BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases12

Claude Fable 5.2 vs Gemini 3.8 Flash

Full profiles: Claude Fable 5.2 (Anthropic) and Gemini 3.8 Flash (Google): every benchmark, price and rank.

Updated · Data from 12 sources

As of 9 Nov 2026, Claude Fable 5.2 is ahead of Gemini 3.8 Flash on quality (69.4 vs 61.8 on the BenchLeader Index), but Gemini 3.8 Flash is 11× cheaper at $1.50 vs $16.00 per 1M tokens blended. Claude Fable 5.2 leads in every category we measure both in. Gemini 3.8 Flash's current price runs until 31 Dec 2026, then $3.00.

Key facts (as of 9 Nov 2026)

  • Claude Fable 5.2 scores 69.4 on the BenchLeader Index and Gemini 3.8 Flash scores 61.8 (BenchLeader, 9 Nov 2026).
  • Claude Fable 5.2 costs $16.00 per 1M tokens blended (list price, 9 Nov 2026).
  • Gemini 3.8 Flash costs $1.50 per 1M tokens blended until 31 Dec 2026, then $3.00 (https://ai.google.dev/gemini-api/docs/pricing, checked 20 Oct 2026).
  • Gemini 3.8 Flash streams ~1.5× faster than Claude Fable 5.2 (Artificial Analysis, 7-day median, 9 Nov 2026).
  • Of the 23 benchmarks both models have, Claude Fable 5.2 leads 21 (BenchLeader, 9 Nov 2026).
Claude Fable 5.2 benchmarks max Anthropic Gemini 3.8 Flash 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 60 category score; FrontierCode 2.0 (AA) 48.8% vs 18.7%High
ReasoningClaude Fable 5.278 vs 63 category score; HLE-Diamond (AA) 80.2% vs 33.1%High
KnowledgeClaude Fable 5.282 vs 64 category score; AA-Omniscience v1.1 66.8 vs 23.3High
Long documentsClaude Fable 5.266 vs 65 category score; AA-LCR v1.1 83.3% vs 81.3%Medium
Chat quality (human preference)–Only Gemini 3.8 Flash has an Arena rating (69 category score)Not comparable
Lowest costGemini 3.8 Flash$1.50 vs $16.00 per 1M blended; agentic coding session $0.060 vs $0.640; from 1 Jan 2027: $3.00 vs $16.00–
Fastest first answerClaude Fable 5.23.0 s (Claude Fable 5.2 (max)) vs 17.5 s (Gemini 3.8 Flash (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) leads on quality: 69.4 vs 61.8.
  • Claude Fable 5.2 (max) is stronger in coding, knowledge, long context, reasoning.
  • Gemini 3.8 Flash (high) is stronger in agents & tools, human preference, maths, multimodal.
  • Gemini 3.8 Flash (high) is 11× cheaper ($1.50 vs $16.00 per 1M blended) until 31 Dec 2026, then $3.00 vs $16.00 from 1 Jan 2027.
  • Gemini 3.8 Flash (high) streams 1.6× faster (112 vs 72 tokens per second).

At a glance

SpecClaude Fable 5.2Gemini 3.8 Flash
DeveloperAnthropicGoogle
Released9 Nov 20262 Sep 2026
Context window (tokens)1,000,0001,048,576
Compared atClaude Fable 5.2 (max)Gemini 3.8 Flash (high)
Open weightsNoNo
Price in / out / cached input per 1M$8.00 / $40.00 / $0.200$0.750 / $3.75 / $0.075
Announced price changeNone announced$1.50 / $7.50 from 1 Jan 2027

Limits, availability and announced prices from the vendors' own pages: ai.google.dev pricing (checked 20 Oct 2026). Everything else is from the day's data.

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 3.8 Flash (high)Leader
Reasoning78.463.2Claude Fable 5.2
Coding80.260.2Claude Fable 5.2
Agents & tools–51.0not comparable
Maths–61.9not comparable
Knowledge81.764.3Claude Fable 5.2
Human preference–69.2not comparable
Multimodal–67.5not comparable
Long context66.465.4Claude 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 3.8 Flash, Reasoning: 63.2Gemini 3.8 Flash, Coding: 60.2Gemini 3.8 Flash, Knowledge: 64.3Gemini 3.8 Flash, Long context: 65.4

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

ModelIndex

Where sources disagree

Across the 23 benchmarks both have, Claude Fable 5.2 leads 21, Gemini 3.8 Flash leads 2. Every overall index that rates both puts Claude Fable 5.2 ahead.

