Qwen3.8-27B: score and benchmark evidence
Historical release · · Alibaba
71.0 points · Rank 18 among 19 ranked models · Stability range 61.8–79.9 points.
Rank follows the point estimate; it does not establish statistically significant superiority. The scale is anchored at mean 100, SD 15 in the frozen calibration cohort, not human IQ or a percentage.
One score summarizes demonstrated capability across published reasoning settings and seven equally weighted domains. Related benchmark variants share a family budget, and influence from one evaluator is capped.
Release tli-2026-v1.0-2026-09-06-presentation-1. Methodology and limitations for this release.
This page preserves historical evidence. See the current model record.
Capability domains
Domain scores use calibration-cohort standard-deviation units. Unmeasured domains are shown as unavailable, not zero.
| Domain | Score (SD units) | Observed benchmarks |
|---|---|---|
| Knowledge & reasoning | -1.07 | 8 |
| Coding & software engineering | -1.04 | 8 |
| Agentic tool & computer use | -0.64 | 3 |
| Professional & real-world work | -0.77 | 12 |
| Multimodal & vision | -0.47 | 6 |
| Cybersecurity | Unavailable | 0 |
| Preference & communication | -0.91 | 2 |
Published benchmark evidence
39 results contribute to this score, from 52 collected results and 39 contributing benchmark families. Counts are not independent sample sizes.
Results, source citations, review decisions and compatible reasoning modes are stored in a versioned relational database. Each publication uses a sealed, checksum-verified export; CSV files are optional exports, not editable scoring inputs. Previous revisions remain available for audit. Collected means a numeric result exists in the database. Used means its source, exact model checkpoint and benchmark protocol have been reviewed and its benchmark has a frozen calibration supported by multiple providers. For each benchmark we select the highest published aggregate across comparable reasoning modes, not necessarily maximum effort, and count it once. More tested settings provide more chances to record a high score; this selection advantage is not corrected by the conditional interval. Developer-reported and sole/unspecified settings remain eligible and disclosed. Unresolved does not mean false or useless: conflicting metrics, unverified citations and unmatched versions stay collected until reconciled.
The score stability range is a 95% bootstrap score interval conditional on frozen calibration and comparable evidence availability. It resamples benchmark families and evaluators and adds a frozen missing-evidence correction. It excludes selection across reasoning settings, selective publication, calibration changes and new domains. It is not a 95% guarantee about true capability or where a future score will land. Sparse or conflicting evidence can widen the range.
Reporting sensitivity: ±1.3 points. Sensitivity to selectively published results. This stress range is not a confidence interval or a probability statement.
GDPval-AA v2 (Elo): 1466.21 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: Qwen3.8 27B (xhigh); Artificial Analysis published evaluation harness
Metric: Elo
Original source · Retrieved 2026-09-06
Best published result among 4 reasoning configurations of the exact AA model release; fallback configurations excluded.
Terminal-Bench 2.1: 79.775281%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: Qwen3.8 27B (xhigh); Artificial Analysis published evaluation harness
Metric: pass@1, AA harness
Original source · Retrieved 2026-09-06
Best published result among 4 reasoning configurations of the exact AA model release; fallback configurations excluded.
DeepSWE v1.1: 42.2%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 42.2 for Qwen3.8-27B on DeepSWE v1.1 still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
LMArena (Chatbot Arena) — Text: 1435.892663 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: qwen3.8-27b; Arena text overall; style control enabled
Metric: style-controlled text overall Elo
Original source · Retrieved 2026-09-06
Best published reasoning-mode rating within the same text overall board. Different leaderboard slices and undated earlier DeepSeek checkpoints are not pooled.
AA Intelligence Index v4.1.1 (score): 52 native-points
Not used in the score. Source category not recorded. Review status: excluded.
Held-out composite, never a scoring input
GPQA Diamond: 90.505051%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: Qwen3.8 27B (xhigh); Artificial Analysis published evaluation harness
Metric: accuracy, AA
Original source · Retrieved 2026-09-06
Best published result among 4 reasoning configurations of the exact AA model release; fallback configurations excluded.
AA-LCR: 77.3%
Not used in the score. Source category: independent. Review status: unresolved.
Configuration: Qwen3.8 27B (xhigh)
Original source · Retrieved 2026-09-06
Current AA result is LCR v1.1. The inherited AA-LCR row has no reviewed version match; a new version cannot silently substantiate the older value.
Finance Agent v2 — Vals: 48.55%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: alibaba_qwen3.8-27b; Vals xhigh effort
Metric: fabv2 overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Excel Modeling Benchmark — Vals: 59.66%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: alibaba_qwen3.8-27b; Vals xhigh effort
Metric: emb overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
SciCode: 46.643519%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: Qwen3.8 27B (xhigh); Artificial Analysis published evaluation harness
Metric: accuracy, AA harness
Original source · Retrieved 2026-09-06
Best published result among 4 reasoning configurations of the exact AA model release; fallback configurations excluded.
