BlogLLM Benchmark Scores as Published, Side by Side
Qwen3.8-Flash-Next: Benchmark Scores as Published
Every result the catalog holds for Qwen3.8-Flash-Next: 58 tests in 13 areas, from 2 pages. 27 printed by Alibaba itself, the rest by the company named beside each number. Each number is as printed; nothing is ranked or rescored.
Developer AlibabaContext window 262KMax output 262KInput Text, image, videoOutput TextWeights OpenData version 2026103001, as of 2026-10-30
Knowledge Work
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| AutomationBench | 72.06% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| GDPval-AA v2 | 1561 | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| JobBench | 55.7 | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15 | - |
| CoWorkBench | 73.9 | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15 | - |
Agentic Coding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| SWE-bench Verified | 78.7% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| SWE-Bench Pro | 62.5% | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15; printed on 1 more page | Harness: Claude Code (official score for Opus 4.6); Context: 256000 |
| Terminal-Bench 2.1 | 85.8% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| DeepSWE v1.1 | 58.7% | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15; printed on 1 more page | Harness: best of Claude Code and mini-SWE-agent; Context: 256000 |
| SWE-bench Multilingual | 81% | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15; printed on 1 more page | Harness: mini-SWE-agent; Context: 256000 |
| Terminal-Bench 4.0 | 20.71% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| NL2Repo-Bench | 48.1 | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15 | Harness: Claude Code |
Science and Math
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPQA Diamond | 91.7% | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15; printed on 1 more page | - |
| SciCode | 46.6% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| MathArena Apex Shortlist | 91.8% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
Long Context
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| AA-LCR | 78.4% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| GraphWalks (variant not stated) | 76.1% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
Computer Use
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| OSWorld-Verified | 55.8% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| OSWorld 2.0 partial | 52.3% | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15 | - |
| AndroidWorld | 84.5% | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15 | - |
| OSWorld 2.0 strict | 19.4% | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15 | - |
| RecreationBench | 49.9% | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15 | - |
Multimodal Understanding
General Knowledge and Reasoning
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Humanity's Last Exam (no tools) | 35.9% | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15; printed on 1 more page | - |
| AA-Omniscience Accuracy | 27.9% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| AA-Omniscience Index | -1.9 | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| AA-Omniscience Hallucination Ratelower is better | 41.3% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| Humanity's Last Exam (full set, tools not stated) | 38.8% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
Code Generation
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| LiveCodeBench v6 | 91.9% | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15; printed on 1 more page | - |
| Vision2Web | 64% | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15 | Harness: Claude Code |
Tool Use and Workflows
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| τ³-bench Banking | 44.5% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| τ²-bench Telecom | 90.4% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| Agents' Last Exam (pass rate) | 24.3% | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15 | - |
| Toolathlon Verified | 73.5% | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15 | - |
| τ²-bench Retail | 71.6% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| τ²-bench Airline | 80.8% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| Agents' Last Exam (score) | 51.2% | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15 | - |
| ClawEval-MM average score | 60.4 | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15 | - |
| ClawEval-MM pass@3 | 64.4% | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15 | - |
Web Search and Research
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| BrowseComp | 89% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| WebVoyager | 90.39% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
Instruction Following
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| IFBench | 81.3 | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15; printed on 1 more page | - |
Multilingual
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| MMLU-ProX | 83% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| WMT24++ (XCOMET-XXL) | 86.2 | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
Writing and Conversation
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| LMArena v3 proxy | 35.2 | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
More from Alibaba
- Qwen3.8-Max
- 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
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.