RankingEffort benchmarks

Qwen3.6-27B · Non-reasoning effort benchmarks

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

Model

Qwen3.6-27B

41 measured results · 3 reported effort labels · 24 benchmark/harness combinations. Model evidence and sources →

Capability score evidence

Qwen3.6-27B · Non-reasoning: 10.8 overall comparison score. Meets the overall evidence requirements.

Which sources carry the weight?

Artificial Analysis · 52.6% direct comparison weight · independent
Epoch AI · 47.4% 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	10.6	-0.2
ARC Prize	12.7	+1.9
Datacurve	9.2	-1.5
LiveCodeBench	10.7	-0.1
Scale	11.7	+1.0
Terminal-Bench	10.8	+0.0
Cognition	11.3	+0.5
LiveBench	11.0	+0.2
SWE-rebench	11.0	+0.2
Epoch AI	11.0	+0.3
Vals AI	10.5	-0.3
Provider reports · Anthropic	10.8	+0.0
Provider reports · Moonshot AI	10.8	-0.0
Provider reports · Meta	10.8	-0.0
Provider reports · Mistral	10.8	+0.0
All provider reports	10.7	-0.0

Every benchmark family

Removed evidence	Recomputed score	Change
arc-agi	12.6	+1.8
deepswe	9.2	-1.5
gpqa	9.4	-1.4
aime	11.5	+0.8
frontiermath	10.2	-0.6
omniscience	11.3	+0.6
frontiercode	11.3	+0.5
mmmu-pro	11.2	+0.4
tau-bench	10.4	-0.4
hle	11.1	+0.4
simpleqa	11.1	+0.3
ifbench	11.1	+0.3
epoch-game-puzzles	11.1	+0.3
mmlu-pro	11.0	+0.3
gdpval	10.5	-0.2
swe-rebench	11.0	+0.2
critpt	10.6	-0.2
multi-swe-bench	10.6	-0.1
livebench-instructions	10.9	+0.1
aa-lcr	10.6	-0.1
scicode	10.9	+0.1
harvey	10.7	-0.1
livebench-language	10.9	+0.1
swe-atlas-qna	10.7	-0.1
livebench-coding	10.7	-0.1
apex-agents	10.9	+0.1
gdp-pdf	10.9	+0.1
arc-agi-3	10.7	-0.1
livebench-reasoning	10.7	-0.1
gmmlu	10.8	+0.1
vibe-code	10.7	-0.1
vals-finance-agent	10.7	-0.0
vals-legal-research	10.7	-0.0
swe-atlas-test-writing	10.7	-0.0
briefcase	10.7	-0.0
vals-code-migration	10.7	-0.0
livebench-data	10.8	+0.0
math500	10.8	+0.0
analyst-agent	10.8	+0.0
automationbench	10.8	-0.0
livebench-math	10.8	+0.0
itbench	10.8	-0.0
terminal-bench	10.8	+0.0
swe-atlas-refactoring	10.8	-0.0
enigma-eval	10.8	+0.0
vals-excel-modeling	10.8	-0.0
enterprise-ops	10.8	+0.0
swe-bench-pro	10.8	+0.0
livecodebench	10.8	-0.0

What evidence is missing from the fit?

Across all collected settings for this model: 41 observations, 35 contributing, 0 matched without graph weight and 6 excluded. Counts do not establish rank eligibility.

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

Inspect every observation and exclusion →

Capability profile

One configuration, seven capabilities

Comparison score · 0–100

AQwen3.6-27B · Non-reasoning3 of 7 capabilities supported

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

Agentic
A21.2Supported
Hard reasoning
A14.1Supported
Coding
A10.6Preliminary
Human pref
Unknown
Knowledge
A5.9Supported
Multimodal
A16.6Preliminary
Long context
A18.7Preliminary

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.

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

Benchmark / source	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.	812.14 Elo Reported settings Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b	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.	77.33% Reported settings Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b	66.67% Reported settings Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-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.	11.05% Reported settings Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b	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.	1.14% Reported settings Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b	0.86% Reported settings Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-non-reasoning	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.	11% Reported settings Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b	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.	1,068.87 Elo Reported settings Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b	1,042.8 Elo Reported settings Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-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.	84.24% Reported settings Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b	82.93% Reported settings Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-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.	82.3% Reported settings Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b	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.	23.08% Reported settings Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b	15.06% Reported settings Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-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.	67.55% Reported settings Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b	45.71% Reported settings Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-non-reasoning	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.	74.62% Reported settings Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b	71.73% Reported settings Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-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.	-20.02 Reported settings Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b	-53.2 Reported settings Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-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.	19.6% Reported settings Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b	16.72% Reported settings Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-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.	42.82% Reported settings Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b	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.	94.15% Reported settings Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b	93.57% Reported settings Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-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.	16.7% Reported settings Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b	9.28% Reported settings Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-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.	34.85% Reported settings Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b	21.21% Reported settings Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-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.	60.67% Reported settings Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b	51.31% Reported settings Qwen3.6 27B (Non-reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b-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.	0% Reported settings Qwen3.6 27B (Reasoning); Model source: https://artificialanalysis.ai/models/qwen3-6-27b	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.	Not reported	9% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.6-27b_none; run=CGac6TZg5qVdxNGULzfR6R; mean accuracy; https://epoch.ai/data/benchmarks.csv	22% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.6-27b; run=Wh3JxFdvxP688EWwE3t2Uk; 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	34.04% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.6-27b_none; run=WjXdTPMnJUAT27azUKo3Ka; mean accuracy; https://epoch.ai/data/benchmarks.csv	35.09% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.6-27b; run=VonoEhAsGSJ2FHU33qnhui; 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	84.85% Reported settings Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3.6-27b_none; run=WeP7Q27N5PzxSgg4ybgijX; mean accuracy; https://epoch.ai/data/benchmarks.csv	85.86% Reported settings Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3.6-27b; run=buLf8Ne29xmzMZBRQkvrQG; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · Mystery Game Puzzles · v1.0.4 · Tool submissionEpoch AI · Epoch AI Inspect; task 1.0.4; scorer agent_submitted_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.	Not reported	7% Reported settings Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=qwen3.6-27b_none; run=dKZDn279PKuc2Kxm68D4r2; mean accuracy; https://epoch.ai/data/benchmarks.csv	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.	Not reported	66.67% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.6-27b_none; run=o6VtA8qruLpoShhPy2JdLg; mean accuracy; https://epoch.ai/data/benchmarks.csv	91.11% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.6-27b; run=452pB5w5ea6uy92e2q2NMv; mean accuracy; https://epoch.ai/data/benchmarks.csv

Qwen3.6-27B · Non-reasoning effort benchmarks

Qwen3.6-27B

Capability score evidence

One configuration, seven capabilities

Agentic

Hard reasoning

Coding

Human pref

Knowledge

Multimodal

Long context