RankingEffort benchmarks

Gemini 3.7 Flash · Medium

Compare models

97 measured results · 4 effort settings · 67 benchmark/harness combinations

Model evidence and sources →

Change model

Model

Current configurationSources

Compare with

Choose a second model and its effort to see both profiles and benchmark differences below.

Compare withModel and configuration

Capability profile

One configuration, seven capabilities

Comparison score · 0–100

AGemini 3.7 Flash · Medium3 of 7 capabilities supported

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

Agentic
A62.2Supported
Hard reasoning
A46.0Supported
Coding
A70.9Supported
Human pref
Unknown
Knowledge
A56.3Preliminary
Multimodal
A65.3Preliminary
Long context
A69.1Preliminary

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.

Capability score evidence

Gemini 3.7 Flash · Medium: 60.9 overall comparison score. Meets the overall evidence requirements.

6 areas measured. The available task mix affects this estimate; missing areas remain unknown.

Shared-result disagreement. This aggregate order conflicts with matched benchmark results against 1 other configurations. Different test coverage and opponents affect the fit. Inspect published results before treating the rank as conclusive.

Which sources carry the weight?

ARC Prize · 31.0% direct comparison weight · independent of the model provider
Artificial Analysis · 27.4% direct comparison weight · independent of the model provider
Cognition · 21.6% direct comparison weight · independent of the model provider
Datacurve · 20.1% direct comparison weight · independent of the model provider

Which benchmark families carry the weight?

ARC-AGI · 31.0% direct comparison weight
FrontierCode · 21.6% direct comparison weight
DeepSWE · 20.1% direct comparison weight
Humanity’s Last Exam · 3.2% direct comparison weight
GPQA · 3.2% direct comparison weight
Other families (8) · 21.1% direct comparison weight

These shares describe direct comparison weight, not fractions of the final score or confidence. Source balancing does not give every family equal weight or remove correlations between overlapping sources.

DeepSWE v1.1 review: Epoch AI reported grading errors in at least 23 of 113 tasks. These published results remain included. Review their limitations in Epoch's review when interpreting this evidence.

How sensitive is this score?

The audit removes one source at a time and refits against the same overall reference panel. These published results use the matching dataset audited 2026-10-20.

Both ranks use the same surviving configurations for each removal. The cohort starts with 444 configurations supported in the original audit, including separate effort settings. These are diagnostic positions, not the default leaderboard ranks. Eligibility is not rechecked after removal.

What changes when a source is removed?
Removed source	Rank before → after	Rank movement	Cohort remaining / lost support	Score after (change)
Artificial Analysis	51 → 49	Up 2	203 remaining / 241 lost	62.6 (+1.7 points)
ARC Prize	51 → 43	Up 8	444 remaining / 0 lost	72.9 (+12.0 points)
Datacurve	51 → 55	Down 4	444 remaining / 0 lost	54.3 (-6.6 points)
LiveCodeBench	51 → 51	No movement	444 remaining / 0 lost	60.9 (+0.0 points)
Scale	51 → 51	No movement	444 remaining / 0 lost	62.3 (+1.4 points)
Terminal-Bench	51 → 51	No movement	444 remaining / 0 lost	60.8 (-0.1 points)
Cognition	51 → 59	Down 8	444 remaining / 0 lost	53.7 (-7.2 points)
LiveBench	51 → 51	No movement	443 remaining / 1 lost	61.9 (+1.0 points)
SWE-rebench	51 → 51	No movement	444 remaining / 0 lost	60.3 (-0.6 points)
Epoch AI	51 → 53	Down 2	431 remaining / 13 lost	62.4 (+1.5 points)
Vals AI	51 → 49	Up 2	443 remaining / 1 lost	60.3 (-0.6 points)
Provider reports · Anthropic	51 → 51	No movement	444 remaining / 0 lost	60.9 (+0.0 points)
Provider reports · Moonshot AI	51 → 51	No movement	444 remaining / 0 lost	60.5 (-0.4 points)
Provider reports · Meta	51 → 51	No movement	444 remaining / 0 lost	60.9 (+0.0 points)
Provider reports · Mistral	51 → 51	No movement	444 remaining / 0 lost	60.9 (+0.0 points)
Provider reports · OpenAI	51 → 52	Down 1	444 remaining / 0 lost	60.9 (-0.1 points)
All provider reports	51 → 52	Down 1	444 remaining / 0 lost	60.5 (-0.4 points)

Lost support means a configuration no longer has a comparison path to the complete reference panel. Its rank is unavailable. A surviving path alone does not establish leaderboard eligibility.

