Skip to main content

Model comparison

Claude Fable 5 vs Gemini 3.1 Pro

Data verified

Head-to-head evidence from 4 shared benchmark results across 3 categories. Overall scores shown here use BenchLM's provisional ranking lane.

91/100
Margin
3.0pts
← winning
88/100
2 category wins0 category wins

Verified leaderboard positions: Claude Fable 5 #2; Gemini 3.1 Pro unranked

Evidence parity. Claude Fable 5 and Gemini 3.1 Pro share 4 comparable benchmark results. 2 of 8 categories are comparable. 16 results are unique to Claude Fable 5; 44 to Gemini 3.1 Pro.

Updated July 13, 2026
Shared results
4
Claude Fable 5 only
16
Gemini 3.1 Pro only
44
Comparable categories
2 / 8

Pick Claude Fable 5 if you want the stronger benchmark profile. Gemini 3.1 Pro only becomes the better choice if you want the cheaper token bill or you would rather avoid the extra latency and token burn of a reasoning model.

Confidence note. This is a partial-evidence comparison with 4 shared benchmark results across 3 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Claude Fable 5 has the cleaner provisional overall profile here, landing at 91 versus 88. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

Claude Fable 5's sharpest advantage is in mathematics, where it averages 97.6 against 31.8. The single biggest benchmark swing on the page is CharXiv, 93.2% to 80.2%.

Claude Fable 5 is also the more expensive model on tokens at $10.00 input / $50.00 output per 1M tokens, versus $2.00 input / $12.00 output per 1M tokens for Gemini 3.1 Pro. That is roughly 4.2x on output cost alone. Claude Fable 5 is the reasoning model in the pair, while Gemini 3.1 Pro is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Claude Fable 5 gives you the larger context window at 1M+, compared with 1M for Gemini 3.1 Pro.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Claude Fable 5 and Gemini 3.1 Pro
CategoryClaude Fable 5ΔGemini 3.1 Pro
MathClaude Fable 597.6Margin 65.8Gemini 3.1 Pro31.8
MultimodalClaude Fable 592.9Margin 10.3Gemini 3.1 Pro82.6
AgenticClaude Fable 585.3MarginNo overlapGemini 3.1 ProNot measured
CodingClaude Fable 585.6MarginNo overlapGemini 3.1 ProNot measured
ReasoningClaude Fable 5Not measuredMarginNo overlapGemini 3.1 Pro77.1
KnowledgeClaude Fable 568.6MarginNo overlapGemini 3.1 ProNot measured

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · Claude Fable 5B · Gemini 3.1 Pro
  1. CharXiv

    Multimodal
    Source ↗
    A 93.2%B 80.2%
    Winner: Claude Fable 5Δ 13
    CharXiv: Claude Fable 5 scored 93.2%; Gemini 3.1 Pro scored 80.2%. Claude Fable 5 wins this benchmark.
  2. MMMU-Pro