Overall indexClaude Fable 5.2 (max)Gemini 3.8 Flash (high)Leader
BenchLeader Index69.461.8Claude Fable 5.2
AA Intelligence Index v5.064.630.9Claude Fable 5.2
Vals Index71.3†56.0Claude 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 3.8 Flash (high)
Blended price per 1M tokens, until 31 Dec 2026$16.00$1.50
Input / output per 1M$8.00 / $40.00$0.750 / $3.75
Blended price per 1M from 1 Jan 2027$16.00$3.00
Input / output per 1M from 1 Jan 2027$8.00 / $40.00$1.50 / $7.50
Cached input per 1M$0.200$0.075
Price per task: chat reply$0.015$0.0014
Price per task: summarize a 30-page report$0.120$0.011
Price per task: code edit$0.108$0.010
Price per task: agentic coding session$0.640$0.060
Price per task: structured extraction$0.024$0.0023
Agentic coding session, input mostly cached$0.289$0.030
Cost per benchmark task (AA Index)$26.54$7.77
Output tokens per task (AA Index)274k99k
Of which reasoning193k60k
Time per task (AA Index)–15 min
Output speed72 tok/s112 tok/s
Time to first answer3.0 s17.5 s
Time to a complete answer–52.0 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 $7.77 on Gemini 3.8 Flash (high), and Claude Fable 5.2 (max) wrote 2.8× 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 3.8 Flash (high) scores 61.8 and takes 18 s to its first answer token; Gemini 3.8 Flash (medium) scores 60.3 in 11 s, Gemini 3.8 Flash (low) scores 55.9 in 4 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

