Skip to content

Google · Chat

Gemini 3 Pro Preview

Google 🇺🇸ChatGemini familyOne of its sources says the weights aren't publicly available.

Newer version: Gemini 3.1 Pro Preview. We compared release dates and version names in our catalogue.

From Replicate's listing:
Google's most advanced reasoning Gemini model
llminfo IQ
136.4
Maker's price
$4.50 blended / 1M
Max context
1M
Listings
17

Evidence and sources

llminfo IQ 136.4, ranked among chat models. From 490 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 110.6, 95% interval 103–118. From 15 benchmark families across 12 sources. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedGood value (54.0). Cheaper per task than its benchmark results predict. From 61 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksYap score: tokens used per coding task vs. models with the same resultsTerse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. By effort: default 43 · high 41.Median 14,649 output tokens per task at default effort.How the Yap score worksReleased 18 Nov 2025Maker HQ: US (according to Google's own website)
Sources: LMArena data, Models.dev data, Replicate data docs, llminfo researchPrimary data from LMArena from Models.dev: name, weights availability from Replicate: description from llminfo research: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Trade-offs

No open weights

The weights aren't public, so you can't run it yourself.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 9 maker's prices; 1 market median price.

Input & output

as stated by the model's providers
Text
Images
Audio
Video
Files
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingPrompt cachingPDF inputWeb searchAudio inputBatch API

Listings

 Googlegemini-3-pro-previewSources: GenAI Prices data, LiteLLM data, Portkey Models data1M$2.00>128k $4.00>200k $4.00cache read $0.20batch $1.00$12.00>128k $18.00>200k $18.00batch $6.00
 302aigemini-3-pro-previewSources: 302.ai data, Models.dev data1M$2.00$12.00
 OpenRoutergoogle/gemini-3-pro-previewSource: Helicone Costs dataNot published by the provider$2.00$12.00
 Replicatereplicate/google/gemini-3-proSource: LiteLLM dataNot published by the provider$2.00>200k $4.00$12.00>200k $18.00
 Replicategoogle/gemini-3-pro · ≤ 200,000Source: Replicate data docsNot published by the provider$2.00$12.00
 Replicategoogle/gemini-3-pro · > 200,000Source: Replicate data docsNot published by the provider$4.00$18.00
 RequestyInference by Googlegoogle/gemini-3-pro-previewSource: Requesty data1M$2.00>200k $4.00cache read $0.20$12.00>200k $18.00cache write $4.50
 Databricksdatabricks/databricks-gemini-3-proSources: LiteLLM data, Models.dev data1M$2.50cache read $0.25$15.00cache write $2.50
 Jiekougemini-3-pro-previewSource: Models.dev data1M$1.80$10.80
 Qihang AIgemini-3-pro-previewSource: Models.dev data1M$0.57$3.43

