UnifyBench

RankingEffort benchmarks

Qwen 3.8-Max effort benchmarks

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

Qwen 3.8-Max

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

Capability score evidence

Qwen 3.8-Max · XHigh: 49.9 overall comparison score. Meets the overall evidence requirements.

Which sources carry the weight?
  • Epoch AI · 51.0% direct comparison weight · independent
  • Datacurve · 49.0% 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 evidenceRecomputed scoreChange
Artificial Analysis50.3+0.5
ARC Prize52.3+2.4
Datacurve46.6-3.3
LiveCodeBench49.9-0.0
Scale51.2+1.3
Terminal-Bench49.8-0.1
Cognition50.0+0.1
LiveBench50.8+1.0
SWE-rebench49.2-0.7
Epoch AI51.0+1.1
Vals AI49.3-0.5
Provider reports · Anthropic49.9+0.0
Provider reports · Moonshot AI49.7-0.1
Provider reports · Meta50.0+0.1
Provider reports · Mistral49.9+0.0
All provider reports49.9-0.0
Every benchmark family
Removed evidenceRecomputed scoreChange
deepswe46.6-3.2
simpleqa52.9+3.0
arc-agi52.3+2.4
aime48.4-1.5
mmmu-pro50.8+0.9
frontiermath49.1-0.8
swe-rebench49.2-0.7
gpqa49.4-0.5
mmlu-pro50.3+0.4
hle50.3+0.4
epoch-game-puzzles49.6-0.3
swe-atlas-qna49.6-0.3
multi-swe-bench49.6-0.3
harvey49.6-0.3
arc-agi-349.7-0.2
tau-bench49.7-0.2
livebench-instructions50.1+0.2
livebench-language50.0+0.2
livebench-coding49.7-0.1
livebench-data50.0+0.1
frontiercode50.0+0.1
livebench-reasoning49.7-0.1
vals-finance-agent49.7-0.1
vals-legal-research49.7-0.1
gdp-pdf50.0+0.1
enigma-eval50.0+0.1
ifbench49.8-0.1
vibe-code49.8-0.1
scicode50.0+0.1
automationbench49.8-0.1
omniscience49.9+0.1
apex-agents49.9+0.0
terminal-bench49.9+0.0
itbench49.8-0.0
swe-atlas-test-writing49.8-0.0
livebench-math49.9+0.0
briefcase49.8-0.0
gdpval49.8-0.0
critpt49.9+0.0
vals-code-migration49.9+0.0
gmmlu49.9+0.0
analyst-agent49.9+0.0
aa-lcr49.9+0.0
livecodebench49.9+0.0
vals-excel-modeling49.9-0.0
math50049.9+0.0
enterprise-ops49.9-0.0
swe-bench-pro49.9+0.0
swe-atlas-refactoring49.9+0.0
What evidence is missing from the fit?

Across all collected settings for this model: 85 observations, 23 contributing, 0 matched without graph weight and 62 excluded. Counts do not establish rank eligibility.

  • 1 · Benchmark family or source protocol has not been reviewed
  • 2 · Evaluator has not been reviewed for independent admission
  • 1 · Source reports 55.1% and 38/64 completed runs; incomplete trials. Published percentage retained.
  • 1 · No matched opponent in this evaluation unit
  • 17 · No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately
  • 34 · Supporting evidence outside the reviewed capability core
  • 1 · The GLM card attributes this evaluation to Artificial Analysis; it is not a new Z.ai comparison.
  • 5 · Legacy self-report lacks a reviewed comparison configuration
Inspect every observation and exclusion →

Capability profile

One configuration, seven capabilities

Comparison score · 0–100
Qwen 3.8-Max · XHigh capability radarComparison scores from 0 to 100. Unknown capabilities have no point; lines stop at gaps. Hollow points are preliminary. Exact values and support labels follow the chart.AgenticHard reasoningCodingHuman prefKnowledgeMultimodalLong context50100Qwen 3.8-Max · XHigh · Hard reasoning: 60.0 · SupportedQwen 3.8-Max · XHigh · Coding: 55.6 · PreliminaryQwen 3.8-Max · XHigh · Knowledge: 29.9 · Preliminary

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

  • Agentic

    Unknown

  • Hard reasoning

    A60.0Supported

  • Coding

    A55.6Preliminary

  • Human pref

    Unknown

  • Knowledge

    A29.9Preliminary

  • Multimodal

    Unknown

  • Long context

    Unknown

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 / sourceLowMediumXHighReasoning
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 reportedNot reportedNot reported
1,387.89 Elo
Reported settings

Qwen3.8 Max; 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 2026-09-12.

Not reportedNot reportedNot reported
78.33%
Reported settings

Qwen3.8 Max; 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 2026-09-12.

