Skip to main content
BenchLM
Advertise

Model comparison

Claude Opus 4.6 vs Gemini 3.1 Pro

Data verified

Head-to-head evidence from 30 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

68.59/100
Margin
13.3pts
← winning
55.3/100
1 category wins1 category wins

Public leaderboard positions: Claude Opus 4.6 #16 (Supported); Gemini 3.1 Pro #83 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude Opus 4.6 and Gemini 3.1 Pro share 30 comparable benchmark results. 2 of 8 categories are comparable. 16 results are unique to Claude Opus 4.6; 17 to Gemini 3.1 Pro.

Updated July 20, 2026
Shared results
30
Claude Opus 4.6 only
16
Gemini 3.1 Pro only
17
Comparable categories
2 / 8

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

Confidence note. This is a partial-evidence comparison with 30 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 Opus 4.6 is clearly ahead on the BenchAlign aggregate, 68.59 to 55.3. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Claude Opus 4.6's sharpest advantage is in mathematics, where it averages 36.3 against 31.8. The single biggest benchmark swing on the page is MMMU-Pro, 77.3% to 83.9%. Gemini 3.1 Pro does hit back in multimodal & grounded, so the answer changes if that is the part of the workload you care about most.

Claude Opus 4.6 is also the more expensive model on tokens at $5.00 input / $25.00 output per 1M tokens, versus $2.00 input / $12.00 output per 1M tokens for Gemini 3.1 Pro. That is roughly 2.1x on output cost alone.

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 Opus 4.6 and Gemini 3.1 Pro
CategoryClaude Opus 4.6ΔGemini 3.1 Pro
MultimodalClaude Opus 4.677.3Margin→ 5.3Gemini 3.1 Pro82.6
MathClaude Opus 4.636.3Margin← 4.5Gemini 3.1 Pro31.8
AgenticClaude Opus 4.673.0MarginNo overlapGemini 3.1 ProNot measured
CodingClaude Opus 4.668.1MarginNo overlapGemini 3.1 ProNot measured
ReasoningClaude Opus 4.6Not measuredMarginNo overlapGemini 3.1 Pro77.1
KnowledgeClaude Opus 4.669.1MarginNo overlapGemini 3.1 ProNot measured

Decisive benchmark drivers

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

More
A · Claude Opus 4.6B · Gemini 3.1 Pro

  1. MMMU-Pro

    Multimodal
    Source ↗
    A 77.3%B 83.9%
    Winner: Gemini 3.1 ProΔ 6.6
    MMMU-Pro: Claude Opus 4.6 scored 77.3%; Gemini 3.1 Pro scored 83.9%. Gemini 3.1 Pro wins this benchmark.

  2. FrontierMath v2 (Tier 4)

    Math
    Source ↗
    A 22.900%B 16.700%
    Winner: Claude Opus 4.6Δ 6.2
    FrontierMath v2 (Tier 4): Claude Opus 4.6 scored 22.900%; Gemini 3.1 Pro scored 16.700%. Claude Opus 4.6 wins this benchmark.

  3. FrontierMath v2 (Tiers 1-3)

    Math
    Source ↗
    A 40.700%B 36.900%
    Winner: Claude Opus 4.6Δ 3.8
    FrontierMath v2 (Tiers 1-3): Claude Opus 4.6 scored 40.700%; Gemini 3.1 Pro scored 36.900%. Claude Opus 4.6 wins this benchmark.

