Compare / Gemini 2.5 Pro vs Inkling

Gemini 2.5 Pro vs Inkling

Which is cheaper, which is more capable, and which does better at each kind of work, from 18 results on 3 sources that measured both models.

Gemini 2.5 Pro
Google · profile
Inkling
Thinkingmachines · profile
Results compared
18
Shared sources
3

Gemini 2.5 Pro or Inkling? The short answer

  • Inkling is cheaper: $1.72 against $3.44 per million tokens, 50% less.
  • Inkling scores higher on the Artificial Analysis Intelligence Index: 25.0 against 16.1.
  • On our business benchmarks, Gemini 2.5 Pro ranks higher for writing and sticking to the facts.
  • On our business benchmarks, Inkling ranks higher for agents and tool use and reasoning and knowledge.

At a glance

Gemini 2.5 ProInkling
Price per million tokens$1.25 in · $10.00 out$0.95 in · $4.05 out
Blended (3 in : 1 out)$3.44$1.72
Cheapest host, blended$1.72 (Google AI Studio)$1.72 (DeepInfra, FP8)
Intelligence Index16.125.0
Spring Prompt overall––
Output speed, tokens a second–166
Context window1,048,576 tokens524,288 tokens
WeightsClosedOpen
Developer based inthe USthe US

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among models available today, for each kind of work, from our own benchmarks and licensed sources. The better rank is in green.

Use caseGemini 2.5 ProInkling
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 109 of 161 56 of 161
Professional workReal tasks from banking, consulting and law, business documents and freelance projects not measured 45 of 51
Reasoning and knowledgeHard questions across science, maths and general knowledge 92 of 195 64 of 195
WritingWhat people prefer in blind comparisons, and judged writing quality 42 of 187 59 of 187
Sticking to the factsSummarising without inventing things, and factual answers 38 of 153 75 of 153

Every shared result

BenchmarkMetricGemini 2.5 ProInkling
Arena (formerly LMArena)reportedOverallArena rating 1,4621,452
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,4371,444
Arena (formerly LMArena)reportedCreative writingArena rating 1,4431,384
Arena (formerly LMArena)reportedExpert promptsArena rating 1,4581,474
Arena (formerly LMArena)reportedInstruction followingArena rating 1,4381,427
Arena (formerly LMArena)reportedOverallArena rating 1,4461,442
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,4451,403
Artificial AnalysisreportedArtificial Analysis Coding Indexindex score 33.352.1
Artificial AnalysisreportedArtificial Analysis Intelligence Indexindex score 16.125.0
Artificial AnalysisreportedGPQA Diamond% of questions 84.4%87.2%
Artificial AnalysisreportedHumanity's Last Exam% of questions 22.5%31.9%
Artificial AnalysisreportedLong-context reasoning (AA-LCR)% of questions 69.0%77.3%
Artificial AnalysisreportedSciCode% of problems 46.3%47.0%
Artificial AnalysisreportedTerminal-Bench 2.1% of tasks 28.5%55.1%
Artificial AnalysisreportedTerminal-Bench 4.0% of tasks 0.0%1.0%
Artificial AnalysisreportedΤ-bench banking% of tasks 9.7%29.1%
tau2-benchreportedConsistency (pass^4)% of tasks 1.0%11.3%
tau2-benchreportedTask success (pass^1)% of tasks 13.7%25.0%

Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.

Quick answers

Is Gemini 2.5 Pro better than Inkling?

It depends on the task. Among models available today, on our benchmarks and licensed sources, Gemini 2.5 Pro ranks higher for writing and sticking to the facts; Inkling ranks higher for agents and tool use and reasoning and knowledge.

Which is cheaper, Gemini 2.5 Pro or Inkling?

Inkling costs $1.72 per million tokens (three input to one output), against $3.44 for Gemini 2.5 Pro.

Run Gemini 2.5 Pro and Inkling on your own prompt

Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.