RankingEffort benchmarks

Qwen3.8 Max 0902

Compare models

28 measured results · 2 effort settings · 28 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

AQwen3.8 Max 0902 · Reasoning2 of 7 capabilities supported

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

Agentic
A69.1Supported
Hard reasoning
A50.6Supported
Coding
A74.4Preliminary
Human pref
Unknown
Knowledge
A23.1Preliminary
Multimodal
A55.9Preliminary
Long context
A59.6Preliminary

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

Qwen3.8 Max 0902 · Reasoning: 60.3 overall comparison score. Meets the overall evidence requirements.

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

Which sources carry the weight?

Artificial Analysis · 100.0% direct comparison weight · independent of the model provider

Which benchmark families carry the weight?

Humanity’s Last Exam · 6.9% direct comparison weight
Critpt · 6.9% direct comparison weight
Mmmu Pro · 6.9% direct comparison weight
omniscience · 6.8% direct comparison weight
GPQA · 6.8% direct comparison weight
Other families (13) · 65.7% 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.

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 2026-10-02.

Both ranks use the same surviving configurations for each removal. The cohort starts with 434 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	Comparison support lost; no rank		197 remaining / 237 lost	Unavailable
ARC Prize	50 → 47	Up 3	434 remaining / 0 lost	64.7 (+4.4 points)
Datacurve	50 → 46	Up 4	434 remaining / 0 lost	56.8 (-3.6 points)
LiveCodeBench	50 → 50	No movement	434 remaining / 0 lost	60.2 (-0.1 points)
Scale	50 → 49	Up 1	434 remaining / 0 lost	61.8 (+1.4 points)
Terminal-Bench	50 → 48	Up 2	434 remaining / 0 lost	60.7 (+0.3 points)
Cognition	50 → 42	Up 8	434 remaining / 0 lost	59.7 (-0.6 points)
LiveBench	50 → 50	No movement	433 remaining / 1 lost	61.1 (+0.7 points)
SWE-rebench	50 → 48	Up 2	434 remaining / 0 lost	60.4 (+0.1 points)
Epoch AI	50 → 51	Down 1	416 remaining / 18 lost	60.5 (+0.1 points)
Vals AI	50 → 50	No movement	433 remaining / 1 lost	59.5 (-0.9 points)
Provider reports · Anthropic	50 → 50	No movement	434 remaining / 0 lost	60.3 (-0.0 points)
Provider reports · Moonshot AI	50 → 50	No movement	434 remaining / 0 lost	59.9 (-0.4 points)
Provider reports · Meta	50 → 50	No movement	434 remaining / 0 lost	60.2 (-0.1 points)
Provider reports · Mistral	50 → 50	No movement	434 remaining / 0 lost	60.3 (+0.0 points)
Provider reports · OpenAI	50 → 51	Down 1	434 remaining / 0 lost	60.5 (+0.1 points)
All provider reports	50 → 51	Down 1	434 remaining / 0 lost	59.9 (-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
omniscience	64.8	+4.5
arc-agi	64.7	+4.4
deepswe	56.8	-3.6
harvey	58.5	-1.8
briefcase	58.7	-1.7
itbench	61.8	+1.4
gdpval	59.2	-1.2
mmmu-pro	61.5	+1.2
critpt	61.5	+1.1
hle	61.3	+0.9
tau-bench	59.4	-0.9
epoch-game-puzzles	59.5	-0.9
aa-lcr	61.1	+0.8
enterprise-ops	59.6	-0.7
terminal-bench-science	59.6	-0.7
simpleqa	61.0	+0.7
ifbench	59.7	-0.7
arc-agi-3	59.7	-0.6
apex-agents	59.7	-0.6
frontiercode	59.7	-0.6
terminal-bench	59.9	-0.5
mmlu-pro	60.7	+0.4
enigma-eval	60.7	+0.4
multi-swe-bench	60.1	-0.3
automationbench	60.6	+0.3
swe-atlas-qna	60.1	-0.3
livebench-instructions	60.6	+0.3
livebench-language	60.6	+0.2
swe-atlas-test-writing	60.2	-0.2
livebench-coding	60.2	-0.2
vibe-code	60.2	-0.1
gpqa	60.5	+0.1
livecodebench	60.3	-0.1
swe-rebench	60.4	+0.1
livebench-reasoning	60.3	-0.1
vals-legal-research	60.3	-0.1
swe-atlas-refactoring	60.3	-0.1
vals-tax-agent	60.3	-0.1
gdp-pdf	60.4	+0.1
vals-finance-agent	60.3	-0.1
frontiermath	60.4	+0.0
livebench-data	60.4	+0.0
vals-code-migration	60.3	-0.0
aime	60.3	-0.0
gmmlu	60.4	+0.0
math500	60.4	+0.0
vals-excel-modeling	60.3	-0.0
analyst-agent	60.3	-0.0
swe-bench-pro	60.4	+0.0
livebench-math	60.3	+0.0

