Skip to main content
BenchLM
Advertise

Model comparison

Claude Sonnet 4.6 vs Gemini 3.1 Pro

Data verified

Head-to-head evidence from 20 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

65.07/100
Margin
9.8pts
← winning
55.3/100
0 category wins2 category wins

Public leaderboard positions: Claude Sonnet 4.6 #32 (Supported); Gemini 3.1 Pro #83 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude Sonnet 4.6 and Gemini 3.1 Pro share 20 comparable benchmark results. 2 of 8 categories are comparable. 13 results are unique to Claude Sonnet 4.6; 27 to Gemini 3.1 Pro.

Updated July 20, 2026
Shared results
20
Claude Sonnet 4.6 only
13
Gemini 3.1 Pro only
27
Comparable categories
2 / 8

Pick Claude Sonnet 4.6 if you want the stronger benchmark profile. Gemini 3.1 Pro only becomes the better choice if mathematics is the priority or you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 20 shared benchmark results across 7 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 Sonnet 4.6 is clearly ahead on the BenchAlign aggregate, 65.07 to 55.3. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Claude Sonnet 4.6 is also the more expensive model on tokens at $3.00 input / $15.00 output per 1M tokens, versus $2.00 input / $12.00 output per 1M tokens for Gemini 3.1 Pro. Gemini 3.1 Pro gives you the larger context window at 1M, compared with 200K for Claude Sonnet 4.6.

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 Sonnet 4.6 and Gemini 3.1 Pro
CategoryClaude Sonnet 4.6ΔGemini 3.1 Pro
MathClaude Sonnet 4.626.4Margin→ 5.4Gemini 3.1 Pro31.8
MultimodalClaude Sonnet 4.677.4Margin→ 5.2Gemini 3.1 Pro82.6
AgenticClaude Sonnet 4.665.2MarginNo overlapGemini 3.1 ProNot measured
CodingClaude Sonnet 4.669.1MarginNo overlapGemini 3.1 ProNot measured
ReasoningClaude Sonnet 4.6Not measuredMarginNo overlapGemini 3.1 Pro77.1
KnowledgeClaude Sonnet 4.666.0MarginNo overlapGemini 3.1 ProNot measured

Decisive benchmark drivers

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

More
A · Claude Sonnet 4.6B · Gemini 3.1 Pro

  1. FrontierMath v2 (Tier 4)

    Math
    Source ↗
    A 8.300%B 16.700%
    Winner: Gemini 3.1 ProΔ 8.4
    FrontierMath v2 (Tier 4): Claude Sonnet 4.6 scored 8.300%; Gemini 3.1 Pro scored 16.700%. Gemini 3.1 Pro wins this benchmark.

  2. FrontierMath v2 (Tiers 1-3)

    Math
    Source ↗
    A 32.400%B 36.900%
    Winner: Gemini 3.1 ProΔ 4.5
    FrontierMath v2 (Tiers 1-3): Claude Sonnet 4.6 scored 32.400%; Gemini 3.1 Pro scored 36.900%. Gemini 3.1 Pro wins this benchmark.

  3. CharXiv

    Multimodal
    Source ↗
    A 77.4%B 80.2%
    Winner: Gemini 3.1 ProΔ 2.8
    CharXiv: Claude Sonnet 4.6 scored 77.4%; Gemini 3.1 Pro scored 80.2%. Gemini 3.1 Pro wins this benchmark.

