RankingEffort benchmarks

Gemini 3 Flash Preview effort benchmarks

Compare measured Low, Medium, High and other settings. Every number keeps its source.

Model

Gemini 3 Flash Preview

56 measured results · 7 reported effort labels · 36 benchmark/harness combinations. Model evidence and sources →

Capability score evidence

Gemini 3 Flash Preview · Reasoning: 30.5 overall comparison score. Meets the overall evidence requirements.

Which sources carry the weight?

Artificial Analysis · 100.0% direct comparison weight · independent

These shares describe the comparisons entering the fit, not fractions of the final score.

How sensitive is this score?

Remove one evaluator or family and refit the graph against the same overall panel. Values use the matching dataset audited 2026-09-12. These are sensitivity checks, not confidence intervals; ranking eligibility may also change.

Removed evidence	Recomputed score	Change
Artificial Analysis	Comparison path lost	—
ARC Prize	34.6	+4.1
Datacurve	27.5	-3.0
LiveCodeBench	30.4	-0.2
Scale	32.2	+1.6
Terminal-Bench	30.7	+0.1
Cognition	31.5	+1.0
LiveBench	30.8	+0.3
SWE-rebench	31.1	+0.6
Epoch AI	30.3	-0.2
Vals AI	29.9	-0.6
Provider reports · Anthropic	30.5	+0.0
Provider reports · Moonshot AI	30.5	-0.0
Provider reports · Meta	30.5	-0.0
Provider reports · Mistral	30.5	+0.0
All provider reports	30.5	-0.1

Every benchmark family

Removed evidence	Recomputed score	Change
arc-agi	34.5	+3.9
deepswe	27.5	-3.0
tau-bench	32.5	+2.0
omniscience	29.3	-1.2
frontiercode	31.5	+1.0
epoch-game-puzzles	29.6	-0.9
ifbench	29.8	-0.7
simpleqa	31.2	+0.7
terminal-bench	31.2	+0.7
apex-agents	29.9	-0.7
hle	31.2	+0.6
gpqa	29.9	-0.6
swe-rebench	31.1	+0.6
mmlu-pro	31.1	+0.6
mmmu-pro	31.1	+0.5
gmmlu	30.2	-0.4
scicode	30.9	+0.4
multi-swe-bench	30.3	-0.3
gdp-pdf	30.8	+0.3
livebench-instructions	30.8	+0.2
frontiermath	30.8	+0.2
livebench-language	30.8	+0.2
swe-atlas-qna	30.4	-0.2
gdpval	30.7	+0.2
arc-agi-3	30.4	-0.2
harvey	30.4	-0.2
aime	30.7	+0.1
aa-lcr	30.7	+0.1
livebench-coding	30.4	-0.1
vibe-code	30.4	-0.1
livebench-reasoning	30.4	-0.1
swe-atlas-test-writing	30.5	-0.1
vals-finance-agent	30.5	-0.1
math500	30.5	-0.1
vals-legal-research	30.5	-0.1
analyst-agent	30.6	+0.1
vals-code-migration	30.5	-0.1
livecodebench	30.5	-0.0
swe-atlas-refactoring	30.5	-0.0
enterprise-ops	30.6	+0.0
critpt	30.5	-0.0
livebench-math	30.6	+0.0
itbench	30.6	+0.0
livebench-data	30.6	+0.0
vals-excel-modeling	30.5	-0.0
briefcase	30.6	+0.0
enigma-eval	30.5	-0.0
swe-bench-pro	30.6	+0.0
automationbench	30.5	-0.0

What evidence is missing from the fit?

Across all collected settings for this model: 58 observations, 49 contributing, 0 matched without graph weight and 9 excluded. Counts do not establish rank eligibility.

2 · Benchmark family or source protocol has not been reviewed
5 · Effort is not identified
2 · No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately

Inspect every observation and exclusion →

Capability profile

One configuration, seven capabilities

Comparison score · 0–100

AGemini 3 Flash Preview · Reasoning4 of 7 capabilities supported

Gaps are unknown, not zero. Hollow points are preliminary.

Agentic
A24.7Supported
Hard reasoning
A35.7Supported
Coding
A26.8Supported
Human pref
Unknown
Knowledge
A45.7Supported
Multimodal
A43.9Preliminary
Long context
A37.0Preliminary

Each profile belongs to the named configuration. Capability scores use a shared panel for all axes, distinct from the overall ranking panel; they are not accuracy percentages or direct head-to-head wins.

