BenchLeader
Menu

Gemini 4 Carbon vs Inkling 2 Small

Full profiles: Gemini 4 Carbon (Google) and Inkling 2 Small (Thinking Machines): every benchmark, price and rank.

Updated · Data from 10 sources

As of 13 Nov 2026, Gemini 4 Carbon is ahead of Inkling 2 Small on quality (69.5 vs 57.9 on the BenchLeader Index), but Inkling 2 Small is 8.4× cheaper at $0.475 vs $4.00 per 1M tokens blended. Choose Gemini 4 Carbon for knowledge (76 vs 54), reasoning (73 vs 53), and agents & tools (76 vs 61); choose Inkling 2 Small for long context (66 vs 64), where it also streams ~2× faster.

Key facts (as of 13 Nov 2026)

  • Gemini 4 Carbon scores 69.5 on the BenchLeader Index and Inkling 2 Small scores 57.9 (BenchLeader, 13 Nov 2026).
  • Gemini 4 Carbon costs $4.00 per 1M tokens blended (list price, 13 Nov 2026).
  • Inkling 2 Small costs $0.475 per 1M tokens blended (list price, 13 Nov 2026).
  • Inkling 2 Small streams ~2× faster than Gemini 4 Carbon (Artificial Analysis, 7-day median, 13 Nov 2026).
  • Of the 31 benchmarks both models have, Gemini 4 Carbon leads 27 (BenchLeader, 13 Nov 2026).
  • On Arena WebDev, Gemini 4 Carbon is rated 1768 and Inkling 2 Small 1647 (LMArena, as published by 13 Nov 2026).
Gemini 4 Carbon benchmarks high Google Inkling 2 Small benchmarks Thinking MachinesAdd a third model

Which to pick for…

The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.

Use casePickWhyConfidence
CodingGemini 4 Carbon74 vs 60 category score; Arena WebDev 1768 vs 1647High
Agents & tool useGemini 4 Carbon76 vs 61 category score; Arena Agent 17 vs 2.5High
ReasoningGemini 4 Carbon73 vs 53 category score; HLE-Diamond (AA) 69.1% vs 28.7%High
KnowledgeGemini 4 Carbon76 vs 54 category score; AA-Omniscience v1.1 53.5 vs 16.1High
Long documentsInkling 2 Small66 vs 64 category score; AA-LCR v1.1 83.3% vs 79.3%Medium
Chat quality (human preference)Gemini 4 Carbon73 vs 59 on Arena votesHigh
Lowest costInkling 2 Small$0.475 vs $4.00 per 1M blended; agentic coding session $0.022 vs $0.160–
Fastest first answerEither66.3 s (Gemini 4 Carbon (high)) vs 63.9 s (Inkling 2 Small) to the first answer token–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • Gemini 4 Carbon (high) leads on quality: 69.5 vs 57.9.
  • Gemini 4 Carbon (high) is stronger in agents & tools, coding, human preference, knowledge, reasoning.
  • Inkling 2 Small is stronger in long context.
  • Inkling 2 Small is 8.4× cheaper ($0.475 vs $4.00 per 1M blended).

At a glance

SpecGemini 4 CarbonInkling 2 Small
DeveloperGoogleThinking Machines
Released28 Oct 20265 Nov 2026
Context window (tokens)1,048,5761,048,576
Compared atGemini 4 Carbon (high)Inkling 2 Small
Open weightsNoNo
Price in / out / cached input per 1M$2.00 / $10.00 / $0.100$0.300 / $1.00 / –

Category by category

Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.

CategoryGemini 4 Carbon (high)Inkling 2 SmallLeader
Reasoning73.252.8Gemini 4 Carbon
Coding74.160.3Gemini 4 Carbon
Agents & tools75.861.1Gemini 4 Carbon
Maths71.9–not comparable
Knowledge76.153.5Gemini 4 Carbon
Human preference72.658.6Gemini 4 Carbon
Multimodal–64.0not comparable
Long context64.366.4Inkling 2 Small

On one chart

Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.