What evidence is missing from the fit?

Across all collected settings for this model: 28 observations, 26 contributing, 0 matched without graph weight and 2 excluded. Counts do not establish rank eligibility.

1 · Benchmark family or source protocol has not been reviewed
1 · 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

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	XHigh	Reasoning
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 2026-10-02.	Not reported	45% Reported settings Qwen3.8 Max (0902); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified
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 2026-10-02.	Not reported	1,620.52 Elo Reported settings Qwen3.8 Max (0902); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified
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 2026-10-02.	Not reported	42.4% Reported settings Qwen3.8 Max (0902); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified
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 2026-10-02.	Not reported	80.33% Reported settings Qwen3.8 Max (0902); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified
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 2026-10-02.	Not reported	56.19% Reported settings Qwen3.8 Max (0902); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified
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 2026-10-02.	Not reported	17.71% Reported settings Qwen3.8 Max (0902); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified
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 2026-10-02.	Not reported	47.63% Reported settings Qwen3.8 Max (0902); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified
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 2026-10-02.	Not reported	22.8% Reported settings Qwen3.8 Max (0902); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified
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 2026-10-02.	Not reported	1,671.4 Elo Reported settings Qwen3.8 Max (0902); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified
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 2026-10-02.	Not reported	92.83% Reported settings Qwen3.8 Max (0902); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified
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 2026-10-02.	Not reported	93.65% Reported settings Qwen3.8 Max (0902); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified
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 2026-10-02.	Not reported	43.1% Reported settings Qwen3.8 Max (0902); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified
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 2026-10-02.	Not reported	40.25% Reported settings Qwen3.8 Max (0902); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified
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 2026-10-02.	Not reported	20% Reported settings Qwen3.8 Max (0902); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified
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 2026-10-02.	Not reported	82.77% Reported settings Qwen3.8 Max (0902); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified
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 2026-10-02.	Not reported	11.98 Reported settings Qwen3.8 Max (0902); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified
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 2026-10-02.	Not reported	31.68% Reported settings Qwen3.8 Max (0902); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified
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 2026-10-02.	Not reported	52.08% Reported settings Qwen3.8 Max (0902); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified
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 2026-10-02.	Not reported	47.84% Reported settings Qwen3.8 Max (0902); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified
Terminal-Bench-Science 0.1Artificial Analysis · mini-swe-agent; Terminal-Bench-Science 0.1.0; 70 tasks; pass@1 averaged over 3 repeats Benchmark details Share of tasks passed (pass@1), averaged over three repeats · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-02.	Not reported	11.9% Reported settings Qwen3.8 Max (0902); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified
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 2026-10-02.	Not reported	88.76% Reported settings Qwen3.8 Max (0902); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified
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 2026-10-02.	Not reported	38.89% Reported settings Qwen3.8 Max (0902); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified
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 2026-10-02.	40% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.8-max-0902_xhigh; run=8qGBfpdQXMmLcSqPwz7ofm; mean accuracy; https://epoch.ai/data/benchmarks.csv	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 2026-10-02.	34.15% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.8-max-0902_xhigh; run=kZUdrqdGtCEJa3ip6L9YnH; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported
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 2026-10-02.	65.61% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.8-max-0902_xhigh; run=FpQf5xBwJPb4ZEo6SgdKWq; mean accuracy; https://epoch.ai/data/benchmarks.csv	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 · 8,360 results across 248 models · Collected 2026-10-02

Qwen3.8 Max 0902

Compare with

One configuration, seven capabilities

Agentic

Hard reasoning

Coding

Human pref

Knowledge

Multimodal

Long context

Capability score evidence

Benchmark results