Operational comparison

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

MetricClaude Opus 4.6Gemini 3.1 ProComparison
Input / output priceUSD per 1M tokensClaude Opus 4.6$5 input / $25 outputGemini 3.1 Pro$2 input / $12 outputGemini 3.1 Pro has the lower combined listed price.
Generation speedtokens per secondClaude Opus 4.640 tok/sGemini 3.1 Pro109 tok/sGemini 3.1 Pro has the higher measured throughput.
First-answer latencyseconds to first tokenClaude Opus 4.61.78 sGemini 3.1 Pro29.71 sClaude Opus 4.6 reaches the first token sooner.
Context windowmaximum listed tokensClaude Opus 4.61MGemini 3.1 Pro1MListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkClaude Opus 4.6Gemini 3.1 ProResult
Terminal-Bench 2.0Source 65.4%—Not comparable
BrowseCompSource 83.7%—Not comparable
OSWorld-VerifiedSource 72.7%—Not comparable
τ²-bench resultsSource 84.8%95.6%Gemini 3.1 Pro leads
Claw-EvalSource 70.4%57.8%Claude Opus 4.6 leads
DeepSearchQASource 73.7%69.7%Claude Opus 4.6 leads
CyberGymSource 66.6%—Not comparable
Gert LabsSource 61.85%56.87%Claude Opus 4.6 leads
ResearchClawBenchSource 19.9%13.3%Claude Opus 4.6 leads
JobBenchSource 36.7%—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
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 Opus 4.6Gemini 3.1 ProResult
SWE-bench VerifiedSource 80.8%—Not comparable
SWE-bench Verified*Source 75.6%—Not comparable
LiveCodeBench ProSource 70.7%82.9%Gemini 3.1 Pro leads
SWE-bench ProSource 53.4%—Not comparable
SWE-RebenchSource 65.3%—Not comparable
React Native EvalsSource 84.1%78.9%Claude Opus 4.6 leads
Vibe Code BenchSource 57.57%32.03%Claude Opus 4.6 leads
AA-SciCodeSource 45.7%58.9%Gemini 3.1 Pro leads
FrontierCode 1.1 MainSource 26.9%—Not comparable
AA Coding IndexSource —68.8%Not comparable
Reasoning
BenchmarkClaude Opus 4.6Gemini 3.1 ProResult
AA-LCRSource 58.3%72.7%Gemini 3.1 Pro leads
CritPtSource 2.8%17.7%Gemini 3.1 Pro leads
ARC-AGI-2Source —77.1%Not comparable
Knowledge
BenchmarkClaude Opus 4.6Gemini 3.1 ProResult
GPQASource 91.3%—Not comparable
GPQA-DSource 89.2%94.3%Gemini 3.1 Pro leads
SuperGPQASource 95%—Not comparable
MMLU-ProSource 82%—Not comparable
MMLU-Pro (Arcee)Source 89.1%—Not comparable
HLESource 53%—Not comparable
HLE w/o toolsSource 40%45.4%Gemini 3.1 Pro leads
HealthBench HardSource 14.8%20.6%Gemini 3.1 Pro leads
MedXpertQA (Text)Source 52.1%71.5%Gemini 3.1 Pro leads
Artificial Analysis Intelligence IndexSource 37.8%46.5%Gemini 3.1 Pro leads
AA-GPQA DiamondSource 84.0%94.1%Gemini 3.1 Pro leads
AA-HLESource 18.6%44.7%Gemini 3.1 Pro leads
AA-Omniscience IndexSource 3.5%32.9%Gemini 3.1 Pro leads
AA-Omniscience AccuracySource 45.2%55.3%Gemini 3.1 Pro leads
AA-Omniscience Hallucination RateSource 76.0%49.9%Gemini 3.1 Pro leads
MathClaude Opus 4.6 wins
BenchmarkClaude Opus 4.6Gemini 3.1 ProResult
AIME25 (Arcee)Source 99.8%—Not comparable
FrontierMath v2 (Tiers 1-3)Source 40.700%36.900%Claude Opus 4.6 leads
FrontierMath v2 (Tier 4)Source 22.900%16.700%Claude Opus 4.6 leads
Multilingual
BenchmarkClaude Opus 4.6Gemini 3.1 ProResult
AA Global-MMLU-LiteSource —93.2%Not comparable
MultimodalGemini 3.1 Pro wins
BenchmarkClaude Opus 4.6Gemini 3.1 ProResult
MMMU-ProSource 77.3%83.9%Gemini 3.1 Pro leads
ERQASource 51.6%69.4%Gemini 3.1 Pro leads
ScreenSpot ProSource 83.1%84.4%Gemini 3.1 Pro leads
MedXpertQA (MM)Source 64.8%81.3%Gemini 3.1 Pro leads
AA-MMMU-ProSource 72.5%82.4%Gemini 3.1 Pro leads
Design Arena WebsiteSource 13281284Claude Opus 4.6 leads
CharXivSource —80.2%Not comparable
SimpleVQASource —72.4%Not comparable
ZeroBenchSource —29.0%Not comparable
Inst. Following
BenchmarkClaude Opus 4.6Gemini 3.1 ProResult
AA-IFBenchSource 44.6%77.1%Gemini 3.1 Pro leads
Frequently Asked Questions (3)

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

Claude Opus 4.6 is ahead on BenchLM's BenchAlign leaderboard, 68.59 to 55.3. The biggest single separator in this matchup is MMMU-Pro, where the scores are 77.3% and 83.9%.

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

Claude Opus 4.6 has the edge for math in this comparison, averaging 36.3 versus 31.8. 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 Opus 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 77.3. 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.