149 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 3.8 Flash (high)
BenchLeader IndexBenchLeader69.461.8
Coding scoreBenchLeader80.260.2
Knowledge scoreBenchLeader81.764.3
Long context scoreBenchLeader66.465.4
Reasoning scoreBenchLeader78.463.2
Agents & tools scoreBenchLeader–51.0
Human preference scoreBenchLeader–69.2
Maths scoreBenchLeader–61.9
Multimodal scoreBenchLeader–67.5
Blended price $/MBenchLeader$16.00$1.50
Output speedBenchLeader72 tok/s112 tok/s
Time to first answerBenchLeader3.0 s17.5 s
Context windowBenchLeader1,000,000 tokens1,048,576 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub–95.4%
Humanity's Last ExamScale AI / CAIS–44.5%†
Arena Hard PromptsArena (LMArena)–1519
LiveBench 2.0 ReasoningLiveBench88.8%†89.3%†
LiveBench 1.0 ReasoningLiveBench–89.3%
GPQA Diamond (AA)Artificial Analysis–95.3%
Humanity's Last Exam (AA)Artificial Analysis74.3%47.8%
HLE-Diamond (AA)Artificial Analysis80.2%33.1%
GPQA Diamond (Vals)Vals AI–94.4%
ARC-AGI-1ARC Prize97.5%98.5%
ARC-AGI-2ARC Prize92.5%89.2%
ARC-AGI-3ARC Prize94.9%35.0%
CritPtArtificial Analysis35.4%18.3%
CritPt v2 hard subset (AA)Artificial Analysis76.5%46.5%
MysteryMechanismVals AI51.8%†36.5%
Chess PuzzlesEpoch AI Benchmarking Hub–58.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub–47.0%
LMCAEpoch AI Benchmarking Hub–51.5%†
DTBenchEpoch AI Benchmarking Hub–95.7%†
Coding
SciCodeSciCode–56.6%
WeirdMLWeirdML–84.8%
FrontierCodeCognition–41.2%†
Arena CodingArena (LMArena)–1530
Arena WebDevArena (LMArena)–1584
LiveBench 2.0 CodingLiveBench79.2%†65.7%†
Show all 149 benchmarks
MetricPublisherClaude Fable 5.2 (max)Gemini 3.8 Flash (high)
Coding
LiveBench 1.0 CodingLiveBench–72.5%
SciCode (AA)Artificial Analysis67.7%56.6%
LiveCodeBenchVals AI–89.5%
IOIVals AI–56.9%
SWE-bench (Vals)Vals AI–80.0%
Code MigrationVals AI–36.5%
Code Migration v1.1Vals AI83.3%†38.6%
ProgramBenchVals AI19.0%†1.0%
SWE-bench MultimodalVals AI62.3%†40.8%
Vibe Code Bench 1-100Vals AI–18.8%
Vibe Code Bench v1.1Vals AI93.8%†78.7%
SWE Atlas: Codebase QnAScale AI SEAL–47.0%†
SWE Atlas: RefactoringScale AI SEAL–44.8%†
SWE Atlas: Test WritingScale AI SEAL–53.7%†
Surface Evolver BenchEpoch AI Benchmarking Hub–76.9%
DeepSWE v1.1Epoch AI Benchmarking Hub–73.8%
CursorBenchCursor–39.6%
ALE-BenchEpoch AI Benchmarking Hub–1269.7
FrontierSWEEpoch AI Benchmarking Hub–19.6%
Terminal-Bench 4.0 (AA)Artificial Analysis59.6%19.7%
Terminal-Bench 2.1 (AA)Artificial Analysis–87.6%
Startrise FrontendStartrise–64.6%†
GameBench 2 OverallDuelLab GameBench 2–59.0†
GameBench 2 by reasoning settingDuelLab GameBench 2–64.2
Design Arena WebsiteDesign Arena–1297†
FrontierCode 1.1 (AA)Artificial Analysis56.2%36.4%
FrontierCode 2.0 (AA)Artificial Analysis48.8%18.7%
Agents & tools
Terminal-BenchTerminal-Bench–18.2%
Remote Labor IndexScale AI / CAIS–5.8%†
APEX-AgentsMercor–64.3%†
Arena AgentArena (LMArena)–2.4
LiveBench Long AgenticLiveBench82.9%†16.5%†
LiveBench BrowserLiveBench86.9%†45.1%†
LiveBench Agentic CodingLiveBench–54.2%
Terminal-Bench 2.1 (Vals)Vals AI–81.3%
HiL-BenchScale AI SEAL–41.5%†
GDPval-AA v2.1, normalised scoreArtificial Analysis–46.8%
GDPval-AA v2.1Artificial Analysis18311445
τ³-Banking (AA)Artificial Analysis–45.0%
ITBench SRE (AA)Artificial Analysis–52.5%
Analyst Agent (AA)Artificial Analysis–46.3%
CUA-benchVals AI–4.2%
CyberBenchVals AI–43.8%
Finance Agent v2Vals AI–61.4%
Finance Agent v2.1Vals AI69.5%†65.8%
Harvey's Legal Agent Benchmark v1.1Vals AI5.0%†12.1%
Harvey's Legal Agent Benchmark v1Vals AI–10.0%
Legal Research BenchVals AI46.1%†38.9%
SkillsBenchVals AI–58.0%
SREBenchVals AI–11.1%
Tax Agent BenchVals AI32.1%†32.1%
Terminal-Bench 4.0 (Vals)Vals AI65.2%†19.7%
Terminal-Bench ScienceVals AI55.7%†8.6%
Time Horizon Index: KSPVals AI–18.8%
Vending-Bench 2Andon Labs–5093.8†
AutomationBenchArtificial Analysis76.4%59.9%
GDP.pdf (AA)Artificial Analysis24.2%21.0%
Harvey LAB-AA v1.1Harvey7.2%0.0%
AA-Briefcase v1.1Artificial Analysis17851203
Design Arena AgenticDesign Arena–1220†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis73.3%10.0%
CWE-Bench (AA)Artificial Analysis–52.5%
DeepSec-Bench (AA)Artificial Analysis–14.5%
CyberGym end-to-end (AA)Artificial Analysis–8.4%
FACTS SearchGoogle–80.4%†
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub–68.4%
FrontierMath Tier 4Epoch AI Benchmarking Hub–21.9%
OTIS Mock AIMEEpoch AI Benchmarking Hub–98.9%
ProofBenchVals AI–48.0%†
LiveBench MathematicsLiveBench–91.6%
Arena MathsArena (LMArena)–1519
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub–69.7%
LiveBench 2.0 Data AnalysisLiveBench81.5%†54.0%†
LiveBench ResearchLiveBench94.5%†79.4%†
LiveBench 1.0 Data AnalysisLiveBench–54.0%
AA-Omniscience v1.1Artificial Analysis66.823.3
MMLU-ProVals AI–90.2%
LegalBenchVals AI–87.0%
TaxEvalVals AI–74.5%
PRBench FinanceScale AI SEAL–49.5%†
PRBench LegalScale AI SEAL–48.9%†
BioMysteryBenchVals AI83.7%†62.2%
Excel Modeling BenchmarkVals AI–72.2%
Excel Modeling Benchmark v1.1Vals AI77.4%†72.9%
MedCodeVals AI–48.1%
MedScribeVals AI–84.5%
Public Benefits Bench v1.1Vals AI–65.3%
GDP.pdfEpoch AI Benchmarking Hub–23.2%
AA-Omniscience v1.1: accuracyArtificial Analysis79.1%50.5%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis40.7%44.9%
HealthBench Professional (AA)OpenAI67.7%51.7%
Instruction following
LiveBench LanguageLiveBench–87.8%
LiveBench Instruction FollowingLiveBench–81.4%
Arena Instruction FollowingArena (LMArena)–1492
Human preference
Arena TextArena (LMArena)–1498
Arena Creative WritingArena (LMArena)–1489
Arena Multi-turnArena (LMArena)–1505
Arena Longer QueriesArena (LMArena)–1512
Multimodal
Arena VisionArena (LMArena)–1317
LiveBench DesignLiveBench85.1%†69.7%†
MMMU-ProArtificial Analysis–85.6%
MMMU-Pro (Vals)Vals AI–89.1%
MortgageTaxVals AI–65.3%
SAGEVals AI–88.2%
AudioMCScale AI SEAL–60.4%
AudioMC (text output)Scale AI SEAL–60.4%
Blueprint-Bench 2Epoch AI Benchmarking Hub–38.6%†
Code2Video-AAArtificial Analysis–899
AA-3DArtificial Analysis1271974
Long context
AA-LCR v1.1Artificial Analysis83.3%81.3%
Arena DocumentArena (LMArena)–1469
MLCRArtificial Analysis–10.6%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub–158.6†
LiveBench 2.0LiveBench84.9%†56.0%†
LiveBench 1.0LiveBench–75.8%
AA Intelligence Index v5.0Artificial Analysis64.630.9
AA Intelligence Index v4.3.2Artificial Analysis–40.9
AA Progress Index v1Artificial Analysis–320.3
Vals IndexVals AI71.3†56.0
Vals Finance IndexVals AI63.6%†60.5%
Vals RSI IndexVals AI–19.9%
Vals Science IndexVals AI63.7%†35.8%
Vals Router IndexVals AI–56.0%†
AA Cyber IndexArtificial Analysis–25.1