Not reportedNot reportedNot reported
49.23%
Reported settings

Qwen3.8 Max; 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 · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis

Unit: percent. Source collected 2026-09-12.

Not reportedNot reportedNot reported
20%
Reported settings

Qwen3.8 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified

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 reportedNot reportedNot reported
20.2%
Reported settings

Qwen3.8 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified

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 reportedNot reportedNot reported
1,630.39 Elo
Reported settings

Qwen3.8 Max; 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 2026-09-12.

Not reportedNot reportedNot reported
92.73%
Reported settings

Qwen3.8 Max; 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 2026-09-12.

Not reportedNot reportedNot reported
43.05%
Reported settings

Qwen3.8 Max; 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 2026-09-12.

Not reportedNot reportedNot reported
19.44%
Reported settings

Qwen3.8 Max; 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 2026-09-12.

Not reportedNot reportedNot reported
82.31%
Reported settings

Qwen3.8 Max; 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 2026-09-12.

Not reportedNot reportedNot reported
3.4
Reported settings

Qwen3.8 Max; 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 2026-09-12.

Not reportedNot reportedNot reported
31.85%
Reported settings

Qwen3.8 Max; 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

Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis

Unit: percent. Source collected 2026-09-12.

Not reportedNot reportedNot reported
53.24%
Reported settings

Qwen3.8 Max; 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 2026-09-12.

Not reportedNot reportedNot reported
51.34%
Reported settings

Qwen3.8 Max; 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 2026-09-12.

Not reportedNot reportedNot reported
81.27%
Reported settings

Qwen3.8 Max; 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 2026-09-12.

Not reportedNot reportedNot reported
18.69%
Reported settings

Qwen3.8 Max; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/qwen3-8-max; Mode from evaluator isReasoning metadata; effort budget not specified

DeepSWE v1.1Datacurve · mini-swe-agent
Benchmark details

Original public board. Configuration and task coverage may differ; inspect source.

Unit: percent. Source collected 2026-09-12.

Not reportedNot reported
57.5%
Reported settings

qwen3-8-max; Reported effort: xhigh; 113 unique tasks; 449 attempts; 4 runs

Not reported
VulcanBench v3 · Report 12VulcanBench · VulcanBench bare-bones API loop, deterministic hidden tests in Docker
Benchmark details

Frozen v3, 23 post-cutoff repository tasks. Published pass@1; repeat counts and time budgets vary by report. Display only pending comparability review.

Unit: percent. Source collected 2026-09-12.

81.2%
Reported settings

Qwen3.8-Max; source label: low; low effort; 23 tasks; evaluation 2026-08-04. See source for repeat counts and wall-clock budget.

71%
Reported settings

Qwen3.8-Max; source label: medium; medium effort; 23 tasks; evaluation 2026-08-04. See source for repeat counts and wall-clock budget.

55.1%
Reported settings

Qwen3.8-Max; source label: xhigh (default); xhigh effort; 23 tasks; evaluation 2026-08-04. Source reports 55.1% and 38/64 completed runs; incomplete trials. Published percentage retained.

Source reports 55.1% and 38/64 completed runs; incomplete trials. Published percentage retained.

Source label needs review
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 reportedNot reported
29%
Reported settings

Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.8-max_xhigh; run=PPbjbUncV6qa9jNRKjYrfp; 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 2026-09-12.

Not reportedNot reported
46.34%
Reported settings

Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.8-max_xhigh; run=PBRdMZyz4L4CqPpXyLD2Lk; 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 2026-09-12.

Not reportedNot reported
74.74%
Reported settings

Epoch AI Inspect; task 2.0.0; scorer verification_code; model=qwen3.8-max_xhigh; run=ABT89ieSWGnGj4RYMduHiG; mean accuracy; https://epoch.ai/data/benchmarks.csv

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.

Not reportedNot reported
92.68%
Reported settings

Epoch AI Inspect; task 1.0.11; scorer choice; model=qwen3.8-max_xhigh; run=TEVNDC9QXBh7PQvX9kHZip; mean accuracy; https://epoch.ai/data/benchmarks.csv

Not reported
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 reportedNot reported
38%
Reported settings

Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=qwen3.8-max_xhigh; run=c2YLifDU4zYCX5Jbi9HLL7; 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 reportedNot reported
99.44%
Reported settings

Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=qwen3.8-max_xhigh; run=aGRKHaq9uSawfYVpC565zU; mean accuracy; https://epoch.ai/data/benchmarks.csv

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 reportedNot reported
45.8%
Reported settings

Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=qwen3.8-max_xhigh; run=bfftd5EzUK9yAekafEofvK; 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 · 7,424 results across 240 models · Collected 2026-09-12