BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases12

Claude Fable 5.2 vs Gemini 4 Carbon

Full profiles: Claude Fable 5.2 (Anthropic) and Gemini 4 Carbon (Google): every benchmark, price and rank.

Updated · Data from 8 sources

As of 9 Nov 2026, Claude Fable 5.2 and Gemini 4 Carbon are neck and neck on quality (69.4 vs 68.5 on the BenchLeader Index, inside the ±6.5 margin), and Gemini 4 Carbon is 2.0× cheaper at $8.00 vs $16.00 per 1M tokens blended. Claude Fable 5.2 leads in every category we measure both in.

Key facts (as of 9 Nov 2026)

  • Claude Fable 5.2 scores 69.4 on the BenchLeader Index and Gemini 4 Carbon scores 68.5 (BenchLeader, 9 Nov 2026).
  • Claude Fable 5.2 costs $16.00 per 1M tokens blended (list price, 9 Nov 2026).
  • Gemini 4 Carbon costs $8.00 per 1M tokens blended (list price, 9 Nov 2026).
  • Of the 13 benchmarks both models have, Claude Fable 5.2 leads 9 (BenchLeader, 9 Nov 2026).
Claude Fable 5.2 benchmarks max Anthropic Gemini 4 Carbon benchmarks high GoogleAdd 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
CodingClaude Fable 5.280 vs 75 category score; FrontierCode 2.0 (AA) 48.8% vs 40.6%Medium
ReasoningClaude Fable 5.278 vs 77 category score; HLE-Diamond (AA) 80.2% vs 69.1%Medium
KnowledgeClaude Fable 5.282 vs 74 category score; AA-Omniscience v1.1 66.8 vs 53.5Medium
Long documentsClaude Fable 5.266 vs 64 category score; AA-LCR v1.1 83.3% vs 79.3%Medium
Chat quality (human preference)–Only Gemini 4 Carbon has an Arena rating (73 category score)Not comparable
Lowest costGemini 4 Carbon$8.00 vs $16.00 per 1M blended; agentic coding session $0.320 vs $0.640–
Fastest first answerClaude Fable 5.23.0 s (Claude Fable 5.2 (max)) vs 69.4 s (Gemini 4 Carbon (high)) 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

  • Claude Fable 5.2 (max) and Gemini 4 Carbon (high) are neck and neck on quality (69.4 vs 68.5, within the ±6.5 margin).
  • Claude Fable 5.2 (max) is stronger in coding, knowledge, long context, reasoning.
  • Gemini 4 Carbon (high) is stronger in agents & tools, human preference.
  • Gemini 4 Carbon (high) is 2.0× cheaper ($8.00 vs $16.00 per 1M blended).

At a glance

SpecClaude Fable 5.2Gemini 4 Carbon
DeveloperAnthropicGoogle
Released9 Nov 202628 Oct 2026
Context window (tokens)1,000,0001,000,000
Compared atClaude Fable 5.2 (max)Gemini 4 Carbon (high)
Open weightsNoNo
Price in / out / cached input per 1M$8.00 / $40.00 / $0.200$4.00 / $20.00 / –

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.

CategoryClaude Fable 5.2 (max)Gemini 4 Carbon (high)Leader
Reasoning78.476.9Claude Fable 5.2
Coding80.274.5Claude Fable 5.2
Agents & tools–78.2not comparable
Knowledge81.774.3Claude Fable 5.2
Human preference–72.8not comparable
Long context66.464.3Claude Fable 5.2

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 avg75ReasoningCodingKnowledgeLong contextClaude Fable 5.2, Reasoning: 78.4Claude Fable 5.2, Coding: 80.2Claude Fable 5.2, Knowledge: 81.7Claude Fable 5.2, Long context: 66.4Gemini 4 Carbon, Reasoning: 76.9Gemini 4 Carbon, Coding: 74.5Gemini 4 Carbon, Knowledge: 74.3Gemini 4 Carbon, Long context: 64.3

Not drawn, measured for fewer than two of these models: Agents & tools, Maths, Instruction following, Multimodal, Human preference.

ModelIndex

Where sources disagree

Across the 13 benchmarks both have, Claude Fable 5.2 leads 9, Gemini 4 Carbon leads 4. Every overall index that rates both puts Claude Fable 5.2 ahead.