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

DuelLab GameBench 2, release gb2-20261103-eaea31df94e6 (https://benchmarks.duellab.org/releases/gb2-20261103-eaea31df94e6/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • Gemini 3.8 Flash: list price moves to $1.50 / $7.50 per 1M input / output tokens (announced).
  • Gemini 3.8 Flash (high): 2 score revisions.
  • Gemini 3.8 Flash (high): 1 new result (Arena Document); 1 score revision.
  • Gemini 3.8 Flash (high): 2 score revisions.
  • Gemini 3.8 Flash (high): 1 new result (MirrorCode).
  • Gemini 3.8 Flash (high): 1 score revision.
  • Gemini 3.8 Flash (high): BenchLeader Index 63.3 → 61.8.
  • Gemini 3.8 Flash (high): 5 new results (AA Intelligence Index v5.0, AA Progress Index v1, HLE-Diamond (AA)…); 3 score revisions; cost per task moved from $3.49/M to $7.77/M (123% up).
  • Gemini 3.8 Flash (high): cost per task moved from $1.24/M to $3.49/M (180% up).
  • Gemini 3.8 Flash (high): 8 new results (Code Migration v1.1, Excel Modeling Benchmark v1.1, Finance Agent v2.1…).

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

Claude Fable 5.2 vs Gemini 3.8 Flash: questions

Is Claude Fable 5.2 better than Gemini 3.8 Flash?
Claude Fable 5.2 (max) leads on quality: 69.4 vs 61.8. The BenchLeader Index combines every independent quality benchmark; Claude Fable 5.2 (max) is ahead overall as of 9 Nov 2026, but check the category scores for your use.
Claude Fable 5.2 vs Gemini 3.8 Flash: which is cheaper, and will that change?
Gemini 3.8 Flash is cheaper today: $1.50 against $16.00 per million tokens, blended at three input tokens per output token. Gemini 3.8 Flash's current price runs until 31 Dec 2026, then $3.00.
Is Claude Fable 5.2 or Gemini 3.8 Flash better for coding?
Claude Fable 5.2 scores higher in coding (80 vs 60 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 18.7% for Gemini 3.8 Flash.
Which is faster, Claude Fable 5.2 or Gemini 3.8 Flash?
Gemini 3.8 Flash streams ~1.5× faster (112 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 65). Both take about 1M tokens: Claude Fable 5.2 1,000,000, Gemini 3.8 Flash 1,048,576.
More questions (3)
Which has lower latency?
Claude Fable 5.2 answers first: 3.0 s against 17.5 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 3.8 Flash?
Across the 23 benchmarks both have, Claude Fable 5.2 leads 21, Gemini 3.8 Flash leads 2. 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.