2550 avg75ReasoningCodingAgents & toolsKnowledgeLong contextHumanpreferenceGemini 4 Carbon, Reasoning: 73.2Gemini 4 Carbon, Coding: 74.1Gemini 4 Carbon, Agents & tools: 75.8Gemini 4 Carbon, Knowledge: 76.1Gemini 4 Carbon, Long context: 64.3Gemini 4 Carbon, Human preference: 72.6Inkling 2 Small, Reasoning: 52.8Inkling 2 Small, Coding: 60.3Inkling 2 Small, Agents & tools: 61.1Inkling 2 Small, Knowledge: 53.5Inkling 2 Small, Long context: 66.4Inkling 2 Small, Human preference: 58.6

Not drawn, measured for fewer than two of these models: Maths, Instruction following, Multimodal.

Model, click to add or removeIndex

Where sources disagree

Across the 31 benchmarks both have, Gemini 4 Carbon leads 27, Inkling 2 Small leads 4. Every overall index that rates both puts Gemini 4 Carbon ahead.

Overall indexGemini 4 Carbon (high)Inkling 2 SmallLeader
BenchLeader Index69.557.9Gemini 4 Carbon
AA Intelligence Index v5.060.030.6Gemini 4 Carbon
Vals Index70.556.1Gemini 4 Carbon
Arena Text15261412Gemini 4 Carbon

Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).

Price, speed and latency

List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.

MeasureGemini 4 Carbon (high)Inkling 2 Small
Blended price per 1M tokens$4.00$0.475
Input / output per 1M$2.00 / $10.00$0.300 / $1.00
Cached input per 1M$0.100–
Price per task: chat reply$0.0038$0.0004
Price per task: summarize a 30-page report$0.030$0.0042
Price per task: code edit$0.027$0.0033
Price per task: agentic coding session$0.160$0.022
Price per task: structured extraction$0.0060$0.0008
Agentic coding session, input mostly cached$0.074–
Cost per benchmark task (AA Index)$5.48$1.18
Output tokens per task (AA Index)123k150k
Of which reasoning72k88k
Time per task (AA Index)29 min28 min
Output speed72 tok/s90 tok/s
Time to first answer66.3 s63.9 s
Time to a complete answer160.6 s163.6 s

Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $5.48 on Gemini 4 Carbon (high) and $1.18 on Inkling 2 Small, and Inkling 2 Small wrote 1.2× as many output tokens for the same work.

Each model is compared at its best-ranked reasoning-effort setting. Gemini 4 Carbon (high) scores 69.5 and takes 66 s to its first answer token; Gemini 4 Carbon (medium) scores 65.8 in 20 s, Gemini 4 Carbon scores 63.0 in 7 s. Inkling 2 Small scores 57.9 and takes 64 s to its first answer token. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.

Every benchmark

91 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.

