Skip to main content
BenchLM
Advertise

Model profile

Gemini 3.1 Pro

GoogleCurrentReleased Feb 19, 2026
Data verified
Overall Score
55.3Public #83 of 200
Arena Elo
1485
Eligible category ranks
5of 8
Price (1M tokens)
$2 in / $12 out
API pricing
Speed
109tok/s
Context
1M

Evidence coverage

47 of 321 tracked benchmarks are published. 8 are verified and 39 provisional. 8 of 8 categories are measured.

Updated July 20, 2026Methodology
Published / tracked
47 / 321
Verified
8
Provisional
39
Categories with evidence
8 / 8

Evidence by category

  • Agentic16 benchmarks
    Mixed evidence
  • Coding5 benchmarks
    Mixed evidence
  • Reasoning3 benchmarks
    Mixed evidence
  • Knowledge10 benchmarks
    Reported
  • Math2 benchmarks
    Verified
  • Multilingual1 benchmark
    Reported
  • Multimodal9 benchmarks
    Reported
  • Inst. Following1 benchmark
    Reported
ProprietaryNon-Reasoning
Confidence:
High
base

Gemini 3.1 Pro ranks #83 out of 200 models on the public leaderboard with an overall score of 55.3/100. It does not yet have enough sourced coverage for BenchLM's verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.

Gemini 3.1 Pro is a proprietary model with a 1M token context window. It processes queries without explicit chain-of-thought reasoning, offering faster response times and lower token usage.

This profile currently has 47 of 321 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Multimodal & Grounded (#5), while its weakest is Agentic (#102). This performance profile makes it particularly strong for screenshots, documents, charts, and grounded multimodal workflows.

Peer position

Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.

Range 55.0–55.47

  1. DeepSeek V4 Pro (High)
    DeepSeek
    #8155.47
    DeepSeek V4 Pro (High) is #81 with a score of 55.47.
    Compare
  2. DeepSeek V3.2
    DeepSeek
    #8255.4
    DeepSeek V3.2 is #82 with a score of 55.4.
    Compare
  3. Gemini 3.1 ProCurrent model
    Google
    #8355.3
    Gemini 3.1 Pro is #83 with a score of 55.3.
  4. GPT-5 (medium)
    OpenAI
    #8455.15
    GPT-5 (medium) is #84 with a score of 55.15.
    Compare
  5. GLM-4.6
    Z.AI
    #8555.12
    GLM-4.6 is #85 with a score of 55.12.
    Compare
  6. Step 3.5 Flash
    StepFun
    #8655.1
    Step 3.5 Flash is #86 with a score of 55.1.
    Compare
  7. Kimi K2.7 Code
    Moonshot AI
    #8755.0
    Kimi K2.7 Code is #87 with a score of 55.0.
    Compare

Category percentile

More

Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.

  1. Multimodal86%
    Eligible cohort rank #5 of 29Category score 80.9
  2. Inst. Following59%
    Eligible cohort rank #16 of 38Category score 85.8
  3. Knowledge57%
    Eligible cohort rank #23 of 52Category score 72.8
  4. Coding45%
    Eligible cohort rank #68 of 122Category score 49.4
  5. Agentic14%
    Eligible cohort rank #102 of 119Category score 37.3

Category evidence

Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank #102 of 119Percentile 14thWeight 22%16 benchmarksMixed sources37.3
CodingRank #68 of 122Percentile 45thWeight 20%5 benchmarksMixed sources49.4
ReasoningRank Not rankedWeight 17%3 benchmarksMixed sources87.6
KnowledgeRank #23 of 52Percentile 57thWeight 12%10 benchmarksReported72.8
MathRank Not rankedWeight 5%2 benchmarksVerified55.2
MultilingualRank Not rankedWeight 7%1 benchmarkReported93.0
MultimodalRank #5 of 29Percentile 86thWeight 12%9 benchmarksReported80.9
Inst. FollowingRank #16 of 38Percentile 59thWeight 5%1 benchmarkReported85.8

Chatbot Arena performance

Scroll horizontally to inspect confidence intervals and vote counts.

Chatbot Arena Elo, confidence interval, and vote count by evaluation view
ViewEloConfidence intervalVotes
Text Overall1485±3.681,473
Coding1521±5.522,312
Math1491±9.64,387
Instruction Following1481±5.326,608
Creative Writing1478±6.613,642
Multi-turn1493±6.314,165
Hard Prompts1506±4.452,096
Hard Prompts (English)1505±5.325,548
Longer Query1497±5.233,534

Benchmark Details

Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.