Compare this configuration →Explore the model evidence profile →

These are published benchmark scores. Supported effort estimates also appear on the Capability leaderboard. Results from different harnesses occupy different rows. Missing cells stay unknown; no scores are copied between effort levels.

Benchmark / source	Minimal	Low	Medium	High	Reasoning	Non-reasoning	Unspecified
AIME 2025Artificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	97% Reported settings Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning	55.67% Reported settings Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash	Not reported
APEX-Agents-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	27.73% Reported settings Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning	Not reported	Not reported
AA-LCR v1.1Artificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	78% Reported settings Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning	55.33% Reported settings Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash	Not reported
CritPtArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by Argonne and UIUC, with contributions from 60+ researchers globally · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	8.57% Reported settings Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning	1.43% Reported settings Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash	Not reported
Global-MMLU-LiteArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	91.44% Reported settings Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning	92.75% Reported settings Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash	Not reported
GPQA DiamondArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	89.8% Reported settings Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning	81.21% Reported settings Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash	Not reported
Humanity's Last ExamArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	36.56% Reported settings Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning	14.97% Reported settings Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash	Not reported
IFBenchArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	77.96% Reported settings Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning	55.1% Reported settings Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash	Not reported
LiveCodeBenchArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	90.79% Reported settings Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning	79.68% Reported settings Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash	Not reported
MLCR-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of tasks judged accurate, complete, and concise · Expert + compound (hard) sets · Benchmark developed by Wisedocs · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	11.11% Reported settings Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning	11.67% Reported settings Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash	Not reported
MMLU-ProArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	89.03% Reported settings Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning	88.22% Reported settings Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash	Not reported
MMMU-ProArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	79.94% Reported settings Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning	78.55% Reported settings Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash	Not reported
AA-Omniscience IndexArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct. · Evaluation results measured independently by Artificial Analysis Unit: index. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	10.13 Reported settings Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning	-4.32 Reported settings Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash	Not reported
AA-Omniscience AccuracyArtificial Analysis · 6000 questions; 1 attempt; correct-answer share; GPT-5.6 Luna medium grader Benchmark details AA-Omniscience Accuracy (higher is better) measures the proportion of correctly answered questions out of all questions, regardless of whether the model chooses to answer · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	53.43% Reported settings Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning	45.78% Reported settings Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash	Not reported
𝜏²-Bench TelecomArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	80.41% Reported settings Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning	43.27% Reported settings Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash	Not reported
𝜏³-BankingArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by Sierra Research · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	20.82% Reported settings Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning	Not reported	Not reported
Terminal-Bench HardArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	38.64% Reported settings Gemini 3 Flash Preview (Reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash-reasoning	31.82% Reported settings Gemini 3 Flash Preview (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemini-3-flash	Not reported