    Multimodal
    Source ↗
    A 92.7%B 83.9%
    Winner: Claude Fable 5Δ 8.8
    MMMU-Pro: Claude Fable 5 scored 92.7%; Gemini 3.1 Pro scored 83.9%. Claude Fable 5 wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricClaude Fable 5Gemini 3.1 ProComparison
Input / output priceUSD per 1M tokensClaude Fable 5$10 input / $50 outputGemini 3.1 Pro$2 input / $12 outputGemini 3.1 Pro has the lower combined listed price.
Generation speedtokens per secondClaude Fable 5Not availableGemini 3.1 Pro109 tok/sA complete speed comparison is not available.
First-answer latencyseconds to first tokenClaude Fable 5Not availableGemini 3.1 Pro29.71 sA complete latency comparison is not available.
Context windowmaximum listed tokensClaude Fable 51M+Gemini 3.1 Pro1MListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkClaude Fable 5Gemini 3.1 ProResult
Terminal-Bench 2.0Source 84.3%Not comparable
OSWorld-VerifiedSource 85%Not comparable
BrowseCompSource 86.9%Not comparable
GDPval-AASource 1760962Claude Fable 5 leads
Claw-EvalSource 57.8%Not comparable
DeepSearchQASource 69.7%Not comparable
Tau2-TelecomSource 95.6%Not comparable
AA Agentic IndexSource 21.4%Not comparable
APEX-Agents-AASource 32.0%Not comparable
GDPval-AASource 23.1%Not comparable
Gert LabsSource 56.87%Not comparable
ResearchClawBenchSource 13.3%Not comparable
AA AutomationBenchSource 37.5%Not comparable
AA EnterpriseOps-GymSource 42.2%Not comparable
AA Harvey LABSource 0.0%Not comparable
AA ITBenchSource 30.3%Not comparable
AA Tau3 BankingSource 16.5%Not comparable
Coding
BenchmarkClaude Fable 5Gemini 3.1 ProResult
SWE-bench VerifiedSource 95%Not comparable
SWE-bench ProSource 80%Not comparable
FrontierCodeSource 53.5%Not comparable
Terminal-Bench 2.0Source 84.3%Not comparable
cursorBench31Source 70.6%Not comparable
cursorBench32Source 70.5%Not comparable
LiveCodeBench ProSource 82.9%Not comparable
React Native EvalsSource 78.9%Not comparable
Vibe Code BenchSource 32.03%Not comparable
AA Coding IndexSource 68.8%Not comparable
Terminal-Bench HardSource 53.8%Not comparable
AA-SciCodeSource 58.9%Not comparable
AA Terminal-Bench 2.1Source 73.8%Not comparable
Reasoning
BenchmarkClaude Fable 5Gemini 3.1 ProResult
ARC-AGI-2Source 77.1%Not comparable
AA-LCRSource 72.7%Not comparable
CritPtSource 17.7%Not comparable
Knowledge
BenchmarkClaude Fable 5Gemini 3.1 ProResult
GPQASource 94.5%Not comparable
HLESource 64.5%Not comparable
HLE w/o toolsSource 59%45.4%Claude Fable 5 leads
GPQA-DSource 94.3%Not comparable
HealthBench HardSource 20.6%Not comparable
MedXpertQA (Text)Source 71.5%Not comparable
Artificial Analysis Intelligence IndexSource 46.5%Not comparable
AA-GPQA DiamondSource 94.1%Not comparable
AA-HLESource 44.7%Not comparable
AA-Omniscience IndexSource 32.9%Not comparable
AA-Omniscience AccuracySource 55.3%Not comparable
AA-Omniscience Hallucination RateSource 49.9%Not comparable
MathClaude Fable 5 wins
BenchmarkClaude Fable 5Gemini 3.1 ProResult
USAMO 2026Source 97.6%Not comparable
FrontierMath v2 (Tiers 1-3)Source 36.900%Not comparable
FrontierMath v2 (Tier 4)Source 16.700%Not comparable
Multilingual
BenchmarkClaude Fable 5Gemini 3.1 ProResult
SWE MultilingualSource 87.3%Not comparable
AA Global-MMLU-LiteSource 93.2%Not comparable
MultimodalClaude Fable 5 wins
BenchmarkClaude Fable 5Gemini 3.1 ProResult
MMMU-ProSource 92.7%83.9%Claude Fable 5 leads
SWE-bench MultimodalSource 59%Not comparable
CharXivSource 93.2%80.2%Claude Fable 5 leads
CharXiv w/o toolsSource 86.1%Not comparable
Blueprint-Bench 2Source 38.6%Not comparable
ERQASource 69.4%Not comparable
SimpleVQASource 72.4%Not comparable
ScreenSpot ProSource 84.4%Not comparable
ZeroBenchSource 29.0%Not comparable
MedXpertQA (MM)Source 81.3%Not comparable
GDPval-AASource 1320Not comparable
AA-MMMU-ProSource 82.4%Not comparable
Design Arena WebsiteSource 1294Not comparable
Inst. Following
BenchmarkClaude Fable 5Gemini 3.1 ProResult
AA-IFBenchSource 77.1%Not comparable
Frequently Asked Questions (3)

Which is better, Claude Fable 5 or Gemini 3.1 Pro?

Claude Fable 5 is ahead on BenchLM's provisional leaderboard, 91 to 88. The biggest single separator in this matchup is CharXiv, where the scores are 93.2% and 80.2%.

Which is better for math, Claude Fable 5 or Gemini 3.1 Pro?

Claude Fable 5 has the edge for math in this comparison, averaging 97.6 versus 31.8. Gemini 3.1 Pro stays close enough that the answer can still flip depending on your workload.

Which is better for multimodal and grounded tasks, Claude Fable 5 or Gemini 3.1 Pro?

Claude Fable 5 has the edge for multimodal and grounded tasks in this comparison, averaging 92.9 versus 82.6. Inside this category, CharXiv is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 13, 2026

The AI models change fast. We track them for you.

A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.