Operational comparison

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

MetricClaude Sonnet 4.6Gemini 3.1 ProComparison
Input / output priceUSD per 1M tokensClaude Sonnet 4.6$3 input / $15 outputGemini 3.1 Pro$2 input / $12 outputGemini 3.1 Pro has the lower combined listed price.
Generation speedtokens per secondClaude Sonnet 4.644 tok/sGemini 3.1 Pro109 tok/sGemini 3.1 Pro has the higher measured throughput.
First-answer latencyseconds to first tokenClaude Sonnet 4.61.48 sGemini 3.1 Pro29.71 sClaude Sonnet 4.6 reaches the first token sooner.
Context windowmaximum listed tokensClaude Sonnet 4.6200KGemini 3.1 Pro1MGemini 3.1 Pro lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkClaude Sonnet 4.6Gemini 3.1 ProResult
Terminal-Bench 2.0Source 59.1%—Not comparable
OSWorld-VerifiedSource 72.1%—Not comparable
Claw-EvalSource 67.8%57.8%Claude Sonnet 4.6 leads
CyberGymSource 65.2%—Not comparable
τ²-bench resultsSource 79.5%95.6%Gemini 3.1 Pro leads
Gert LabsSource 62.92%56.87%Claude Sonnet 4.6 leads
OSWorld 2.0Source 8.3%—Not comparable
JobBenchSource 36.9%—Not comparable
DeepSearchQASource —69.7%Not comparable
AA Agentic IndexSource —21.4%Not comparable
APEX-Agents-AASource —32.0%Not comparable
GDPval-AASource —23.2%Not comparable
GDPval-AASource —965Not 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
terminalBenchHardSource —53.8%Not comparable
aaTerminalBench21Source —73.8%Not comparable
Coding
BenchmarkClaude Sonnet 4.6Gemini 3.1 ProResult
SWE-bench VerifiedSource 79.6%—Not comparable
SWE-RebenchSource 60.7%—Not comparable
React Native EvalsSource 80.6%78.9%Claude Sonnet 4.6 leads
Vibe Code BenchSource 51.48%32.03%Claude Sonnet 4.6 leads
cursorBench31Source 48.8%—Not comparable
AA-SciCodeSource 46.9%58.9%Gemini 3.1 Pro leads
FrontierCode 1.1 MainSource 24.3%—Not comparable
LiveCodeBench ProSource —82.9%Not comparable
AA Coding IndexSource —68.8%Not comparable
Reasoning
BenchmarkClaude Sonnet 4.6Gemini 3.1 ProResult
AA-LCRSource 57.7%72.7%Gemini 3.1 Pro leads
CritPtSource 0.9%17.7%Gemini 3.1 Pro leads
ARC-AGI-2Source —77.1%Not comparable
Knowledge
BenchmarkClaude Sonnet 4.6Gemini 3.1 ProResult
GPQASource 89.9%—Not comparable
SuperGPQASource 95%—Not comparable
MMLU-ProSource 79.2%—Not comparable
HLESource 49%—Not comparable
Artificial Analysis Intelligence IndexSource 35.9%46.5%Gemini 3.1 Pro leads
AA-GPQA DiamondSource 79.9%94.1%Gemini 3.1 Pro leads
AA-HLESource 13.2%44.7%Gemini 3.1 Pro leads
AA-Omniscience IndexSource -2.9%32.9%Gemini 3.1 Pro leads
AA-Omniscience AccuracySource 38.0%55.3%Gemini 3.1 Pro leads
AA-Omniscience Hallucination RateSource 65.9%49.9%Gemini 3.1 Pro leads
GPQA-DSource —94.3%Not comparable
HLE w/o toolsSource —45.4%Not comparable
HealthBench HardSource —20.6%Not comparable
MedXpertQA (Text)Source —71.5%Not comparable
MathGemini 3.1 Pro wins
BenchmarkClaude Sonnet 4.6Gemini 3.1 ProResult
FrontierMath v2 (Tiers 1-3)Source 32.400%36.900%Gemini 3.1 Pro leads
FrontierMath v2 (Tier 4)Source 8.300%16.700%Gemini 3.1 Pro leads
Multilingual
BenchmarkClaude Sonnet 4.6Gemini 3.1 ProResult
AA Global-MMLU-LiteSource —93.2%Not comparable
MultimodalGemini 3.1 Pro wins
BenchmarkClaude Sonnet 4.6Gemini 3.1 ProResult
CharXivSource 77.4%80.2%Gemini 3.1 Pro leads
AA-MMMU-ProSource 70.6%82.4%Gemini 3.1 Pro leads
Design Arena WebsiteSource 13171284Claude Sonnet 4.6 leads
MMMU-ProSource —83.9%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
Inst. Following
BenchmarkClaude Sonnet 4.6Gemini 3.1 ProResult
AA-IFBenchSource 41.2%77.1%Gemini 3.1 Pro leads
Frequently Asked Questions (3)

Which is better, Claude Sonnet 4.6 or Gemini 3.1 Pro?

Claude Sonnet 4.6 is ahead on BenchLM's BenchAlign leaderboard, 65.07 to 55.3. The biggest single separator in this matchup is FrontierMath v2 (Tier 4), where the scores are 8.300% and 16.700%.

Which is better for math, Claude Sonnet 4.6 or Gemini 3.1 Pro?

Gemini 3.1 Pro has the edge for math in this comparison, averaging 31.8 versus 26.4. Inside this category, FrontierMath v2 (Tier 4) is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Claude Sonnet 4.6 or Gemini 3.1 Pro?

Gemini 3.1 Pro has the edge for multimodal and grounded tasks in this comparison, averaging 82.6 versus 77.4. Inside this category, Design Arena Website is the benchmark that creates the most daylight between them.

Related Comparisons

Explore More

Anthropic Compare Pricing Methodology Find Your Best LLM Overall Rankings
Last updated: July 20, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.