Overall indexClaude Fable 5.2 (max)Gemini 4 Carbon (high)Leader
BenchLeader Index69.468.5neck and neck
AA Intelligence Index v5.064.660.0Claude Fable 5.2
Vals Index71.3†70.5Claude Fable 5.2

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.

MeasureClaude Fable 5.2 (max)Gemini 4 Carbon (high)
Blended price per 1M tokens$16.00$8.00
Input / output per 1M$8.00 / $40.00$4.00 / $20.00
Cached input per 1M$0.200–
Price per task: chat reply$0.015$0.0076
Price per task: summarize a 30-page report$0.120$0.060
Price per task: code edit$0.108$0.054
Price per task: agentic coding session$0.640$0.320
Price per task: structured extraction$0.024$0.012
Agentic coding session, input mostly cached$0.289–
Cost per benchmark task (AA Index)$26.54$7.76
Output tokens per task (AA Index)274k123k
Of which reasoning193k72k
Time per task (AA Index)–27 min
Output speed72 tok/s75 tok/s
Time to first answer3.0 s69.4 s
Time to a complete answer–160.3 s

Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $26.54 on Claude Fable 5.2 (max) and $7.76 on Gemini 4 Carbon (high), and Claude Fable 5.2 (max) wrote 2.2× as many output tokens for the same work, which a per-token price hides.

Each model is compared at its best-ranked reasoning-effort setting. Claude Fable 5.2 (max) scores 69.4 and takes 3 s to its first answer token; Claude Fable 5.2 (high) scores 68.9 in 3 s, Claude Fable 5.2 (xhigh) scores 68.7 in 3 s. Gemini 4 Carbon (high) scores 68.5 and takes 69 s to its first answer token; Gemini 4 Carbon (medium) scores 64.1 in 27 s. 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

64 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.

MetricPublisherClaude Fable 5.2 (max)Gemini 4 Carbon (high)
BenchLeader IndexBenchLeader69.468.5
Coding scoreBenchLeader80.274.5
Knowledge scoreBenchLeader81.774.3
Long context scoreBenchLeader66.464.3
Reasoning scoreBenchLeader78.476.9
Agents & tools scoreBenchLeader–78.2
Human preference scoreBenchLeader–72.8
Blended price $/MBenchLeader$16.00$8.00
Output speedBenchLeader72 tok/s75 tok/s
Time to first answerBenchLeader3.0 s69.4 s
Context windowBenchLeader1,000,000 tokens1,000,000 tokens
Reasoning
Arena Hard PromptsArena (LMArena)–1547
LiveBench 2.0 ReasoningLiveBench88.8%†–
Humanity's Last Exam (AA)Artificial Analysis74.3%–
HLE-Diamond (AA)Artificial Analysis80.2%69.1%
ARC-AGI-1ARC Prize97.5%–
ARC-AGI-2ARC Prize92.5%–
ARC-AGI-3ARC Prize94.9%–
CritPtArtificial Analysis35.4%–
CritPt v2 hard subset (AA)Artificial Analysis76.5%69.0%
MysteryMechanismVals AI51.8%†–
Coding
SciCodeSciCode–64.2%
Arena CodingArena (LMArena)–1567
Arena WebDevArena (LMArena)–1768
LiveBench 2.0 CodingLiveBench79.2%†–
SciCode (AA)Artificial Analysis67.7%–
Code Migration v1.1Vals AI83.3%†–
ProgramBenchVals AI19.0%†–
SWE-bench MultimodalVals AI62.3%†–
Vibe Code Bench v1.1Vals AI93.8%†89.1%
Terminal-Bench 4.0 (AA)Artificial Analysis59.6%65.2%
FrontierCode 1.1 (AA)Artificial Analysis56.2%–
FrontierCode 2.0 (AA)Artificial Analysis48.8%40.6%
Agents & tools
Arena AgentArena (LMArena)–16.6
LiveBench Long AgenticLiveBench82.9%†–
LiveBench BrowserLiveBench86.9%†–
Show all 64 benchmarks
MetricPublisherClaude Fable 5.2 (max)Gemini 4 Carbon (high)
Agents & tools
GDPval-AA v2.1Artificial Analysis18311733
Finance Agent v2.1Vals AI69.5%†67.2%
Harvey's Legal Agent Benchmark v1.1Vals AI5.0%†17.5%
Legal Research BenchVals AI46.1%†55.8%
Tax Agent BenchVals AI32.1%†51.8%
Terminal-Bench 4.0 (Vals)Vals AI65.2%†63.1%
Terminal-Bench ScienceVals AI55.7%†–
Vending-Bench 2Andon Labs–16484.2†
AutomationBenchArtificial Analysis76.4%77.8%
GDP.pdf (AA)Artificial Analysis24.2%28.4%
Harvey LAB-AA v1.1Harvey7.2%–
AA-Briefcase v1.1Artificial Analysis17851611
GDPxGDPx by SemiAnalysis–10.9%
Terminal-Bench-Science 0.1 (AA)Artificial Analysis73.3%64.8%
FACTS SearchGoogle–94.4%†
Knowledge
LiveBench 2.0 Data AnalysisLiveBench81.5%†–
LiveBench ResearchLiveBench94.5%†–
AA-Omniscience v1.1Artificial Analysis66.853.5
BioMysteryBenchVals AI83.7%†–
Excel Modeling Benchmark v1.1Vals AI77.4%†76.5%
AA-Omniscience v1.1: accuracyArtificial Analysis79.1%58.3%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis40.7%88.6%
HealthBench Professional (AA)OpenAI67.7%–
Instruction following
Arena Instruction FollowingArena (LMArena)–1526
Human preference
Arena TextArena (LMArena)–1527
Arena Creative WritingArena (LMArena)–1518
Arena Multi-turnArena (LMArena)–1564
Arena Longer QueriesArena (LMArena)–1539
Multimodal
LiveBench DesignLiveBench85.1%†–
MMMU-ProArtificial Analysis–89.3%†
Blueprint-Bench 2Epoch AI Benchmarking Hub–58.6%†
AA-3DArtificial Analysis1271–
Long context
AA-LCR v1.1Artificial Analysis83.3%79.3%
Composite
LiveBench 2.0LiveBench84.9%†–
AA Intelligence Index v5.0Artificial Analysis64.660.0
AA Progress Index v1Artificial Analysis–350.8
Vals IndexVals AI71.3†70.5
Vals Finance IndexVals AI63.6%†67.0%
Vals Science IndexVals AI63.7%†–