Agentic16 benchmarks
Claw-EvalBenchmark exact
57.8%Display only
Source: Claw-Eval leaderboardProvenance: Claw-Eval reports this model as gemini31_pro in the official 2026-05-09 leaderboard snapshot. BenchLM stores the primary Pass^3 value on the local Claw-Eval display key.
DeepSearchQASecondary exact
69.7%Display only
Source: Meta AI: Muse Spark comparison chartProvenance: Secondary exact
τ²-bench resultsSecondary exact

τ²-Bench Tool-Agent-User Evaluation

95.6%Display only
Source: Meta AI: Muse Spark comparison chartProvenance: Secondary exact
AA Agentic IndexReported

Artificial Analysis Agentic Index

21.4%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
APEX-Agents-AAReported
32.0%Display only
Source: Artificial Analysis: apex-agents-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
GDPval-AAReported

GDPval-AA normalized

23.2%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
GDPval-AAReported
965Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Gert LabsBenchmark exact

Gert Labs Composite Game Benchmark

56.87%Display only
Source: Gert Labs rankingsProvenance: Gert Labs reports this composite leaderboard score in the public rankings API. BenchLM scales the source gscore from 0-1 to 0-100 and stores it as a display-only agentic benchmark.
ResearchClawBenchBenchmark exact
13.3%Display only
Source: ResearchClawBench leaderboardProvenance: ResearchClawBench reports this model as ResearchHarness (Gemini-3.1-Pro) in the official Pass@1 leaderboard. BenchLM stores the one-decimal RADS average on the local ResearchClawBench display key and excludes it from weighted rankings.
AA AutomationBenchReported

Artificial Analysis AutomationBench

37.5%Display only
Source: Artificial Analysis: automationbench-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA EnterpriseOps-GymReported

Artificial Analysis EnterpriseOps-Gym

42.2%Display only
Source: Artificial Analysis: enterprise-ops-gym-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA Harvey LABReported

Artificial Analysis Harvey LAB-AA

0.0%Display only
Source: Artificial Analysis: harvey-lab-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA ITBenchReported

Artificial Analysis ITBench-AA

30.3%Display only
Source: Artificial Analysis: itbench-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA Tau3 BankingReported

Artificial Analysis Tau3-Banking

16.5%Display only
Source: Artificial Analysis: tau3-banking leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
terminalBenchHardReported
53.8%Display only
Source: Artificial Analysis: terminalbench-hard leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
aaTerminalBench21Reported
73.8%Display only
Source: Artificial Analysis: terminalbench-v2-1 leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Coding5 benchmarks
LiveCodeBench ProSecondary exact
82.9%Display only
Source: Meta AI: Muse Spark comparison chartProvenance: Secondary exact
React Native EvalsBenchmark exact
78.9%Display only
Source: React Native Evals leaderboardProvenance: React Native Evals reports this exact overall score for Gemini 3.1 Pro Preview in the public dashboard run finished on 2026-04-28.
Vibe Code BenchBenchmark exact

Vibe Code Bench v1.1

32.03%Display only
Source: Vals AI: Vibe Code Bench v1.1Provenance: Vals Vibe Code Bench v1.1 reports this exact row under google/gemini-3.1-pro-preview; BenchLM stores it on the local vibeCodeBench key.
AA Coding IndexReported

Artificial Analysis Coding Index

68.8%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-SciCodeReported

Artificial Analysis SciCode

58.9%Display only
Source: Artificial Analysis: scicode leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Reasoning3 benchmarks
ARC-AGI-2Provider exact

Abstraction and Reasoning Corpus for AGI v2

77.1%Weighted 31%
Source: Google: Gemini 3.1 ProProvenance: Google explicitly states that Gemini 3.1 Pro achieved a verified 77.1% score on ARC-AGI-2 in the launch announcement.
AA-LCRReported

Artificial Analysis Long Context Reasoning

72.7%Display only
Source: Artificial Analysis: artificial-analysis-long-context-reasoning leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
CritPtReported

Critical Physics Tasks

17.7%Display only
Source: Artificial Analysis: critpt leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Knowledge10 benchmarks
GPQA-DSecondary exact

GPQA Diamond

94.3%Display only
Source: Meta AI: Muse Spark comparison chartProvenance: Secondary exact
HLE w/o toolsSecondary exact

Humanity's Last Exam without tools

45.4%Display only
Source: Meta AI: Muse Spark comparison chartProvenance: Secondary exact
HealthBench HardSecondary exact
20.6%Display only
Source: Meta AI: Muse Spark comparison chartProvenance: Secondary exact
MedXpertQA (Text)Secondary exact

MedXpertQA Text

71.5%Display only
Source: Meta AI: Muse Spark comparison chartProvenance: Secondary exact
Artificial Analysis Intelligence IndexReported
46.5%Display only
Source: Artificial Analysis: artificial-analysis-intelligence-index leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-GPQA DiamondReported

Artificial Analysis GPQA Diamond

94.1%Display only
Source: Artificial Analysis: gpqa-diamond leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-HLEReported

Artificial Analysis Humanity's Last Exam

44.7%Display only
Source: Artificial Analysis: humanitys-last-exam leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-Omniscience IndexReported

Artificial Analysis Omniscience Index

32.9%Display only
Source: Artificial Analysis: omniscience leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-Omniscience AccuracyReported

Artificial Analysis Omniscience Accuracy

55.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience Hallucination RateReported

