RankingEffort benchmarks

Gemini 2.5 Pro effort benchmarks

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

Model

Gemini 2.5 Pro

31 measured results · 6 reported effort labels · 28 benchmark/harness combinations. Model evidence and sources →

Capability score evidence

Gemini 2.5 Pro · Reasoning: 12.9 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	15.1	+2.2
Datacurve	11.2	-1.8
LiveCodeBench	12.8	-0.1
Scale	14.1	+1.2
Terminal-Bench	13.0	+0.0
Cognition	13.5	+0.5
LiveBench	13.2	+0.2
SWE-rebench	13.2	+0.3
Epoch AI	13.1	+0.1
Vals AI	12.6	-0.4
Provider reports · Anthropic	12.9	+0.0
Provider reports · Moonshot AI	12.9	-0.0
Provider reports · Meta	12.9	-0.0
Provider reports · Mistral	12.9	+0.0
All provider reports	12.9	-0.0

Every benchmark family

Removed evidence	Recomputed score	Change
arc-agi	15.0	+2.1
deepswe	11.2	-1.8
omniscience	12.1	-0.9
gdpval	13.6	+0.6
math500	13.5	+0.6
briefcase	13.5	+0.5
epoch-game-puzzles	12.4	-0.5
frontiercode	13.5	+0.5
gmmlu	12.5	-0.5
terminal-bench	13.4	+0.5
gpqa	12.5	-0.4
simpleqa	13.4	+0.4
mmmu-pro	13.4	+0.4
automationbench	13.4	+0.4
hle	13.3	+0.4
critpt	12.6	-0.3
swe-rebench	13.2	+0.3
tau-bench	13.2	+0.3
gdp-pdf	12.7	-0.2
ifbench	13.1	+0.2
scicode	12.8	-0.2
multi-swe-bench	12.8	-0.2
livecodebench	12.8	-0.2
aa-lcr	12.8	-0.2
livebench-instructions	13.1	+0.2
harvey	12.8	-0.1
livebench-language	13.1	+0.1
apex-agents	13.1	+0.1
swe-atlas-qna	12.8	-0.1
frontiermath	13.1	+0.1
livebench-coding	12.9	-0.1
arc-agi-3	12.9	-0.1
vibe-code	12.9	-0.1
livebench-reasoning	12.9	-0.1
aime	12.9	-0.1
mmlu-pro	13.0	+0.1
vals-finance-agent	12.9	-0.1
swe-atlas-test-writing	12.9	-0.0
vals-legal-research	12.9	-0.0
vals-code-migration	12.9	-0.0
analyst-agent	13.0	+0.0
itbench	12.9	-0.0
livebench-data	13.0	+0.0
livebench-math	13.0	+0.0
swe-atlas-refactoring	12.9	-0.0
vals-excel-modeling	12.9	-0.0
enigma-eval	13.0	+0.0
swe-bench-pro	13.0	+0.0
enterprise-ops	12.9	-0.0

What evidence is missing from the fit?

Across all collected settings for this model: 55 observations, 26 contributing, 0 matched without graph weight and 29 excluded. Counts do not establish rank eligibility.

1 · Benchmark family or source protocol has not been reviewed
4 · Effort is not identified
16 · No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately
8 · Supporting evidence outside the reviewed capability core

Inspect every observation and exclusion →

Capability profile

One configuration, seven capabilities

Comparison score · 0–100

AGemini 2.5 Pro · Reasoning4 of 7 capabilities supported

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

Agentic
A10.7Supported
Hard reasoning
A16.5Supported
Coding
A14.1Supported
Human pref
Unknown
Knowledge
A22.6Supported
Multimodal
A22.5Preliminary
Long context
A20.3Preliminary

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	Thinking 1K	Thinking 8K	Thinking 16K	Thinking 32K	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	Not reported	Not reported	Not reported	315.4 Elo Reported settings Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
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	87.67% Reported settings Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified	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	69% Reported settings Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified	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	Not reported	Not reported	Not reported	2.17% Reported settings Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified	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	2.57% Reported settings Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified	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	Not reported	Not reported	Not reported	10.2% Reported settings Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified	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	Not reported	Not reported	Not reported	615.9 Elo Reported settings Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified	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	90.31% Reported settings Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified	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	84.44% Reported settings Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified	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	22.52% Reported settings Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified	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	48.71% Reported settings Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified	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	80.11% Reported settings Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
MATH-500Artificial 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	96.73% Reported settings Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified	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	86.19% Reported settings Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified	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	74.91% Reported settings Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified	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	-16.35 Reported settings Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified	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	39.05% Reported settings Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified	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	Not reported	Not reported	Not reported	46.3% Reported settings Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified	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	54.09% Reported settings Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified	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	9.69% Reported settings Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified	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	26.52% Reported settings Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified	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	Not reported	Not reported	Not reported	28.46% Reported settings Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified	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	Not reported	Not reported	Not reported	0% Reported settings Gemini 2.5 Pro; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/gemini-2-5-pro; Mode from evaluator isReasoning metadata; effort budget not specified	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.	0% Reported settings Gemini 2.5 Pro (Thinking 1K); Source model ID: gemini-2-5-pro-2025-06-17-thinking-1k; 120 tasks	2.92% Reported settings Gemini 2.5 Pro (Thinking 8K); Source model ID: gemini-2-5-pro-2025-06-17-thinking-8k; 120 tasks	4.03% Reported settings Gemini 2.5 Pro (Thinking 16K); Source model ID: gemini-2-5-pro-2025-06-17-thinking-16k; 120 tasks	4.86% Reported settings Gemini 2.5 Pro (Thinking 32K); Source model ID: gemini-2-5-pro-2025-06-17-thinking-32k; 120 tasks	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	20% Reported settings Epoch AI Inspect; task 1.0.0; scorer model_extracted_exact_match; model=gemini-2.5-pro; run=mQ3UwD6hUioWSp2s2oELY4; mean accuracy; https://epoch.ai/data/benchmarks.csv
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	0% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gemini-2.5-pro; run=2z7kL9DpfvY44T9Wo99FYx; 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	24.56% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=gemini-2.5-pro; run=FkywQ2KS4AkLPzjSPmhHcS; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · GPQA diamond · v1.0.1Epoch AI · Epoch AI Inspect; task 1.0.1; 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	85.29% Reported settings Epoch AI Inspect; task 1.0.1; scorer choice; model=gemini-2.5-pro; run=cqUZ6gcq2HBnShFRWvKjGr; 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

Gemini 2.5 Pro effort benchmarks

Gemini 2.5 Pro

Capability score evidence

One configuration, seven capabilities

Agentic

Hard reasoning

Coding

Human pref

Knowledge

Multimodal

Long context