Overlapping sources may remain correlated even with source balancing. Leave-one-source-out movement is a sensitivity diagnostic, not a spread of source-specific ranks or a confidence measure. Scoring methodology · Dated configuration audit

Every benchmark family

Removed evidence	Recomputed score	Change
arc-agi	70.4	+9.5
frontiercode	53.7	-7.2
deepswe	54.3	-6.6
arc-agi-3	59.2	-1.7
hle	61.9	+1.0
simpleqa	61.7	+0.8
enterprise-ops	60.2	-0.8
mmmu-pro	61.5	+0.6
swe-rebench	60.3	-0.6
critpt	61.4	+0.5
epoch-game-puzzles	60.4	-0.5
mmlu-pro	61.4	+0.4
gdpval	61.3	+0.4
ifbench	60.6	-0.3
multi-swe-bench	60.6	-0.3
swe-atlas-qna	60.6	-0.3
aime	60.7	-0.2
livebench-instructions	61.1	+0.2
harvey	60.7	-0.2
automationbench	60.7	-0.2
swe-atlas-test-writing	60.7	-0.2
gdp-pdf	61.1	+0.2
gpqa	60.8	-0.2
livebench-language	61.1	+0.1
aa-lcr	60.8	-0.1
terminal-bench	61.0	+0.1
vals-finance-agent	60.8	-0.1
briefcase	60.8	-0.1
livebench-coding	60.8	-0.1
livebench-data	61.0	+0.1
livebench-reasoning	60.8	-0.1
vals-tax-agent	60.8	-0.1
vals-legal-research	60.8	-0.1
vibe-code	60.8	-0.1
apex-agents	61.0	+0.1
enigma-eval	60.9	-0.1
itbench	60.9	-0.1
analyst-agent	60.9	+0.0
terminal-bench-science	60.9	+0.0
frontiermath	60.9	-0.0
tau-bench	60.9	-0.0
livebench-math	60.9	+0.0
gmmlu	60.9	-0.0
omniscience	60.9	-0.0
swe-atlas-refactoring	60.9	-0.0
math500	60.9	-0.0
swe-bench-pro	60.9	+0.0
livecodebench	60.9	+0.0
vals-excel-modeling	60.9	-0.0
vals-code-migration	60.9	-0.0

What evidence is missing from the fit?

Across all collected settings for this model: 120 observations, 85 contributing, 0 matched without graph weight and 35 excluded. Counts do not establish rank eligibility.

5 · Benchmark family or source protocol has not been reviewed
3 · Original SciCode grading defects are under review; retained as supporting evidence, excluded from aggregate and capability scores. Corrected SciCode-Verified requires a separate protocol review. Sources: https://arxiv.org/abs/2608.04975 and https://artificialanalysis.ai/evaluations/scicode
3 · Evaluator has not been reviewed for independent admission
1 · Effort is not identified
7 · Supporting evidence outside the reviewed capability core
12 · No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately
1 · Mixed source task revisions and best-of-three versus provider reporting prevent a uniform common-core unit.
3 · Narrow specialist biological, medical or security evaluation; preserved as raw evidence outside general capability scoring.