Artificial Analysis Omniscience Hallucination Rate

49.9%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Math2 benchmarks
FrontierMath v2 (Tiers 1-3)Benchmark exact

FrontierMath v2 Tiers 1-3

36.900%Weighted 30%
Source: Epoch AI FrontierMath v2 leaderboardProvenance: Epoch AI reports FrontierMath v2 Tiers 1-3 at 36.9% for gemini-3.1-pro-preview. BenchLM selects the highest published thinking effort for the model and stores the v2 benchmark slice separately.
FrontierMath v2 (Tier 4)Benchmark exact

FrontierMath v2 Tier 4

16.700%Weighted 10%
Source: Epoch AI FrontierMath v2 leaderboardProvenance: Epoch AI reports FrontierMath v2 Tier 4 at 16.7% for gemini-3.1-pro-preview. BenchLM selects the highest published thinking effort for the model and stores the v2 benchmark slice separately.
Multilingual1 benchmark
AA Global-MMLU-LiteReported

Artificial Analysis Global-MMLU-Lite

93.2%Display only
Source: Artificial Analysis: global-mmlu-lite leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Multimodal9 benchmarks
MMMU-ProSecondary exact

Massive Multi-discipline Multimodal Understanding Pro

83.9%Weighted 45%
Source: Meta AI: Muse Spark comparison chartProvenance: Secondary exact
CharXivSecondary exact

CharXiv Reasoning

80.2%Weighted 25%
Source: Meta AI: Muse Spark comparison chartProvenance: Secondary exact
ERQASecondary exact
69.4%Display only
Source: Meta AI: Muse Spark comparison chartProvenance: Secondary exact
SimpleVQASecondary exact
72.4%Display only
Source: Meta AI: Muse Spark comparison chartProvenance: Secondary exact
ScreenSpot ProSecondary exact
84.4%Display only
Source: Meta AI: Muse Spark comparison chartProvenance: Secondary exact
ZeroBenchSecondary exact
29.0%Display only
Source: Meta AI: Muse Spark comparison chartProvenance: Secondary exact
MedXpertQA (MM)Secondary exact

MedXpertQA Multimodal

81.3%Display only
Source: Meta AI: Muse Spark comparison chartProvenance: Secondary exact
AA-MMMU-ProReported

Artificial Analysis MMMU-Pro

82.4%Display only
Source: Artificial Analysis: mmmu-pro leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Design Arena WebsiteReported

Design Arena Website Elo

1284Display only
Source: OpenRouter model benchmarksProvenance: Display-only Design Arena Website Elo synced from OpenRouter model benchmark metadata. It is excluded from BenchLM weighted scoring.
Inst. Following1 benchmark
AA-IFBenchReported

Artificial Analysis IFBench

77.1%Display only
Source: Artificial Analysis: ifbench leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.

Frequently Asked Questions

How does Gemini 3.1 Pro perform overall in AI benchmarks?

Gemini 3.1 Pro currently ranks #83 out of 200 models on BenchLM's provisional leaderboard with an overall score of 55.3. It is created by Google. Its published context window is 1M.

Is Gemini 3.1 Pro good for knowledge and understanding?

Gemini 3.1 Pro ranks #23 out of 52 models in knowledge and understanding benchmarks with an average score of 72.8. There are stronger options in this category.

Is Gemini 3.1 Pro good for coding and programming?

Gemini 3.1 Pro ranks #68 out of 122 models in coding and programming benchmarks with an average score of 49.4. There are stronger options in this category.

Is Gemini 3.1 Pro good for mathematics?

Gemini 3.1 Pro has visible benchmark coverage in mathematics, but BenchLM does not currently assign it a global category rank there.

Is Gemini 3.1 Pro good for reasoning and logic?

Gemini 3.1 Pro has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

Is Gemini 3.1 Pro good for agentic tool use and computer tasks?

Gemini 3.1 Pro ranks #102 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 37.3. There are stronger options in this category.

Is Gemini 3.1 Pro good for multimodal and grounded tasks?

Gemini 3.1 Pro ranks #5 out of 29 models in multimodal and grounded tasks benchmarks with an average score of 80.9. It is among the top performers in this category.

Is Gemini 3.1 Pro good for instruction following?

Gemini 3.1 Pro ranks #16 out of 38 models in instruction following benchmarks with an average score of 85.8. There are stronger options in this category.

Is Gemini 3.1 Pro good for multilingual tasks?

Gemini 3.1 Pro has visible benchmark coverage in multilingual tasks, but BenchLM does not currently assign it a global category rank there.

Does Gemini 3.1 Pro have full benchmark coverage on BenchLM?

Not yet. Gemini 3.1 Pro currently has 47 published benchmark scores out of the 321 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of Gemini 3.1 Pro?

Gemini 3.1 Pro has a published context window of 1M, which determines how much text it can process in a single interaction.

Related Resources

More from Google LLM Pricing Comparison BenchLM Methodology The AI Race Which LLM Should I Use? Benchmark Explainers
Last updated: July 20, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Choose with this week’s evidence

Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.

Free. One email per week.