RankingEffort benchmarks

Gemma 4 31B IT effort benchmarks

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

Model

Gemma 4 31B IT

38 measured results · 4 reported effort labels · 25 benchmark/harness combinations. Model evidence and sources →

Capability score evidence

Gemma 4 31B IT · Reasoning: 13.2 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	15.3	+2.1
Datacurve	11.4	-1.8
LiveCodeBench	13.1	-0.1
Scale	14.4	+1.2
Terminal-Bench	13.2	-0.0
Cognition	13.6	+0.5
LiveBench	13.4	+0.2
SWE-rebench	13.5	+0.3
Epoch AI	13.4	+0.2
Vals AI	12.8	-0.4
Provider reports · Anthropic	13.2	+0.0
Provider reports · Moonshot AI	13.2	-0.0
Provider reports · Meta	13.2	-0.0
Provider reports · Mistral	13.2	+0.0
All provider reports	13.2	-0.0

Every benchmark family

Removed evidence	Recomputed score	Change
arc-agi	15.2	+2.0
deepswe	11.4	-1.8
ifbench	12.3	-0.9
itbench	12.3	-0.9
briefcase	13.8	+0.6
gpqa	12.6	-0.6
omniscience	13.8	+0.6
mmmu-pro	13.7	+0.5
epoch-game-puzzles	12.7	-0.5
frontiercode	13.6	+0.5
simpleqa	13.6	+0.4
harvey	13.6	+0.4
enterprise-ops	13.6	+0.4
mmlu-pro	13.5	+0.3
swe-rebench	13.5	+0.3
hle	13.5	+0.3
gdpval	13.5	+0.3
aa-lcr	13.0	-0.2
terminal-bench	13.4	+0.2
scicode	13.0	-0.2
multi-swe-bench	13.0	-0.2
livebench-instructions	13.4	+0.2
critpt	13.1	-0.1
apex-agents	13.3	+0.1
livebench-language	13.3	+0.1
automationbench	13.3	+0.1
swe-atlas-qna	13.1	-0.1
frontiermath	13.3	+0.1
livebench-coding	13.1	-0.1
arc-agi-3	13.1	-0.1
vibe-code	13.1	-0.1
livebench-reasoning	13.1	-0.1
gdp-pdf	13.3	+0.1
gmmlu	13.3	+0.1
vals-finance-agent	13.1	-0.1
swe-atlas-test-writing	13.1	-0.0
vals-legal-research	13.1	-0.0
vals-code-migration	13.2	-0.0
math500	13.2	+0.0
tau-bench	13.2	+0.0
analyst-agent	13.2	+0.0
aime	13.2	+0.0
livebench-data	13.2	+0.0
swe-atlas-refactoring	13.2	-0.0
livebench-math	13.2	+0.0
vals-excel-modeling	13.2	-0.0
livecodebench	13.2	-0.0
enigma-eval	13.2	+0.0
swe-bench-pro	13.2	+0.0

What evidence is missing from the fit?

Across all collected settings for this model: 38 observations, 35 contributing, 0 matched without graph weight and 3 excluded. Counts do not establish rank eligibility.

2 · Benchmark family or source protocol has not been reviewed
1 · Effort is not identified

Inspect every observation and exclusion →

Capability profile

One configuration, seven capabilities

Comparison score · 0–100

AGemma 4 31B IT · Reasoning4 of 7 capabilities supported

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

Agentic
A13.4Supported
Hard reasoning
A21.2Supported
Coding
A15.8Supported
Human pref
Unknown
Knowledge
A17.3Supported
Multimodal
A19.6Preliminary
Long context
A21.3Preliminary

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	Reasoning	Non-reasoning	Unspecified
AA-Briefcase EloArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details AA-Briefcase is an agentic knowledge work benchmark developed by Artificial Analysis. AA-Briefcase Elo is a combined metric that aggregates rubric pass rate, analytical quality Elo and presentation Elo · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-09-12.	Not reported	376.57 Elo Reported settings Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b	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	69.67% Reported settings Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b	46.67% Reported settings Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning	Not reported
AutomationBench-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of task objectives completed with no guardrail violations · Higher is better · Benchmark developed by Zapier · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	4.93% Reported settings Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b	Not reported	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	1.43% Reported settings Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b	0% Reported settings Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning	Not reported
EnterpriseOps-Gym-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Overall task success rate across all eight enterprise domains (oracle tool mode) · Benchmark developed by ServiceNow Research · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	28.35% Reported settings Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b	Not reported	Not reported
GDP.pdf: All-passArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of attempts where every atomic criterion passed · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	6% Reported settings Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b	Not reported	Not reported
GDPval-AA v2 LeaderboardArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Elo rating for performance on real-world work tasks · Anchored to a human baseline of 1,000 · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-09-12.	Not reported	755.45 Elo Reported settings Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b	691.46 Elo Reported settings Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning	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	85.66% Reported settings Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b	76.26% Reported settings Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning	Not reported
Harvey LAB-AA: Criterion Pass RateArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of atomic pass/fail rubric criteria the deliverables satisfy, graded by a single LLM judge · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	47.23% Reported settings Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b	Not reported	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	23.63% Reported settings Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b	11.82% Reported settings Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning	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	75.58% Reported settings Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b	53.47% Reported settings Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning	Not reported
ITBench-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Combined public and private Site Reliability Engineering (SRE) tasks · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	37.29% Reported settings Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b	Not reported	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	73.41% Reported settings Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b	70.35% Reported settings Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning	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	-47.93 Reported settings Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b	-51.68 Reported settings Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning	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	20.03% Reported settings Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b	16.63% Reported settings Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning	Not reported
SciCodeArtificial 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	45.49% Reported settings Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b	Not reported	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	59.94% Reported settings Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b	65.5% Reported settings Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning	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	14.85% Reported settings Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b	8.87% Reported settings Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning	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	36.36% Reported settings Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b	30.3% Reported settings Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning	Not reported
Terminal-Bench v2.1Artificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by the Laude Institute and open-source contributors · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	43.45% Reported settings Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b	29.21% Reported settings Gemma 4 31B (Non-reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning	Not reported
Terminal-Bench v4.0Artificial Analysis · mini-SWE-agent v2.4.6; 66 tasks; pass@1 averaged over 3 repeats; 500 steps; task timeout up to 8 hours Benchmark details Benchmark developed by the Laude Institute, Stanford, and open-source contributors · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	0% Reported settings Gemma 4 31B (Reasoning); Model source: https://artificialanalysis.ai/models/gemma-4-31b	Not reported	Not reported
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.	5% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemma-4-31b-it_minimal; run=4LjmaK4MRrxuDXUiZsvA3o; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	Not reported	Not reported
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.	75.76% Reported settings Epoch AI Inspect; task 1.0.11; scorer choice; model=gemma-4-31b-it_minimal; run=P5L8qbXo42vTvbU3UvTNjk; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	Not reported	Not reported
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.	73.33% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=gemma-4-31b-it_minimal; run=jFJucVunfLgoQqoFvPVQWP; 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	10.4% Reported settings Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=gemma-4-31b-it; run=D5cbXacPnJ8akq2jAtifEQ; mean accuracy; https://epoch.ai/data/benchmarks.csv

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

Gemma 4 31B IT effort benchmarks

Gemma 4 31B IT

Capability score evidence

One configuration, seven capabilities

Agentic

Hard reasoning

Coding

Human pref

Knowledge

Multimodal

Long context