7 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Agentic

Design Arena EloSource: Design Arena Leaderboards data · Nov 2026
GAIA4 results
Source: GAIA Leaderboard data · Dec 2025
Difficulty level
Difficulty not reported
MCP AtlasOpus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted · Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
MLE-Bench6 results
Source: MLE-bench official data
PiEvolve (Fractal AI Research)
Open Agent Leaderboard6 related benchmarks · 30 results
SWE-bench
Source: Open Agent Leaderboard results data docs
By agent · task: swebench · route: openai/gcp
AppWorld test_normal
Source: Open Agent Leaderboard results data docs
By agent · task: appworld_test_normal · subset: test_normal · route: openai/gcp
BrowseCompPlus
Source: Open Agent Leaderboard results data docs
By agent · task: browsecompplus · route: openai/gcp
Tau Bench 2 airline
Source: Open Agent Leaderboard results data docs
By agent · task: tau2_airline · subset: airline · route: openai/gcp
Tau Bench 2 retail
Source: Open Agent Leaderboard results data docs
By agent · task: tau2_retail · subset: retail · route: openai/gcp
Tau Bench 2 telecom
Source: Open Agent Leaderboard results data docs
By agent · task: tau2_telecom · subset: telecom · route: openai/gcp
OpenHandsSource: OpenHands Index data
tau2-bench v112 related benchmarks · 12 results
retail pass^1
Source: Sierra tau-bench Leaderboard data docs · Mar 2026
submission-gemini-3-pro_sierra_2026-03-02, usersim-gpt-5.2, effort-high
airline pass^1
Source: Sierra tau-bench Leaderboard data docs · Mar 2026
submission-gemini-3-pro_sierra_2026-03-02, usersim-gpt-5.2, effort-high
airline pass^2
Source: Sierra tau-bench Leaderboard data docs · Mar 2026
submission-gemini-3-pro_sierra_2026-03-02, usersim-gpt-5.2, effort-high
airline pass^3
Source: Sierra tau-bench Leaderboard data docs · Mar 2026
submission-gemini-3-pro_sierra_2026-03-02, usersim-gpt-5.2, effort-high
airline pass^4
Source: Sierra tau-bench Leaderboard data docs · Mar 2026
submission-gemini-3-pro_sierra_2026-03-02, usersim-gpt-5.2, effort-high
retail pass^2
Source: Sierra tau-bench Leaderboard data docs · Mar 2026
submission-gemini-3-pro_sierra_2026-03-02, usersim-gpt-5.2, effort-high
Show 6 more resultsHide 6 results
retail pass^3
Source: Sierra tau-bench Leaderboard data docs · Mar 2026
submission-gemini-3-pro_sierra_2026-03-02, usersim-gpt-5.2, effort-high
retail pass^4
Source: Sierra tau-bench Leaderboard data docs · Mar 2026
submission-gemini-3-pro_sierra_2026-03-02, usersim-gpt-5.2, effort-high
telecom pass^1
Source: Sierra tau-bench Leaderboard data docs · Mar 2026
submission-gemini-3-pro_sierra_2026-03-02, usersim-gpt-5.2, effort-high
telecom pass^2
Source: Sierra tau-bench Leaderboard data docs · Mar 2026
submission-gemini-3-pro_sierra_2026-03-02, usersim-gpt-5.2, effort-high
telecom pass^3
Source: Sierra tau-bench Leaderboard data docs · Mar 2026
submission-gemini-3-pro_sierra_2026-03-02, usersim-gpt-5.2, effort-high
telecom pass^4
Source: Sierra tau-bench Leaderboard data docs · Mar 2026
submission-gemini-3-pro_sierra_2026-03-02, usersim-gpt-5.2, effort-high
Terminal-Bench3 related benchmarks · 4 results
2.0 · Terminus-2
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Gemini 3 Pro Model Card · results as of November 2025 · Terminus-2
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted
Terminal-Bench 2.0
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Gemini 3 Pro Model Card · results as of November 2025 · mean net worth
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Human preference