ARC-AGI-2ARC Prize · v2 Semi-Private Benchmark details Original public board. Configuration and task coverage may differ; inspect source. Unit: percent. Source collected 2026-09-12.	3.33% Reported settings Gemini 3 Flash Preview (Minimal); Source model ID: gemini-3-flash-preview-thinking-minimal; 120 tasks	1.25% Reported settings Gemini 3 Flash Preview (Low); Source model ID: gemini-3-flash-preview-thinking-low; 120 tasks	12.78% Reported settings Gemini 3 Flash Preview (Medium); Source model ID: gemini-3-flash-preview-thinking-medium; 120 tasks	33.61% Reported settings Gemini 3 Flash Preview (High); Source model ID: gemini-3-flash-preview-thinking-high; 120 tasks	Not reported	Not reported	Not reported
Epoch · Chess Puzzles · v1.0.0Epoch AI · Epoch AI Inspect; task 1.0.0; scorer model_extracted_exact_match Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	38% Reported settings Epoch AI Inspect; task 1.0.0; scorer model_extracted_exact_match; model=gemini-3-flash-preview; run=ZMRExFd2WEEwTRSQPLXXwu; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · Chess Puzzles · v1.1.6Epoch AI · Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	40% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3-flash-preview_high; run=HVtbACyemDaTPW5XUDC6Jf; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	Not reported	Not reported
Epoch · FrontierMath Tier 4 · v2.0.0Epoch AI · Epoch AI Inspect; task 2.0.0; scorer verification_code Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. FrontierMath was developed with OpenAI funding and unequal access to part of the question set; this result is from Epoch's evaluation. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	17.07% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gemini-3-flash-preview; run=ZczEhu69FQ9Cnns8NT6ew4; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · FrontierMath Tiers 1–3 · v2.0.0Epoch AI · Epoch AI Inspect; task 2.0.0; scorer verification_code Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. FrontierMath was developed with OpenAI funding and unequal access to part of the question set; this result is from Epoch's evaluation. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	51.23% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gemini-3-flash-preview; run=EtgrDq6ei6kZe8K7QbXUe3; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · GPQA diamond · v1.0.11Epoch AI · Epoch AI Inspect; task 1.0.11; scorer choice Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	89.39% Reported settings Epoch AI Inspect; task 1.0.11; scorer choice; model=gemini-3-flash-preview_high; run=gVdraDT3pXmaExP9VbqME4; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	Not reported	Not reported
Epoch · GPQA diamond · v1.0.3Epoch AI · Epoch AI Inspect; task 1.0.3; scorer choice Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	83.21% Reported settings Epoch AI Inspect; task 1.0.3; scorer choice; model=gemini-3-flash-preview; run=oAu9CZSNPZgwiwKnoNpM8Q; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · Mystery Game Puzzles · v1.0.4 · Exact moveEpoch AI · Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. Unit: percent. Source collected 2026-09-12.	25% Reported settings Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer; model=gemini-3-flash-preview_minimal; run=njpkLAWZTvept6tnkraYrR; mean accuracy; https://epoch.ai/data/benchmarks.csv	26% Reported settings Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer; model=gemini-3-flash-preview_low; run=ZQMcTQjHcDSevCN2dYYHKY; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	20% Reported settings Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer; model=gemini-3-flash-preview_high; run=MvdunHkVURna3JuyDjhzEc; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	Not reported	Not reported
Epoch · OTIS Mock AIME 2024-2025 · v1.0.3Epoch AI · Epoch AI Inspect; task 1.0.3; scorer model_extracted_exact_match Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	92.78% Reported settings Epoch AI Inspect; task 1.0.3; scorer model_extracted_exact_match; model=gemini-3-flash-preview; run=H3E7EjjXfGCPnm9ooLdmAo; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · OTIS Mock AIME 2024-2025 · v1.1.6Epoch AI · Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	95.56% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemini-3-flash-preview_high; run=a4uE6KgMhGSUjcnemRnbkA; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	Not reported	Not reported
Epoch · SimpleQA Verified · v1.2.0Epoch AI · Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	66.8% Reported settings Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=gemini-3-flash-preview_high; run=7cc6cDCXjsPjtKt36bbeMR; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	Not reported	Not reported
Vals AI · Finance Agent v2Vals AI · Vals FAB v2 shared six-tool harness; two-hour task limit Benchmark details Overall weighted rubric accuracy, averaged over three runs on 450 tasks. Dealbreaker failures and timeouts score zero. Related categories and all-pass scores are not additional votes. Three-model judge panel; private test set. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	42.55% Reported settings {"checkpoint":"gemini-3-flash-preview","evaluatorModel":"google/gemini-3-flash-preview","sourceUpdatedOn":"2026-09-10","reasoning_effort":"high","compute_effort":null,"reasoning":null,"temperature":1,"top_p":null,"max_output_tokens":65536,"verbosity":null,"provider":"Google","harness":null}	Not reported	Not reported	Not reported
Vals AI · Code Migration v1Vals AI · Vals Code Migration shared agent harness Benchmark details Hidden behavior-test pass rate, equally weighted across 40 repositories (30 CLI and 10 COBOL-to-Java). Anti-cheat failures score zero. Code-quality ratings and language splits are not additional votes. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	6.39% Reported settings {"checkpoint":"gemini-3-flash-preview","evaluatorModel":"google/gemini-3-flash-preview","sourceUpdatedOn":"2026-09-10","reasoning_effort":"high","compute_effort":null,"reasoning":null,"temperature":1,"top_p":null,"max_output_tokens":65536,"verbosity":null,"provider":"Google","harness":null}	Not reported	Not reported	Not reported