Data as of 2026-11-09. Best configuration of each model; every score links to its source on the model pages.

What changed

  • Gemini 4 Carbon (high): BenchLeader Index 69.3 → 68.5.
  • Gemini 4 Carbon (high): BenchLeader Index 68.8 → 69.3.
  • Gemini 4 Carbon (high): 1 score revision.
  • Gemini 4 Carbon (high): 2 score revisions.
  • Gemini 4 Carbon (high): 1 score revision.
  • Gemini 4 Carbon (high): 2 score revisions.
  • Gemini 4 Carbon (high): 1 score revision.

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

Claude Fable 5.2 vs Gemini 4 Carbon: questions

Is Claude Fable 5.2 better than Gemini 4 Carbon?
Claude Fable 5.2 (max) and Gemini 4 Carbon (high) are neck and neck on quality (69.4 vs 68.5, within the ±6.5 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 9 Nov 2026, so check the category scores for your use.
Claude Fable 5.2 vs Gemini 4 Carbon: which is cheaper, and will that change?
Gemini 4 Carbon is cheaper today: $8.00 against $16.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Claude Fable 5.2 or Gemini 4 Carbon better for coding?
Claude Fable 5.2 scores higher in coding (80 vs 75 on the category index, where 50 is average). On FrontierCode 2.0 (AA), the top shared coding benchmark, it is 48.8% for Claude Fable 5.2 against 40.6% for Gemini 4 Carbon.
Which is faster, Claude Fable 5.2 or Gemini 4 Carbon?
Gemini 4 Carbon streams faster (75 vs 72 output tokens per second, Artificial Analysis 7-day median).
Which is better for long documents?
Claude Fable 5.2 scores higher on long-context benchmarks (66 vs 64). Both accept 1,000,000 tokens of context.
More questions (3)
Which has lower latency?
Claude Fable 5.2 answers first: 3.0 s against 69.4 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 Claude Fable 5.2 vs Gemini 4 Carbon?
Across the 13 benchmarks both have, Claude Fable 5.2 leads 9, Gemini 4 Carbon leads 4. Every overall index that rates both puts Claude Fable 5.2 ahead.
When was Claude Fable 5.2 released?
Claude Fable 5.2 was released on 9 Nov 2026.