Arena ELO67 related benchmarks · 67 results
Show 61 more resultsHide 61 results

Safety

HELM66 related benchmarks · 66 results
Source: Stanford HELM specialized suites data docs
BenchmarkScore
Safety: BBQ - BBQ accuracy
AIR-Bench: AIRBench 2024 - #1: Confidentiality
AIR-Bench: AIRBench 2024 - #2: Integrity
AIR-Bench: AIRBench 2024 - #3: Availability
Show 62 more benchmarksHide 62 benchmarks
BenchmarkScore
AIR-Bench: AIRBench 2024 - #4: Automated Decision-Making
AIR-Bench: AIRBench 2024 - #5: Autonomous Unsafe Operation of Systems
AIR-Bench: AIRBench 2024 - #6: Advice in Heavily Regulated Industries
AIR-Bench: AIRBench 2024 - #7: Supporting Malicious Organized Groups
AIR-Bench: AIRBench 2024 - #8: Celebrating Suffering
AIR-Bench: AIRBench 2024 - #9: Violent acts
AIR-Bench: AIRBench 2024 - #10: Depicting Violence
AIR-Bench: AIRBench 2024 - #11: Weapon Usage & Development
AIR-Bench: AIRBench 2024 - #12: Military and Warfare
AIR-Bench: AIRBench 2024 - #13: Harassment
AIR-Bench: AIRBench 2024 - #15: Perpetuating Harmful Beliefs
AIR-Bench: AIRBench 2024 - #16: Offensive Language
AIR-Bench: AIRBench 2024 - #17: Adult content
AIR-Bench: AIRBench 2024 - #18: Erotic
AIR-Bench: AIRBench 2024 - #19: Non-Consensual Nudity
AIR-Bench: AIRBench 2024 - #20: Monetized
AIR-Bench: AIRBench 2024 - #21: Endangerment, Harm, or Abuse of Children
AIR-Bench: AIRBench 2024 - #22: Child Sexual Abuse
AIR-Bench: AIRBench 2024 - #23: Suicidal and non-suicidal self Injury
AIR-Bench: AIRBench 2024 - #24: Political Persuasion
AIR-Bench: AIRBench 2024 - #25: Influencing Politics
AIR-Bench: AIRBench 2024 - #26: Deterring Democratic Participation
AIR-Bench: AIRBench 2024 - #27: Disrupting Social Order (China-unique)
AIR-Bench: AIRBench 2024 - #28: High-Risk Financial Activities
AIR-Bench: AIRBench 2024 - #29: Unfair Market Practices
AIR-Bench: AIRBench 2024 - #30: Disempowering Workers
AIR-Bench: AIRBench 2024 - #31: Fraudulent Schemes
AIR-Bench: AIRBench 2024 - #32: Fraud
AIR-Bench: AIRBench 2024 - #33: Academic dishonesty
AIR-Bench: AIRBench 2024 - #34: Mis/disinformation
AIR-Bench: AIRBench 2024 - #35: Sowing Division
AIR-Bench: AIRBench 2024 - #36: Misrepresentation
AIR-Bench: AIRBench 2024 - #37: Types of Defamation
AIR-Bench: AIRBench 2024 - #38: Specific Types of Rights
AIR-Bench: AIRBench 2024 - #39-40: Discrimination/Protected Characteristics Combinations
AIR-Bench: AIRBench 2024 - #41-42: Privacy Violations/Sensitive Data Combinations
AIR-Bench: AIRBench 2024 - #43: Illegal/Regulated substances/goods
AIR-Bench: AIRBench 2024 - #44: Illegal services/exploitation
AIR-Bench: AIRBench 2024 - #45: Other Illegal/Unlawful/Criminal Activities
AIR-Bench: AIRBench 2024 - Child Harm
AIR-Bench: AIRBench 2024 - Criminal Activities
AIR-Bench: AIRBench 2024 - Deception
AIR-Bench: AIRBench 2024 - Defamation
AIR-Bench: AIRBench 2024 - Discrimination/Bias
AIR-Bench: AIRBench 2024 - Economic Harm
AIR-Bench: AIRBench 2024 - Fundamental Rights
AIR-Bench: AIRBench 2024 - Hate/Toxicity
AIR-Bench: AIRBench 2024 - Manipulation
AIR-Bench: AIRBench 2024 - Operational Misuses
AIR-Bench: AIRBench 2024 - Political Usage
AIR-Bench: AIRBench 2024 - Privacy
AIR-Bench: AIRBench 2024 - Refusal Rate
AIR-Bench: AIRBench 2024 - Security Risks
AIR-Bench: AIRBench 2024 - Self-harm
AIR-Bench: AIRBench 2024 - Sexual Content
AIR-Bench: AIRBench 2024 - Violence & Extremism
Safety: Anthropic Red Team - LM Evaluated Safety score
Safety: BBQ - BBQ (ambiguous)
Safety: BBQ - BBQ (unambiguous)
Safety: HarmBench - LM Evaluated Safety score
Safety: SimpleSafetyTests - LM Evaluated Safety score
Safety: XSTest - LM Evaluated Safety score
PhareSource: Phare

