BlogLLM Benchmark Scores as Published, Side by Side
Qwen3.8-Max: Benchmark Scores as Published
Every result the catalog holds for Qwen3.8-Max: 45 tests in 12 areas, from 6 pages. 32 printed by Alibaba itself, the rest by the company named beside each number. Each number is as printed; nothing is ranked or rescored.
Developer AlibabaReleased 2026-08-03Context window 1MMax output 131KInput Text, image, videoOutput TextWeights ClosedData version 2026103001, as of 2026-10-30
Knowledge Work
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| AutomationBench | 27.3% | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14; printed on 1 more page | - |
| GDPval-AA v2 | 1739 | Z.ai, GLM-5.3 model cardchecked 2026-10-15 | - |
| JobBench | 53.4 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| Vals Finance Agent v2 | 50.6% | Mistral AI, Mistral Large 4 (preview)checked 2026-10-15 | - |
| Harvey's Legal Agent Benchmark | 10.4% | Mistral AI, Mistral Large 4 (preview)checked 2026-10-15 | - |
| CoWorkBench | 74.8 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| $OneMillion-Bench (expert score) | 52.5 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| PLawBench | 73.2 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| PRBench-Finance | 58.3 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| PRBench-Legal | 57.6 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| WorkSpaceBench | 67.7 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
Agentic Coding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| SWE-Bench Pro | 67.7% | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| Terminal-Bench 2.1 | 86.6% | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14; printed on 1 more page | - |
| DeepSWE v1.1 | 56.6% | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14; printed on 2 more pages | - |
| Terminal-Bench 4.0 | 17% | Mistral AI, Mistral Large 4 (preview)checked 2026-10-15 | - |
| NL2Repo-Bench | 55.9 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14; printed on 1 more page | - |
| ProgramBench Almost@1 | 10.5% | Z.ai, GLM-5.3 model cardchecked 2026-10-15 | - |
| SWE-Atlas-QnA (setting not stated) | 62% | Mistral AI, Mistral Large 4 (preview)checked 2026-10-15 | - |
| FrontierSWE (dominance score) | 73.5 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| QwenSWEBench | 80.7 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| AndroidBench | 75.1 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| QwenQoderBench | 58.4 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
ML Engineering
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| PaperBench | 93 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| MLS-Bench-Lite | 41 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
Science and Math
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPQA Diamond | 92.6% | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| FrontierMath Tier 4 (v2) | 46.3% | Epoch AI, Epoch AI Benchmarking Hubchecked 2026-10-30 | Effort: xhigh |
| FrontierMath Tier 1-3 (v2) | 74.7% | Epoch AI, Epoch AI Benchmarking Hubchecked 2026-10-30 | Effort: xhigh |
Long Context
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| LongBench v2 | 66.3% | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| MRCR v2 8-needle 256K | 92.9 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
Cybersecurity
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| CyberGym | 78.5% | Z.ai, GLM-5.3 model cardchecked 2026-10-15 | - |
| ExploitBench | 28.8% | Z.ai, GLM-5.3 model cardchecked 2026-10-15 | - |
| ExploitGym (2h) | 14 | Z.ai, GLM-5.3 model cardchecked 2026-10-15 | Effort: max; Harness: Claude Code 2.1.207; Attempt budget: timeout budget 2 hours (rescaled API inference time plus overhead) |
| ExploitGym (6h) | 26 | Z.ai, GLM-5.3 model cardchecked 2026-10-15 | Effort: max; Harness: Claude Code 2.1.207; Attempt budget: timeout budget 6 hours (rescaled API inference time plus overhead) |
General Knowledge and Reasoning
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Humanity's Last Exam (no tools) | 43.6% | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| Humanity's Last Exam (with tools) | 56.2% | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14; printed on 1 more page | Tools: enabled; exact tools in source |
| SimpleQA Verified | 45.8% | Epoch AI, Epoch AI Benchmarking Hubchecked 2026-10-30 | Effort: xhigh |
Code Generation
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| QwenReactBench | 1724 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| QwenSVGBench | 1713 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
Tool Use and Workflows
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Agents' Last Exam (pass rate) | 27% | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14; printed on 1 more page | - |
| Toolathlon Verified | 72.5% | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14; printed on 1 more page | - |
| Agents' Last Exam (score) | 52.4% | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| SkillsBench | 70.2 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
Web Search and Research
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| WideSearch (metric not stated) | 81.9 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
Instruction Following
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| IFBench | 82.8 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
Healthcare
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| HealthBench | 60.2 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
Price
API list prices in US dollars per one million tokens, as printed on the developer's pricing page on the day checked. Cost per task is measured by Vals AI.
| Price | Value | Printed by | Setup as printed |
|---|---|---|---|
| Input | $1.65 | Alibaba, Alibaba Model Studio pricingchecked 2026-10-15 | - |
| Output | $4.951 | Alibaba, Alibaba Model Studio pricingchecked 2026-10-15 | - |
| Cost per taskVals AI, USD, lower is better | $8.24 | Vals AI, Vibe Code Bench v1.1 leaderboardchecked 2026-10-27 | Harness: OpenHands |
Side by side
More from Alibaba
- Qwen3.7-Plus
- Qwen3.6-27B
- Qwen3.6-35B-A3B
- Qwen3.6-Plus
- Qwen3.5-122B-A10B
- Qwen3.5-27B
- Qwen3.5-35B-A3B
- Qwen3.5-397B-A17B
- Qwen3-VL-32B-Instruct
- Qwen3-VL-32B-Thinking
- Qwen3-VL-8B-Instruct
- Qwen3-VL-8B-Thinking
- Qwen3-VL-235B-A22B
- Qwen3-VL-235B-A22B-Thinking
- Qwen3-Next-80B-A3B
- Qwen3-30B-A3B-Instruct-2507
- Qwen3-30B-A3B-Thinking-2507
- Qwen3-Coder-Plus
- Qwen3-235B-A22B
- Qwen3-32B
- Qwen3-8B
- QwQ-32B-Preview
- Qwen-Max
- Qwen3-Max-Thinking
- Qwen3.7-Max
- Qwen3.8-2.4T-A95B
- Qwen3.8-27B
- Qwen3.8-Flash-Next
Every number here is read from the same catalog file as the benchmark table, data version 2026103001. Where one page printed the model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.