Humanity's Last Exam (no tools): 33.920297%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: Qwen3.8 27B (xhigh); Artificial Analysis published evaluation harness
Metric: accuracy, no tools, AA
Original source · Retrieved 2026-09-06
Best published result among 4 reasoning configurations of the exact AA model release; fallback configurations excluded.
Legal Research Bench — Vals: 36.06%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: alibaba_qwen3.8-27b; Vals xhigh effort
Metric: legal_research overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Harvey LAB (Vals): 11.25%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: alibaba_qwen3.8-27b; Vals xhigh effort
Metric: hlab overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
AA-Briefcase Overall Elo: 1401.81 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: Qwen3.8 27B (xhigh); Artificial Analysis published evaluation harness
Metric: overall Elo
Original source · Retrieved 2026-09-06
Best published result among 1 reasoning configurations of the exact AA model release; fallback configurations excluded.
MedScribe — Vals: 83.85%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: alibaba_qwen3.8-27b; Vals xhigh effort
Metric: medscribe overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
SWE-bench Verified — Vals: 86%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: alibaba_qwen3.8-27b; Vals xhigh effort
Metric: swebench overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
LegalBench — Vals: 82.43%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: alibaba_qwen3.8-27b; Vals xhigh effort
Metric: legal_bench overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
TaxEval v2 — Vals: 70.85%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: alibaba_qwen3.8-27b; Vals xhigh effort
Metric: tax_eval_v2 overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
MedCode — Vals: 28.7%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: alibaba_qwen3.8-27b; Vals xhigh effort
Metric: medcode overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
AA-Omniscience: -7.95 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: Qwen3.8 27B (Non-reasoning); Artificial Analysis published evaluation harness
Metric: knowledge reliability index -100 to 100
Original source · Retrieved 2026-09-06
Best published result among 4 reasoning configurations of the exact AA model release; fallback configurations excluded.
MMLU Pro — Vals: 84.34%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: alibaba_qwen3.8-27b; Vals xhigh effort
Metric: mmlu_pro overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
LiveBench: 75.269107%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: qwen3.8-27b; LiveBench 2026-06-25 release
Metric: official overall: equal mean of seven category means
Original source · Retrieved 2026-09-06
Task mapping archived from categories_2026_06_25.json. Aggregate follows the official UI, not a flat mean of the 23 tasks. Undated old DeepSeek checkpoints excluded.
MortgageTax — Vals: 64.94%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: alibaba_qwen3.8-27b; Vals xhigh effort
Metric: mortgage_tax overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
SAGE — Vals: 52.4%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: alibaba_qwen3.8-27b; Vals xhigh effort
Metric: sage overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Code Migration †: 14.16%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: alibaba_qwen3.8-27b; Vals xhigh effort
Metric: code-migration overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Agents' Last Exam: 20.4%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 20.4 for Qwen3.8-27B on Agents' Last Exam still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
LiveCodeBench: 84%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: alibaba_qwen3.8-27b; Vals xhigh effort
Metric: lcb overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
ProgramBench v1 (Raw Pass Rate) — Vals: 11.168%
Contributes to the score. Source category: independent. Review status: reviewed-archive.
Configuration: alibaba/qwen3.8-27b · reasoning_effort=xhigh
Metric: Raw Pass Rate: mean percent of hidden behavioral tests passed per task. Not Fully Resolved (all tests pass) and not Almost Resolved (≥95% of tests pass).
Original source · Retrieved 2026-09-05
Matched exact metric/value and the archived benchmark-specific configuration review. Unknown native effort stays explicitly unknown.
SWE-bench Pro: 61.7%
Not used in the score. Developer-reported. Review status: reviewed-developer.
Configuration: Qwen3.8-27B; published developer evaluation; benchmark-specific configuration
Metric: SWE-bench Pro
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
CharXiv (with CI / RQ): 90.2%
Contributes to the score. Developer-reported. Review status: reviewed-developer.
Configuration: Qwen3.8-27B; published developer evaluation; With CI
Metric: CharXiv (RQ)
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
MMMU-Pro: 76.300578%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: Qwen3.8 27B (xhigh); Artificial Analysis published evaluation harness
Metric: accuracy, AA
Original source · Retrieved 2026-09-06
Best published result among 4 reasoning configurations of the exact AA model release; fallback configurations excluded.
JobBench: 33.4%
Contributes to the score. Developer-reported. Review status: reviewed-developer.
Configuration: Qwen3.8-27B; published developer evaluation; benchmark-specific configuration
Metric: JobBench
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
BabyVision (with CI): 85.6%
Contributes to the score. Developer-reported. Review status: reviewed-developer.
Configuration: Qwen3.8-27B; published developer evaluation; With CI
Metric: BabyVision
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
OSWorld-Verified: 84.3%
Contributes to the score. Developer-reported. Review status: reviewed-developer.
