ResearchLLM Verifications Leaderboard

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

Head to head · tested 27 Oct 2026

Claude Opus 5.5 vs Gemini 3.1 Pro Preview: accuracy, speed and price

Similar accuracy; Claude Opus 5.5 costs less per question.

AnthropicClaude Opus 5.585.0% score · #1$0.015 per question129 tok/sGoogleGemini 3.1 Pro Preview77.5% score · #9$0.017 per question124 tok/s

Verdict

Built from the measurements below

  • Accuracy is too close to call: Claude Opus 5.5 scored 85.0% and Gemini 3.1 Pro Preview 77.5% on the same 80 questions, a gap within what chance alone could produce.
  • Claude Opus 5.5 is 1.2× cheaper per question as billed ($0.015 vs $0.017), reasoning tokens included.
  • Output speed is similar (129 vs 124 tokens per second).
  • Claude Opus 5.5 starts answering sooner: 2.3 s to the first token, against 3.4 s for Gemini 3.1 Pro Preview.

Which should you choose?

Choose Claude Opus 5.5 for the lower cost per correct answer ($0.017 against $0.022), a quicker first token, shorter outputs (about 645 tokens per question against 1,382) and more hosts to choose from on OpenRouter (5 against 2). The widest subject gap is in law: Claude Opus 5.5 answered 5 of 6 correctly, Gemini 3.1 Pro Preview 3 of 6. With so few questions per subject, treat this as a lead to test on your own prompts, not a result.

Accuracy gap +7.5 points (z = 1.22). 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

MeasureClaude Opus 5.5Gemini 3.1 Pro PreviewEdge
Verification scoreHigher is better85.0%77.5%Too close to call
Cost per questionLower is better$0.015$0.017Claude Opus 5.5
Output speedHigher is better129124Similar
Time to first tokenLower is better2.3 s3.4 sClaude Opus 5.5
End-to-end response timeLower is better7.6 s8.9 sClaude Opus 5.5
Tokens per questionLower is better6451,382Claude Opus 5.5
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

Claude Opus 5.5 first, Gemini 3.1 Pro Preview second

Verification scorehigher is better
Claude Opus 5.585.0%
Gemini 3.1 Pro Preview77.5%
Cost per questionlower is better
Claude Opus 5.5$0.015
Gemini 3.1 Pro Preview$0.017
Output speedhigher is better
Claude Opus 5.5129
Gemini 3.1 Pro Preview124
Time to first tokenlower is better
Claude Opus 5.52.3 s
Gemini 3.1 Pro Preview3.4 s
End-to-end response timelower is better
Claude Opus 5.57.6 s
Gemini 3.1 Pro Preview8.9 s
Tokens per questionlower is better
Claude Opus 5.5645
Gemini 3.1 Pro Preview1,382
Context windowhigher is better
Claude Opus 5.51M
Gemini 3.1 Pro Preview1M

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

SpecificationClaude Opus 5.5Gemini 3.1 Pro Preview
CreatorAnthropicGoogle
Released22 Sept 202619 Feb 2026
Weights——
ReasoningYesYes
Inputtext, image, fileaudio, file, image, text, video
Outputtexttext
Context window1M tokens1M tokens
Knowledge cutoff——
List price in / out per 1M$4 / $20$2 / $12
Blended price per 1M (3:1)$8.00$4.50
Cheapest hostAmazon Bedrock · $4 / $20Google · $1 / $6
Hosts on OpenRouter52
Last tested25 Oct 202626 Oct 2026

Compare any two models →

Claude Opus 5.5 vs Gemini 3.1 Pro Preview: frequently asked questions

Is Claude Opus 5.5 better than Gemini 3.1 Pro Preview?
On accuracy they are statistically tied: Claude Opus 5.5 scored 85.0% and Gemini 3.1 Pro Preview 77.5% on the same 80 questions from open datasets. Similar accuracy; Claude Opus 5.5 costs less per question.
Which is cheaper, Claude Opus 5.5 or Gemini 3.1 Pro Preview?
Claude Opus 5.5 is cheaper: $0.015 per question as billed, against $0.017. List prices: Claude Opus 5.5 $4 in / $20 out, Gemini 3.1 Pro Preview $2 in / $12 out per million tokens.
Which is faster, Claude Opus 5.5 or Gemini 3.1 Pro Preview?
Their output speed is similar: 129 and 124 tokens per second.
Which has the larger context window, Claude Opus 5.5 or Gemini 3.1 Pro Preview?
Both accept about the same amount of context: 1M and 1M tokens.