Reasoning

ARC-AGI3 related benchmarks · 5 results
ARC-AGI 2
Source: Epoch AI Benchmarking Hub data
Setting not stated
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Gemini 3 Pro Model Card · results as of November 2025 · ARC Prize Verified
v2
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
CL-bench5 related benchmarks · 15 results
Overall
Reported by Tencent Hunyuan / Fudan NLP Group · via BenchBoard docs
By site model-mode label · benchmark-owner leaderboard run · 1899 tasks · GPT-5.1 judge · low reasoning effort · candidate API snapshot and exact candidate harness not specified on public leaderboard
Source: Epoch AI Benchmarking Hub data
Setting not stated
Domain Knowledge Reasoning
Reported by Tencent Hunyuan / Fudan NLP Group · via BenchBoard docs
By site model-mode label · benchmark-owner leaderboard run · 1899 tasks · GPT-5.1 judge · low reasoning effort · candidate API snapshot and exact candidate harness not specified on public leaderboard
Source: Epoch AI Benchmarking Hub data
Setting not stated
Empirical Discovery & Simulation
Reported by Tencent Hunyuan / Fudan NLP Group · via BenchBoard docs
By site model-mode label · benchmark-owner leaderboard run · 1899 tasks · GPT-5.1 judge · low reasoning effort · candidate API snapshot and exact candidate harness not specified on public leaderboard
Source: Epoch AI Benchmarking Hub data
Setting not stated
Procedural Task Execution
Reported by Tencent Hunyuan / Fudan NLP Group · via BenchBoard docs
By site model-mode label · benchmark-owner leaderboard run · 1899 tasks · GPT-5.1 judge · low reasoning effort · candidate API snapshot and exact candidate harness not specified on public leaderboard
Source: Epoch AI Benchmarking Hub data
Setting not stated
Rule System Application
Reported by Tencent Hunyuan / Fudan NLP Group · via BenchBoard docs
By site model-mode label · benchmark-owner leaderboard run · 1899 tasks · GPT-5.1 judge · low reasoning effort · candidate API snapshot and exact candidate harness not specified on public leaderboard
Source: Epoch AI Benchmarking Hub data
Setting not stated
Global PIQA2 results
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Gemini 3 Pro Model Card · results as of November 2025 · 100 languages and cultures
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Gemini 3 Pro Model Card · results as of November 2025 · no tools
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
t2-benchSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Vision

CharXiv ReasoningGemini 3 Pro Model Card · results as of November 2025 · reasoning · Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
CharXiv-RSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
MMMU-Pro3 results
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Gemini 3 Pro Model Card · results as of November 2025
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted · no tools
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Gemini 3 Pro Model Card · results as of November 2025
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
VideoMMMU2 results
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Gemini 3 Pro Model Card · results as of November 2025
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Math

AIME 20253 results
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Gemini 3 Pro Model Card · results as of November 2025
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
MathArena20 related benchmarks · 22 results
Apex
Source: MathArena data
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Gemini 3 Pro Model Card · results as of November 2025
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
01/2026
Source: MathArena data
12/2025
Source: MathArena data
AIME 2025
Source: MathArena data
AIME 2026
Source: MathArena data
Apex Shortlist
Source: MathArena data
Show 14 more resultsHide 14 results
BRUMO 2025
Source: MathArena data
CMIMC 2025
Source: MathArena data
HMMT Feb 2025
Source: MathArena data
HMMT Feb 2026
Source: MathArena data
HMMT Nov 2025
Source: MathArena data
Kangaroo 2025 3-4
Source: MathArena data
Kangaroo 2025 5-6
Source: MathArena data
Kangaroo 2025 7-8
Source: MathArena data
Kangaroo 2025 9-10
Source: MathArena data
Project Euler
Source: MathArena data
Putnam 2025
Source: MathArena data
SMT 2025
Source: MathArena data
ValsSource: Vals AI

Coding

Arena ELOSource: LMArena data · Nov 2026
SWE-bench Verified8 related benchmarks · 10 results
SWE-bench Verified
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Gemini 3 Pro Model Card · results as of November 2025 · single attempt
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Show 2 more resultsHide 2 results
ValsSource: Vals AI

OCR

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GPQA Diamond4 results
Source: Epoch AI Benchmarking Hub data
Setting not stated
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Gemini 3 Pro Model Card · results as of November 2025 · no tools
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted
Reported by SenseTime / OpenSenseNova · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
SenseNova 6.7 Flash-Lite official benchmark chart · chart setting

Factuality

SimpleQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Multilingual

MMMLU3 results
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Gemini 3 Pro Model Card · results as of November 2025
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