Vals AI · Legal Research Bench v1Vals AI · Vals Legal Research shared five-tool harness; three-hour task limit Benchmark details All-pass accuracy on 208 private legal research tasks. Every expert rubric check must pass; GPT-5.4 judges responses. Partial-credit scores and practice-area splits are not additional votes. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	18.27% Reported settings {"checkpoint":"gemini-3-flash-preview","evaluatorModel":"google/gemini-3-flash-preview","sourceUpdatedOn":"2026-09-10","reasoning_effort":"high","compute_effort":null,"reasoning":null,"temperature":1,"top_p":null,"max_output_tokens":65536,"verbosity":null,"provider":"Google","harness":null}	Not reported	Not reported	Not reported
Vals AI · Excel Modeling Benchmark v1Vals AI · Vals EMB shared workbook agent harness; 3.5-hour task limit Benchmark details Mean of seven equally weighted task categories. Template submissions use recalculated Excel cell accuracy; scratch submissions use rubric checks judged by GPT-5.4 Mini XHigh. Partial credit does not mean task completion. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	26.02% Reported settings {"checkpoint":"gemini-3-flash-preview","evaluatorModel":"google/gemini-3-flash-preview","sourceUpdatedOn":"2026-09-10","reasoning_effort":"high","compute_effort":null,"reasoning":null,"temperature":1,"top_p":null,"max_output_tokens":65536,"verbosity":null,"provider":"Google","harness":null}	Not reported	Not reported	Not reported
Vals AI · MMLU-Pro v1Vals AI · Vals MMLU-Pro five-shot chain-of-thought; regex answer grading Benchmark details Mean accuracy across 14 subjects under Vals five-shot prompting. Subject splits share one family and are not additional votes. Vals labels this benchmark archived; it is historical corroboration, not ongoing frontier evaluation. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	88.59% Reported settings {"checkpoint":"gemini-3-flash-preview","evaluatorModel":"google/gemini-3-flash-preview","sourceUpdatedOn":"2026-09-01","reasoning_effort":"high","compute_effort":null,"reasoning":null,"temperature":1,"top_p":null,"max_output_tokens":65536,"verbosity":null,"provider":"Google","harness":null}	Not reported	Not reported	Not reported
Vals AI · Terminal-Bench 2.1Vals AI · Vals Terminus 2 harness; pass@1 on 89 tasks Benchmark details Overall task pass rate under the shared Terminus 2 configuration. All task tests must pass. Difficulty splits share one family. Fable 5 and Opus 5 mixed-checkpoint fallback runs are excluded. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	53.93% Reported settings {"checkpoint":"gemini-3-flash-preview","evaluatorModel":"google/gemini-3-flash-preview","sourceUpdatedOn":"2026-09-10","reasoning_effort":"high","compute_effort":null,"reasoning":null,"temperature":1,"top_p":null,"max_output_tokens":65536,"verbosity":null,"provider":"Google","harness":null}	Not reported	Not reported	Not reported
Vals AI · Vibe Code Bench v1.1Vals AI · Vals modified OpenHands harness; five hours or 1,000 turns per app Benchmark details Mean app test pass rate on the canonical v1.1 test set. Browser Use executes workflow tests; each test requires at least 90% of its substeps. Automated judging can introduce error. Alternate agents are excluded. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	20.2% Reported settings {"checkpoint":"gemini-3-flash-preview","evaluatorModel":"google/gemini-3-flash-preview","sourceUpdatedOn":"2026-09-10","reasoning_effort":"high","compute_effort":null,"reasoning":null,"temperature":1,"top_p":null,"max_output_tokens":65536,"verbosity":null,"provider":"Google","harness":"OpenHands"}	Not reported	Not reported	Not reported
Vals AI · Harvey Legal Agent Benchmark v1Vals AI · Vals Harvey held-out legal file-work protocol; internet disabled Benchmark details Mean task resolution across two judges (GPT-5.5 Medium and Sonnet 4.6), requiring every criterion to pass. Criteria pass rates and practice-area splits do not add votes. Shared Harvey family; Fable 5 fallback run excluded. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	0% Reported settings {"checkpoint":"gemini-3-flash-preview","evaluatorModel":"google/gemini-3-flash-preview","sourceUpdatedOn":"2026-09-10","reasoning_effort":"high","compute_effort":null,"reasoning":null,"temperature":1,"top_p":null,"max_output_tokens":65536,"verbosity":null,"provider":"Google","harness":null}	Not reported	Not reported	Not reported

What these comparisons mean

Each source reports its own effort labels. Matching labels do not establish equal compute budgets or identical fallback behavior. Open Reported settings to inspect the exact model name, agent and task coverage. Multiple results at one level remain visible rather than selecting the best. Source-reported None or Non-reasoning labels are not treated as evidence that an API supports those settings.

These measurements use their own dated source collection. The leaderboard fits identified configurations jointly; it contains no pooled model ratings. Explicit thinking budgets are separate configurations. Read the methodology.

Download all effort benchmark results · 7,424 results across 240 models · Collected 2026-09-12

Gemini 3 Flash Preview effort benchmarks