ResearchLLM Verifications Leaderboard

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

Head to head · tested 27 Oct 2026

Inkling vs Step 5 Preview: accuracy, speed and price

Similar accuracy; Inkling costs less per question.

Thinking MachinesInkling66.2% score · #31$0.0012 per question118 tok/sStepFunStep 5 Preview63.8% score · #34$0.0047 per question93 tok/s

Verdict

Built from the measurements below

  • Accuracy is too close to call: Inkling scored 66.2% and Step 5 Preview 63.8% on the same 80 questions, a gap within what chance alone could produce.
  • Inkling is 3.8× cheaper per question as billed ($0.0012 vs $0.0047), reasoning tokens included.
  • Inkling generates text 1.3× faster: 118 tokens per second against 93.
  • Inkling starts answering sooner: 0.6 s to the first token, against 0.6 s for Step 5 Preview.
  • Step 5 Preview accepts more context: 1M tokens against 524k.

Which should you choose?

Choose Inkling for the lower cost per correct answer ($0.0019 against $0.0074), faster streaming, a quicker first token and shorter outputs (about 228 tokens per question against 1,630). Choose Step 5 Preview for a 1M-token context window and more hosts to choose from on OpenRouter (4 against 1). The widest subject gap is in law: Inkling answered 4 of 6 correctly, Step 5 Preview 2 of 6. 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 = 0.33). 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

MeasureInklingStep 5 PreviewEdge
Verification scoreHigher is better66.2%63.8%Too close to call
Cost per questionLower is better$0.0012$0.0047Inkling
Output speedHigher is better11893Inkling
Time to first tokenLower is better0.6 s0.6 sInkling
End-to-end response timeLower is better5.0 s8.2 sInkling
Tokens per questionLower is better2281,630Inkling
Context windowHigher is better524k1MStep 5 Preview

Side by side

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

Every measure

Inkling first, Step 5 Preview second

Verification scorehigher is better
Inkling66.2%
Step 5 Preview63.8%
Cost per questionlower is better
Inkling$0.0012
Step 5 Preview$0.0047
Output speedhigher is better
Inkling118
Step 5 Preview93
Time to first tokenlower is better
Inkling0.6 s
Step 5 Preview0.6 s
End-to-end response timelower is better
Inkling5.0 s
Step 5 Preview8.2 s
Tokens per questionlower is better
Inkling228
Step 5 Preview1,630
Context windowhigher is better
Inkling524k
Step 5 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

SpecificationInklingStep 5 Preview
CreatorThinking MachinesStepFun
Released17 Jul 20268 Oct 2026
WeightsOpen weightsOpen weights
ReasoningYesYes
Inputtext, image, audiotext, image, video
Outputtexttext
Context window524k tokens1M tokens
Knowledge cutoff——
List price in / out per 1M$1 / $4.05$1 / $2.7
Blended price per 1M (3:1)$1.76$1.43
Cheapest hostTogether · $1 / $4.05InferenceNet · $1 / $2.7
Hosts on OpenRouter14
Last tested27 Oct 202627 Oct 2026

Compare any two models →

Inkling vs Step 5 Preview: frequently asked questions

Is Inkling better than Step 5 Preview?
On accuracy they are statistically tied: Inkling scored 66.2% and Step 5 Preview 63.8% on the same 80 questions from open datasets. Similar accuracy; Inkling costs less per question.
Which is cheaper, Inkling or Step 5 Preview?
Inkling is cheaper: $0.0012 per question as billed, against $0.0047. List prices: Inkling $1 in / $4.05 out, Step 5 Preview $1 in / $2.7 out per million tokens.
Which is faster, Inkling or Step 5 Preview?
Inkling is faster at 118 output tokens per second, against 93. Time to first token: 0.6 s for Inkling, 0.6 s for Step 5 Preview.
Which has the larger context window, Inkling or Step 5 Preview?
Step 5 Preview, with 1M tokens against 524k.