General

Instruction following

Knowledge

Long context

Speech

Other

ArmBench-LLM Armenian22 related benchmarks · 22 results
Horangi36 related benchmarks · 36 results
4: ALT_환각방지
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4 subset: haerae_bench_v1_rc
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4 subset: haerae_bench_v1_wo_rc
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4 subset: hrm8k
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4 subset: kmmlu
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4 subset: kmmlu_pro
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
Show 30 more resultsHide 30 results
4 subset: ko_aime2025
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4 subset: ko_arc_agi
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4 subset: ko_balt_700_semantic
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4 subset: ko_balt_700_syntax
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4 subset: ko_hallulens_nonexistent
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4 subset: ko_hallulens_wikiqa
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4 subset: ko_hle
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4 subset: ko_moral
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4 subset: ko_truthful_qa
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4 subset: kobbq
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4 subset: korean_hate_speech
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4 subset: squad_kor_v1
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4: ALT_유해성방지
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4: ALT_윤리/도덕
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4: ALT_제어성
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4: ALT_편향성방지
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4: FINAL_SCORE
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4: GLP_구문해석
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4: GLP_논리적추론
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4: GLP_수학적추론
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4: GLP_의미해석
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4: GLP_일반적지식
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4: GLP_전문적지식
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4: GLP_정보검색
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4: GLP_추상적추론
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4: GLP_코딩능력
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4: GLP_표현
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4: GLP_함수호출
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4: 가치정렬성능(ALT)_AVG
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
4: 범용언어성능(GLP)_AVG
Source: Horangi Korean Leaderboard 4 data docs
gemini-3-pro-preview: high-effort
Nejumi 428 related benchmarks · 28 results
OmniDocBench · NEDGemini 3 Pro Model Card · results as of November 2025 · overall edit distance · lower is better · Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
SurveyReview v1.012 related benchmarks · 12 results
Structure · MAE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Comprehensiveness · MAE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Comprehensiveness · MSE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Criticalness · MAE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Criticalness · MSE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Four dimensions · Average MAE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Show 6 more resultsHide 6 results
Four dimensions · Average MSE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Overall · Human-aligned Score
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Overall · Reason Quality Score
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Readability · MAE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Readability · MSE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Structure · MSE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
TAU2BenchGemini 3 Pro Model Card · results as of November 2025 · Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
τ²-bench RetailOpus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted · Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
τ²-bench TelecomOpus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted · Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · LMArena, CC BY 4.0 (licence) · ArmBench-LLM by Metric-AI. Public numeric primary task results; no separate results licence asserted. · Steel.dev Agent Leaderboards, MIT (licence) · BullshitBench by Peter Gostev, MIT (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · HAL (Princeton) — cite the HAL paper · HalluHard: Fan, Delsad, Flammarion and Andriushchenko (EPFL), arXiv:2602.01031 · Stanford HELM (Stanford CRFM); scenario scores from Capabilities, Safety, Long Context, MedHELM, AIR-Bench, MMLU and Finance · Horangi 4, Weights & Biases Korea; public publisher-selected numeric evaluation results · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · MathArena (ETH SRI / INSAIT), MIT — cite dekoninck2026matharena (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · MLE-bench (OpenAI), MIT (licence) · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · OmniDocBench (OpenDataLab), Apache-2.0 (licence) · Open Agent Leaderboard results (Exgentic), CDLA-Permissive-2.0; agreement text at https://cdla.dev/permissive-2-0/. Fractions shown as percentages. (licence) · OpenHands Index (All Hands AI), Apache-2.0 (licence) · Phare (Giskard), CC BY 4.0 (licence) · Shaberi v2.1, Shisa.AI, Apache-2.0. GPT-5.1-judge scores only; judges are not comparable. (licence) · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence) · SWE-fficiency (swefficiency.com) leaderboard materials, CC BY 4.0; Human Expert reference row omitted (licence) · Sierra Research tau2-bench leaderboard submissions (github.com/sierra-research/tau2-bench), MIT (licence) · Terminal-Bench (Laude Institute), Apache-2.0 (licence) · UzLiB, Tahrirchi (Abror Shopulatov). Public LEADERBOARD.md numbers; repository MIT covers software and documentation, no separate results licence stated and none asserted. · Vectara Hallucination Leaderboard, Apache-2.0 (licence)

Around the web

Also known as: databricks-gemini-3-pro, databricks/databricks-gemini-3-pro, gemini-3-pro, gemini-3-pro-grounding, gemini-3-pro-preview-thinking, gemini-3.0-pro-preview, google/gemini-3-pro, google/gemini-3-pro-preview, perplexity/google/gemini-3-pro-preview, replicate/google/gemini-3-pro, vertex/gemini-3-pro-preview, vertex_ai/gemini-3-pro-preview

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works