Configuration: Qwen3.8-27B; published developer evaluation; benchmark-specific configuration
Metric: OSWorld-Verified
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Creative Writing v3: 1669.1 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: *Qwen/Qwen3.8-27B; published evaluation, effort unspecified
Metric: Creative Writing v3 Elo
Original source · Retrieved 2026-09-06
Exact checkpoint on the evaluator-hosted board. A starred model is externally submitted; it is not claimed as independently rerun by the benchmark owner.
NL2Repo: 42.3%
Not used in the score. Developer-reported. Review status: reviewed-developer.
Configuration: Qwen3.8-27B; published developer evaluation; benchmark-specific configuration
Metric: NL2Repo-Bench
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
CoWorkBench: 70.7%
Not used in the score. Developer-reported. Review status: reviewed-developer.
Configuration: Qwen3.8-27B; published developer evaluation; benchmark-specific configuration
Metric: CoWorkBench
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
ERQA: 65.5%
Not used in the score. Developer-reported. Review status: reviewed-developer.
Configuration: Qwen3.8-27B; published developer evaluation; benchmark-specific configuration
Metric: ERQA
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Vision2Web (Avg. Frontend/Webpage/etc.): 62.9%
Not used in the score. Developer-reported. Review status: reviewed-developer.
Configuration: Qwen3.8-27B; published developer evaluation; benchmark-specific configuration
Metric: Vision2Web
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
WebArena-Verified: 64.8%
Not used in the score. Developer-reported. Review status: reviewed-developer.
Configuration: Qwen3.8-27B; published developer evaluation; benchmark-specific configuration
Metric: WebArena-Verified
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
τ³-Banking: 48.041237%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: Qwen3.8 27B (xhigh); Artificial Analysis published evaluation harness
Metric: strict task success, AA
Original source · Retrieved 2026-09-06
Best published result among 4 reasoning configurations of the exact AA model release; fallback configurations excluded.
CritPt: 5.428571%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: Qwen3.8 27B (xhigh); Artificial Analysis published evaluation harness
Metric: accuracy, AA official grading
Original source · Retrieved 2026-09-06
Best published result among 4 reasoning configurations of the exact AA model release; fallback configurations excluded.
ProofBench v1.1 — Vals: 16%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: alibaba_qwen3.8-27b; Vals xhigh effort
Metric: proof_bench overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Vibe Code Bench v1.1 — Vals: 64.85%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: alibaba_qwen3.8-27b; Vals xhigh effort
Metric: vibe-code overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
EnterpriseOps-Gym-AA: 44.23%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 44.23 for Qwen3.8-27B on EnterpriseOps-Gym-AA still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
MLCR-AA (Medical Long Context Reasoning): 21.666667%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: Qwen3.8 27B (xhigh); Artificial Analysis published evaluation harness
Metric: overall accuracy, AA
Original source · Retrieved 2026-09-06
Best published result among 1 reasoning configurations of the exact AA model release; fallback configurations excluded.
IFBench: 79.5%
Not used in the score. Developer-reported. Review status: reviewed-developer.
Configuration: Qwen3.8-27B; published developer evaluation; benchmark-specific configuration
Metric: IFBench
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
AndroidWorld: 81.9%
Not used in the score. Developer-reported. Review status: reviewed-developer.
Configuration: Qwen3.8-27B; published developer evaluation; benchmark-specific configuration
Metric: AndroidWorld
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
MathVision (with CI): 94.6%
Contributes to the score. Developer-reported. Review status: reviewed-developer.
Configuration: Qwen3.8-27B; published developer evaluation; With CI
Metric: MathVision
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
OmniDocBench 1.5: 91.1%
Contributes to the score. Developer-reported. Review status: reviewed-developer.
Configuration: Qwen3.8-27B; published developer evaluation; benchmark-specific configuration
Metric: OmniDocBench 1.5
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
RuneBench (30m, mean ln(1 + XP/min)): 2.794282 native-points
Contributes to the score. Source category: independent. Review status: reviewed-archive.
Configuration: qwen38
Metric: Arithmetic mean of ln(1 + peakXpRate) over all 16 skills, exactly as the owner’s Heatmap.js default ranking. Data rates are already normalized; do not divide by 200 again.
Original source · Retrieved 2026-09-06
Matched exact metric/value and the archived benchmark-specific configuration review. Unknown native effort stays explicitly unknown.
Code Arena WebDev (overall): 1594 native-points
Contributes to the score. Source category: independent. Review status: reviewed-archive.
Configuration: qwen3.8-27b
Metric: Published overall WebDev preference rating, not task success percentage or Arena Text score.
Original source · Retrieved 2026-09-06
Matched exact metric/value and the archived benchmark-specific configuration review. Unknown native effort stays explicitly unknown.
Cite this model record
The Latent. “Qwen3.8-27B: score and benchmark evidence.” 2026-09-06. Release tli-2026-v1.0-2026-09-06-presentation-1.
Download release data and definitions (JSON) · Data usage terms