RankingQwen3.8 Max 0902
Qwen3.8 Max 0902
Qwen3.8 Max 0902 by Qwen is a qwen3.8 model, released 2026-09-02. This profile collects the published benchmark results and reported effort settings for this model. Configurations are compared on the effort page. Ranks are on the leaderboard.
2 published benchmark measures · 29 measured effort results · 1 benchmark families contribute across 1 task areas. 1 capability estimates available in the full profile. See all results ↓ · Compare published benchmarks →
Model evidence summary
This profile combines published settings. It is not a runnable configuration or a leaderboard rank. Compare measured configurations →
Performance profile
Capabilities
Filled points are supported; hollow points are preliminary. Lines stop at unknown capabilities. Exact values and sources follow below.
Scores estimate outcomes against a shared reference panel; they are not accuracy percentages. Sparse or disconnected evidence cannot qualify an overall profile. Open a capability to inspect its evidence.
Reported effort · Not specified
Settings reported in this model's published benchmark results, including results outside the aggregate. Effort names are provider-specific. These are not API defaults or equal compute budgets.
- Not specified: 2 observations
Mixed settings means multiple settings occur in the evidence. Best across efforts means the source selected its best reported result across settings; it does not mean Max. Unspecified settings stay unknown. This model-summary chart combines reported settings. The leaderboard keeps identified configurations separate and excludes unknown effort.
Inspect each result and its source ↓ · Download effort evidenceScore contributions and missing evidence
1 contributing families across 1 capabilities. Fixed reference panels do not change when the catalog expands.
Capability is fitted jointly across families. Capability estimates below describe different task areas; their weighted sum is not the Capability score.
Results without reviewed compatibility or a reference match remain in the raw evidence below. Coverage counts only contributing results.
Model information & shareable badge
- Lab
- Qwen
- Catalog status
- api-listed
- Availability
- Documented dated provider API snapshot; distinct from August 0803. Account and region restrictions may apply.
- Family
- qwen3.8
- Released
- 2026-09-02
- Context
- 1,000,000 tokens
- License
- —
- Model card
- https://www.alibabacloud.com/help/en/model-studio/qwen3-8-max
- Default Capability family coverage
/badge/qwen-3.8-max-0902.svg
Qwen3.8 Max 0902 measured results by effort setting
Each row is one published result for one effort setting. Evidence collected 2026-11-22. Compare the effort settings →
| Benchmark | Effort | Score | Source |
|---|---|---|---|
| AA-AnalystAgent | Reasoning | 45.0% | Artificial Analysis |
| AA-Briefcase Elo | Reasoning | 1604 | Artificial Analysis |
| AA-LCR v1.1 | Reasoning | 80.3% | Artificial Analysis |
| AA-Omniscience Accuracy | Reasoning | 29.5% | Artificial Analysis |
| AA-Omniscience Index | Reasoning | 10.5 | Artificial Analysis |
| APEX-Agents-AA | Reasoning | 42.4% | Artificial Analysis |
| AutomationBench-AA | Reasoning | 56.2% | Artificial Analysis |
| CritPt | Reasoning | 17.7% | Artificial Analysis |
| EnterpriseOps-Gym-AA | Reasoning | 47.6% | Artificial Analysis |
| Epoch · Chess Puzzles · v2.0.0 | XHigh | 37.0% | Epoch AI |
| Epoch · FrontierMath Tier 4 · v2.0.0 | XHigh | 34.1% | Epoch AI |
| Epoch · FrontierMath Tiers 1–3 · v2.0.0 | XHigh | 65.6% | Epoch AI |
| Epoch · GPQA diamond · v1.0.11 | XHigh | 92.3% | Epoch AI |
| Epoch · OTIS Mock AIME 2024-2025 · v1.1.6 | XHigh | 100.0% | Epoch AI |
| Epoch · SimpleQA Verified · v1.2.0 | XHigh | 47.3% | Epoch AI |
| FrontierSWE v2 | Unspecified | 17.8% | Proximal |
| GDP.pdf: All-pass Rate | Reasoning | 22.8% | Artificial Analysis |
| GDPval-AA v2.1 Leaderboard | Reasoning | 1674 | Artificial Analysis |
| GPQA Diamond | Reasoning | 92.8% | Artificial Analysis |
| Humanity's Last Exam | Reasoning | 43.1% | Artificial Analysis |
| ITBench-AA | Reasoning | 40.3% | Artificial Analysis |
| MLCR-AA | Reasoning | 20.0% | Artificial Analysis |
| MMMU-Pro | Reasoning | 82.8% | Artificial Analysis |
| SciCode | Reasoning | 52.1% | Artificial Analysis |
| Terminal-Bench 4.0 · claudecode | Max | 27.0% | Terminal-Bench |
| Terminal-Bench v2.1 | Reasoning | 88.8% | Artificial Analysis |
| Terminal-Bench v4.0 | Reasoning | 38.9% | Artificial Analysis |
| Terminal-Bench-Science 0.1 | Reasoning | 11.9% | Artificial Analysis |
| 𝜏³-Banking | Reasoning | 47.8% | Artificial Analysis |
Benchmark scores & sources
Original results, evaluation harnesses, and evidence behind this model.
| Benchmark | Bucket | Score | Harness | Evidence | Source-recorded date |
|---|---|---|---|---|---|
| FrontierSWE v2 | Supporting evidence | 17.8% | Proximal FrontierSWE v2 · Proximus · unspecified | official board | 2026-11-22 |
| Terminal-Bench 4.0 | Coding | 26.97% | Terminal-Bench 4.0 reportedcontributes to capability | official board | 2026-09-02 |
| ARC-AGI-2 | Hard reasoning | — | — | — | — |
| DeepSWE v1.1 | Agentic | — | — | — | — |
| GDPval-AA | Agentic | — | — | — | — |
| GPQA Diamond | Hard reasoning | — | — | — | — |
| Humanity's Last Exam | Hard reasoning | — | — | — | — |
| LiveCodeBench | Coding | — | — | — | — |
| LMArena Text Arena | Human pref | — | — | — | — |
| MMLU-Pro | Knowledge | — | — | — | — |
| OSWorld-Verified | Agentic | — | — | — | — |
| SWE-bench Pro | Agentic | — | — | — | — |
| SWE-bench Verified | Agentic | — | — | — | — |
| Terminal-Bench 2.1 | Agentic | — | — | — | — |