QwenQwen3.7 Plus60.0% score · #38$0.0033 per question62 tok/sQwenQwen3.8 2.4T A95B57.5% score · #43$0.015 per question44 tok/s

Verdict

Built from the measurements below

  • Accuracy is too close to call: Qwen3.7 Plus scored 60.0% and Qwen3.8 2.4T A95B 57.5% on the same 80 questions, a gap within what chance alone could produce.
  • Qwen3.7 Plus is 4.7× cheaper per question as billed ($0.0033 vs $0.015), reasoning tokens included.
  • Qwen3.7 Plus generates text 1.4× faster: 62 tokens per second against 44.
  • Qwen3.7 Plus starts answering sooner: 1.1 s to the first token, against 3.1 s for Qwen3.8 2.4T A95B.

Which should you choose?

Choose Qwen3.7 Plus for the lower cost per correct answer ($0.0054 against $0.026), faster streaming and a quicker first token. Choose Qwen3.8 2.4T A95B for open weights you can run yourself and more hosts to choose from on OpenRouter (5 against 1). The widest subject gap is in humanities & social science: Qwen3.7 Plus answered 9 of 9 correctly, Qwen3.8 2.4T A95B 7 of 9. With so few questions per subject, treat this as a lead to test on your own prompts, not a result.

Accuracy gap +2.5 points (z = 0.32). 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

MeasureQwen3.7 PlusQwen3.8 2.4T A95BEdge
Verification scoreHigher is better60.0%57.5%Too close to call
Cost per questionLower is better$0.0033$0.015Qwen3.7 Plus
Output speedHigher is better6244Qwen3.7 Plus
Time to first tokenLower is better1.1 s3.1 sQwen3.7 Plus
End-to-end response timeLower is better12.4 s14.8 sQwen3.7 Plus
Tokens per questionLower is better2,4622,408Similar
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

Qwen3.7 Plus first, Qwen3.8 2.4T A95B second

Verification scorehigher is better
Qwen3.7 Plus60.0%
Qwen3.8 2.4T A95B57.5%
Cost per questionlower is better
Qwen3.7 Plus$0.0033
Qwen3.8 2.4T A95B$0.015
Output speedhigher is better
Qwen3.7 Plus62
Qwen3.8 2.4T A95B44
Time to first tokenlower is better
Qwen3.7 Plus1.1 s
Qwen3.8 2.4T A95B3.1 s
End-to-end response timelower is better
Qwen3.7 Plus12.4 s
Qwen3.8 2.4T A95B14.8 s
Tokens per questionlower is better
Qwen3.7 Plus2,462
Qwen3.8 2.4T A95B2,408
Context windowhigher is better
Qwen3.7 Plus1M
Qwen3.8 2.4T A95B1M

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

SpecificationQwen3.7 PlusQwen3.8 2.4T A95B
CreatorQwenQwen
Released3 Jun 202612 Aug 2026
Weights—Open weights
ReasoningYesYes
Inputtext, imagetext
Outputtexttext
Context window1M tokens1M tokens
Knowledge cutoff——
List price in / out per 1M$0.32 / $1.28$2 / $6
Blended price per 1M (3:1)$0.56$3.00
Cheapest hostAlibaba · $0.32 / $1.28Novita · $2 / $6
Hosts on OpenRouter15
Last tested27 Oct 202627 Oct 2026

Compare any two models →

Qwen3.7 Plus vs Qwen3.8 2.4T A95B: frequently asked questions

Is Qwen3.7 Plus better than Qwen3.8 2.4T A95B?
On accuracy they are statistically tied: Qwen3.7 Plus scored 60.0% and Qwen3.8 2.4T A95B 57.5% on the same 80 questions from open datasets. Similar accuracy; Qwen3.7 Plus costs less per question.
Which is cheaper, Qwen3.7 Plus or Qwen3.8 2.4T A95B?
Qwen3.7 Plus is cheaper: $0.0033 per question as billed, against $0.015. List prices: Qwen3.7 Plus $0.32 in / $1.28 out, Qwen3.8 2.4T A95B $2 in / $6 out per million tokens.
Which is faster, Qwen3.7 Plus or Qwen3.8 2.4T A95B?
Qwen3.7 Plus is faster at 62 output tokens per second, against 44. Time to first token: 1.1 s for Qwen3.7 Plus, 3.1 s for Qwen3.8 2.4T A95B.
Which has the larger context window, Qwen3.7 Plus or Qwen3.8 2.4T A95B?
Both accept about the same amount of context: 1M and 1M tokens.