MetricPublisherGemini 4 Carbon (high)Inkling 2 Small
BenchLeader IndexBenchLeader69.557.9
Agents & tools scoreBenchLeader75.861.1
Coding scoreBenchLeader74.160.3
Human preference scoreBenchLeader72.658.6
Knowledge scoreBenchLeader76.153.5
Long context scoreBenchLeader64.366.4
Maths scoreBenchLeader71.9–
Reasoning scoreBenchLeader73.252.8
Multimodal scoreBenchLeader–64.0
Blended price $/MBenchLeader$4.00$0.475
Output speedBenchLeader72 tok/s90 tok/s
Time to first answerBenchLeader66.3 s63.9 s
Context windowBenchLeader1,048,576 tokens1,048,576 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub96.5%–
SimpleBenchSimpleBench92.6%†–
Arena Hard PromptsArena (LMArena)15471438
LiveBench 2.0 ReasoningLiveBench90.6%†–
Humanity's Last Exam (AA)Artificial Analysis–44.1%
HLE-Diamond (AA)Artificial Analysis69.1%28.7%
ARC-AGI-1ARC Prize97.5%96.5%†
ARC-AGI-2ARC Prize92.1%81.7%†
ARC-AGI-3ARC Prize96.9%–
CritPt v2 hard subset (AA)Artificial Analysis69.0%35.0%
MysteryMechanismVals AI–25.2%
Chess PuzzlesEpoch AI Benchmarking Hub78.0%–
Mystery Game PuzzlesEpoch AI Benchmarking Hub73.0%–
Coding
SciCodeSciCode64.2%52.3%
Arena CodingArena (LMArena)15681485
Arena WebDevArena (LMArena)17681647
LiveBench 2.0 CodingLiveBench91.0%†–
SciCode (AA)Artificial Analysis–52.3%
ProgramBenchVals AI–0.5%
SWE-bench MultimodalVals AI–43.1%
Vibe Code Bench v1.1Vals AI89.1%81.5%
CursorBenchCursor60.4%–
FrontierSWEEpoch AI Benchmarking Hub61.2%–
Terminal-Bench 4.0 (AA)Artificial Analysis65.2%13.1%
Terminal-Bench 2.1 (AA)Artificial Analysis–81.3%
Show all 91 benchmarks
MetricPublisherGemini 4 Carbon (high)Inkling 2 Small
Coding
Design Arena WebsiteDesign Arena1324†1335
FrontierCode 2.0 (AA)Artificial Analysis40.6%25.4%
Agents & tools
Terminal-BenchTerminal-Bench–13.0%†
APEX-AgentsMercor84.2%†46.8%
Arena AgentArena (LMArena)172.5
LiveBench Long AgenticLiveBench72.7%†–
LiveBench BrowserLiveBench80.0%†–
MCP AtlasScale AI SEAL–85.4%
HiL-BenchScale AI SEAL50.3%†–
GDPval-AA v2.1Artificial Analysis17331630
τ³-Banking (AA)Artificial Analysis–40.4%
Analyst Agent (AA)Artificial Analysis–51.3%
CyberBenchVals AI–72.7%
Finance Agent v2.1Vals AI67.2%67.5%
Harvey's Legal Agent Benchmark v1.1Vals AI17.5%21.7%
Legal Research BenchVals AI55.8%46.6%
SREBenchVals AI–1.9%
Tax Agent BenchVals AI51.8%38.9%
Terminal-Bench 4.0 (Vals)Vals AI63.1%12.6%
Terminal-Bench ScienceVals AI–2.9%
Vending-Bench 2Andon Labs16484.2†–
AutomationBenchArtificial Analysis77.8%45.6%
GDP.pdf (AA)Artificial Analysis28.4%25.2%
EnterpriseOps-GymArtificial Analysis–46.8%
AA-Briefcase v1.1Artificial Analysis16111527
GDPxGDPx by SemiAnalysis10.9%–
Design Arena AgenticDesign Arena1298†1374
Terminal-Bench-Science 0.1 (AA)Artificial Analysis64.8%5.7%
FACTS SearchGoogle94.4%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub90.5%–
FrontierMath Tier 4Epoch AI Benchmarking Hub95.1%–
OTIS Mock AIMEEpoch AI Benchmarking Hub100.0%–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub77.7%–
LiveBench 2.0 Data AnalysisLiveBench86.5%†–
LiveBench ResearchLiveBench92.5%†–
AA-Omniscience v1.1Artificial Analysis53.516.1
PRBench LegalScale AI SEAL53.4%†–
BioMysteryBenchVals AI–70.0%
Excel Modeling Benchmark v1.1Vals AI76.5%69.5%
DrugDiscoveryBenchScale AI SEAL71.5%–
EBR-benchEpoch AI Benchmarking Hub87.6%–
AA-Omniscience v1.1: accuracyArtificial Analysis58.3%33.8%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis88.6%73.3%
Instruction following
Arena Instruction FollowingArena (LMArena)15251410
Human preference
Arena TextArena (LMArena)15261412
Arena Creative WritingArena (LMArena)15161345
Arena Multi-turnArena (LMArena)15641415
Arena Longer QueriesArena (LMArena)15381410
Multimodal
LiveBench DesignLiveBench80.2%†–
MMMU-ProArtificial Analysis89.3%†81.6%
SAGEVals AI–88.6%
Blueprint-Bench 2Epoch AI Benchmarking Hub58.6%†–
Code2Video-AAArtificial Analysis–1020
AA-3DArtificial Analysis–1027
Long context
AA-LCR v1.1Artificial Analysis79.3%83.3%
MLCRArtificial Analysis19.4%20.6%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub169.8†–
LiveBench 2.0LiveBench83.5%†–
AA Intelligence Index v5.0Artificial Analysis60.030.6
AA Progress Index v1Artificial Analysis350.8–
Vals IndexVals AI70.556.1
Vals Finance IndexVals AI67.0%61.5%
Vals RSI IndexVals AI27.7%–
Vals Science IndexVals AI–32.7%
Safety & honesty
FORTRESSScale AI SEAL16.4%†16.2%
Metadata
AA Openness IndexArtificial Analysis–38.9