Inspect every observation and exclusion →

Benchmark results

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	Low	Medium	High	Unspecified
AA-AnalystAgentArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of tasks solved on all 5 of 5 attempts · 80 tasks, 5 attempts per task · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	60% Reported settings Gemini 3.7 Flash (High); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash	Not reported
AA-Briefcase EloArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details AA-Briefcase v1.1 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 2026-10-18.	Not reported	Not reported	1,113.53 Elo Reported settings Gemini 3.7 Flash (High); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash	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 2026-10-18.	78.67% Reported settings Gemini 3.7 Flash (Low); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-low	83% Reported settings Gemini 3.7 Flash (Medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium	81.67% Reported settings Gemini 3.7 Flash (High); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash	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 2026-10-18.	Not reported	Not reported	62.03% Reported settings Gemini 3.7 Flash (High); Model source: https://artificialanalysis.ai/models/gemini-3-7-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. CritPt is under review by its authors following external feedback · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	5.71% Reported settings Gemini 3.7 Flash (Low); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-low	9.43% Reported settings Gemini 3.7 Flash (Medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium	14.29% Reported settings Gemini 3.7 Flash (High); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash	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 2026-10-18.	Not reported	50.4% Reported settings Gemini 3.7 Flash (Medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium	Not reported	Not reported
GDP.pdf: All-pass RateArtificial 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 2026-10-18.	Not reported	Not reported	23.6% Reported settings Gemini 3.7 Flash (High); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash	Not reported
GDPval-AA v2.1 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 DeepSeek V4.1 Flash (max) at 1600 · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-10-18.	1,323.42 Elo Reported settings Gemini 3.7 Flash (Low); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-low	1,360.38 Elo Reported settings Gemini 3.7 Flash (Medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium	1,391.99 Elo Reported settings Gemini 3.7 Flash (High); Model source: https://artificialanalysis.ai/models/gemini-3-7-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 2026-10-18.	90.1% Reported settings Gemini 3.7 Flash (Low); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-low	92.12% Reported settings Gemini 3.7 Flash (Medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium	94.55% Reported settings Gemini 3.7 Flash (High); Model source: https://artificialanalysis.ai/models/gemini-3-7-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 2026-10-18.	35.13% Reported settings Gemini 3.7 Flash (Low); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-low	38.97% Reported settings Gemini 3.7 Flash (Medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium	47.87% Reported settings Gemini 3.7 Flash (High); Model source: https://artificialanalysis.ai/models/gemini-3-7-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 2026-10-18.	Not reported	Not reported	15% Reported settings Gemini 3.7 Flash (High); Model source: https://artificialanalysis.ai/models/gemini-3-7-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 2026-10-18.	84.86% Reported settings Gemini 3.7 Flash (Low); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-low	84.74% Reported settings Gemini 3.7 Flash (Medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium	85.49% Reported settings Gemini 3.7 Flash (High); Model source: https://artificialanalysis.ai/models/gemini-3-7-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 2026-10-18.	22.13 Reported settings Gemini 3.7 Flash (Low); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-low	23.7 Reported settings Gemini 3.7 Flash (Medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium	26.48 Reported settings Gemini 3.7 Flash (High); Model source: https://artificialanalysis.ai/models/gemini-3-7-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 2026-10-18.	53.57% Reported settings Gemini 3.7 Flash (Low); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-low	54% Reported settings Gemini 3.7 Flash (Medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium	55.32% Reported settings Gemini 3.7 Flash (High); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash	Not reported
SciCodeArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark curated by scientists across 16 disciplines. SciCode is under review following an independent audit of the dataset · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	55.67% Reported settings Gemini 3.7 Flash (Low); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-low	59.84% Reported settings Gemini 3.7 Flash (Medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium	57.18% Reported settings Gemini 3.7 Flash (High); Model source: https://artificialanalysis.ai/models/gemini-3-7-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 2026-10-18.	29.48% Reported settings Gemini 3.7 Flash (Low); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-low	35.46% Reported settings Gemini 3.7 Flash (Medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium	32.78% Reported settings Gemini 3.7 Flash (High); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash	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 2026-10-18.	79.78% Reported settings Gemini 3.7 Flash (Low); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-low	78.28% Reported settings Gemini 3.7 Flash (Medium); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash-medium	85.77% Reported settings Gemini 3.7 Flash (High); Model source: https://artificialanalysis.ai/models/gemini-3-7-flash	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 2026-10-18.	Not reported	Not reported	13.64% Reported settings Gemini 3.7 Flash (High); Model source: https://artificialanalysis.ai/models/gemini-3-7-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 2026-10-18.	52.92% Reported settings Gemini 3.7 Flash (Low); Source model ID: google-gemini-3-7-flash-low; 120 tasks	63.75% Reported settings Gemini 3.7 Flash (Medium); Source model ID: google-gemini-3-7-flash-medium; 120 tasks	84.58% Reported settings Gemini 3.7 Flash (High); Source model ID: google-gemini-3-7-flash-high; 120 tasks	Not reported
DeepSWE v1.1Datacurve · mini-swe-agent Benchmark details Original public board. Configuration and task coverage may differ; inspect source. Unit: percent. Source collected 2026-10-18.	53.8% Reported settings gemini-3-7-flash; Reported effort: low; 113 unique tasks; 452 attempts; 4 runs	65.5% Reported settings gemini-3-7-flash; Reported effort: medium; 113 unique tasks; 452 attempts; 4 runs	65.3% Reported settings gemini-3-7-flash; Reported effort: high; 113 unique tasks; 452 attempts; 4 runs	Not reported
FrontierCode 1.1 · extended-chiselCognition · chisel Benchmark details FrontierCode 1.1; chisel. Open each result for its exact effort, task subset, metric and protocol details. Unit: percent. Source collected 2026-10-18.	51.85% Reported settings FrontierCode 1.1; extended; 150 tasks; chisel; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0	56.27% Reported settings FrontierCode 1.1; extended; 150 tasks; chisel; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0	54.74% Reported settings FrontierCode 1.1; extended; 150 tasks; chisel; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0	Not reported
FrontierCode 1.1 · main-chiselCognition · chisel Benchmark details FrontierCode 1.1; chisel. Open each result for its exact effort, task subset, metric and protocol details. Unit: percent. Source collected 2026-10-18.	36.91% Reported settings FrontierCode 1.1; main; 100 tasks; chisel; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0	43.59% Reported settings FrontierCode 1.1; main; 100 tasks; chisel; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0	42.23% Reported settings FrontierCode 1.1; main; 100 tasks; chisel; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0	Not reported
Terminal-Bench 4.0 · minisweagentTerminal-Bench · mini-SWE-agent Benchmark details Terminal-Bench 4.0; mini-SWE-agent. Open each result for its exact effort, task subset, metric and protocol details. Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	11.2% Reported settings Terminal-Bench 4.0.0; 66 tasks; mini-SWE-agent; effort high; reported margin ±2.4 percentage points, confidence level unspecified; release date 2026-08-13; board checked 2026-10-07	Not reported
LiveBench · AMPS Hard · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	98% Reported settings LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash	Not reported
LiveBench · code completion · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	76.09% Reported settings LiveBench official task evaluation; livebench-2026-06-25-code_completion; gemini-3.7-flash-high; checkpoint=gemini-3.7-flash	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 · 8,915 results across 259 models · Collected 2026-10-18

Gemini 3.7 Flash · Medium

Compare with

One configuration, seven capabilities

Agentic

Hard reasoning

Coding

Human pref

Knowledge

Multimodal

Long context

Capability score evidence

Benchmark results