Data as of 2026-11-13. Best configuration of each model; every score links to its source on the model pages.

What changed

  • Inkling 2 Small: BenchLeader Index 58.4 → 57.9.
  • Inkling 2 Small: 2 new results (FORTRESS, Design Arena Agentic).
  • Gemini 4 Carbon (high): 1 new result (DrugDiscoveryBench); input price moved from $4.00/M to $2.00/M (50% down); output price moved from $20.00/M to $10.00/M (50% down); cost per task moved from $7.76/M to $5.48/M (29% down).
  • Inkling 2 Small: 2 new results (MysteryMechanism, Vals Science Index); 1 score revision.
  • Gemini 4 Carbon (high): BenchLeader Index 68.5 → 69.9.
  • Gemini 4 Carbon (high): 13 new results (GPQA Diamond, FrontierMath Tiers 1–3, FrontierMath Tier 4…).
  • Gemini 4 Carbon (high): 2 new results (FrontierSWE, Vals RSI Index).
  • Inkling 2 Small: 3 new results (SciCode, APEX-Agents, MLCR).
  • Gemini 4 Carbon (high): BenchLeader Index 69.3 → 68.5.
  • Inkling 2 Small: 8 new results (Arena Text, Arena Hard Prompts, Arena Coding…); 2 score revisions.

Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs

Gemini 4 Carbon vs Inkling 2 Small: questions

Is Gemini 4 Carbon better than Inkling 2 Small?
Gemini 4 Carbon (high) leads on quality: 69.5 vs 57.9. The BenchLeader Index combines every independent quality benchmark; Gemini 4 Carbon (high) is ahead overall as of 13 Nov 2026, but check the category scores for your use.
Gemini 4 Carbon vs Inkling 2 Small: which is cheaper, and will that change?
Inkling 2 Small is cheaper today: $0.475 against $4.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Gemini 4 Carbon or Inkling 2 Small better for coding?
Gemini 4 Carbon scores higher in coding (74 vs 60 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1768 for Gemini 4 Carbon against 1647 for Inkling 2 Small.
Which is faster, Gemini 4 Carbon or Inkling 2 Small?
Inkling 2 Small streams ~2× faster (90 vs 72 output tokens per second, Artificial Analysis 7-day median).
Is Gemini 4 Carbon or Inkling 2 Small better for agents and tool use?
Gemini 4 Carbon scores higher in agentic tasks (76 vs 61 on the category index, where 50 is average). On Arena Agent, the top shared agents & tools benchmark, it is 17 for Gemini 4 Carbon against 2.5 for Inkling 2 Small.
More questions (4)
Which is better for long documents?
Inkling 2 Small scores higher on long-context benchmarks (66 vs 64). Both accept 1,048,576 tokens of context.
Which has lower latency?
Inkling 2 Small answers first: 63.9 s against 66.3 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
Do independent benchmarks agree on Gemini 4 Carbon vs Inkling 2 Small?
Across the 31 benchmarks both have, Gemini 4 Carbon leads 27, Inkling 2 Small leads 4. Every overall index that rates both puts Gemini 4 Carbon ahead.
When was Inkling 2 Small released?
Inkling 2 Small was released on 5 Nov 2026.