Alibaba
availableShows if the model has enough results for an index.Qwen3.8-Flash-Next
Qwen3.8-Flash-Next is a reasoning model from Alibaba. 31 benchmarks count toward its score, in 7 categories.
IndexOverall score out of 100.66.4 ±3.4
CoverageShare of the index weight with results.95%
SpeedOutput tokens per second.54/s
Input / 1MUS dollars per 1M input tokens.Free
Output / 1MUS dollars per 1M output tokens.Free
ContextMaximum tokens in one request.262K
EloLMArena rating and rank.N/A
The index is a score out of 100. The ± range shows how much it can change.
CapabilitiesScore per category, out of 100.
Out of 100Results
31 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result as a score out of 100. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| MathVision with Python | Multimodal | 95.7% | — | — | — | Moonshot AI / MathVision authors |
| Artificial Analysis GPQA Diamond | Knowledge | 92.3% | 63.1 | — | — | Artificial Analysis |
| LiveCodeBench v6 | Coding | 91.9% | 60.7 | — | — | LiveCodeBench maintainers |
| Graduate-Level Google-Proof Q&A | Knowledge | 91.7% | 62.9 | — | — | David Rein et al. |
| GPQA Diamond | Knowledge | 91.7% | 62.9 | — | — | David Rein et al. |
| MathVision | Multimodal | 90.6% | — | — | — | Qwen |
| CharXiv Reasoning | Multimodal | 90.6% | 69.3 | — | — | CharXiv authors |
| RealWorldQA | Multimodal | 88.5% | 63.2 | — | — | Qwen |
| LiveBench Reasoning | Reasoning | 87.4% | 77.3 | — | 25 Jun 2026 | LiveBench |
| LiveBench Mathematics | Math | 85.8% | 62.5 | — | 25 Jun 2026 | LiveBench |
| CharXiv Reasoning without tools | Multimodal | 84.6% | — | — | — | CharXiv authors |
| AndroidWorld | Agentic | 84.5% | — | — | — | Z.AI |
| Instruction Following Benchmark | Instruction | 81.3% | 60.6 | — | — | Benchmark authors |
| Artificial Analysis MMMU-Pro | Multimodal | 79.8% | 64.6 | — | — | Artificial Analysis |
| Artificial Analysis Long Context Reasoning | Reasoning | 79.7% | 63.4 | — | — | Artificial Analysis |
| LiveBench Instruction Following | Instruction | 77.1% | 81.6 | — | 25 Jun 2026 | LiveBench |
| LVBench | Multimodal | 76.6% | — | — | — | Qwen Team |
| LiveBench Language | Knowledge | 74.6% | 60.6 | — | 25 Jun 2026 | LiveBench |
| LiveBench Data Analysis | Reasoning | 74.2% | 59.1 | — | 25 Jun 2026 | LiveBench |
| CoWorkBench | Agentic | 73.9% | — | — | — | Qwen Team |
| Toolathlon-Verified | Agentic | 73.5% | 71.8 | — | — | Moonshot AI |
| Artificial Analysis Coding Index | Coding | 73.0% | 70.4 | — | — | Artificial Analysis |
| LiveBench Coding | Coding | 72.6% | 58.1 | — | 25 Jun 2026 | LiveBench |
| ERQA | Multimodal | 72.3% | 66.5 | — | — | Qwen |
| Vision2Web | Multimodal | 64.0% | — | — | — | Z.AI |
| SWE-bench Pro | Coding | 62.5% | 64.4 | — | — | Xiang Deng et al. |
| LiveBench Agentic Coding | Agentic | 61.6% | 74.7 | — | 25 Jun 2026 | LiveBench |
| DeepSWE | Agentic | 58.7% | 66.4 | — | — | Datacurve AI |
| JobBench | Agentic | 55.7% | 72.4 | — | — | Yuetai Li et al. |
| GDPval-AA normalized | Agentic | 55.6% | 78.3 | — | — | Artificial Analysis |
| Agents' Last Exam | Agentic | 51.2% | 89.4 | — | — | DeepSeek-AI |
| Artificial Analysis SciCode | Coding | 50.6% | 63.1 | — | — | Artificial Analysis |
| NL2Repo | Coding | 48.1% | 62.7 | — | — | MiniMax |
| Artificial Analysis Intelligence Index | Knowledge | 39.8% | 72.2 | — | — | Artificial Analysis |
| Artificial Analysis Humanity's Last Exam | Knowledge | 38.0% | 65.8 | — | — | Artificial Analysis |
| Humanity's Last Exam | Knowledge | 35.9% | 59.2 | — | — | Center for AI Safety et al. |
| Humanity's Last Exam without tools | Knowledge | 35.9% | 59.2 | — | — | OpenAI |
| Artificial Analysis Omniscience Accuracy | Knowledge | 24.5% | 44.2 | — | — | Artificial Analysis |
| OSWorld 2.0 | Agentic | 19.4% | 65.2 | — | — | Mengqi Yuan et al. |
| Critical Physics Tasks | Reasoning | 11.1% | 61.7 | — | — | Artificial Analysis |
| Agent Arena task outcome | Agentic | 8.9 | 77.4 | — | 15 Sept 2026 | LMArena |
| Agent Arena command recovery | Agentic | -2.0 | 65.1 | — | 15 Sept 2026 | LMArena |
| Agent Arena steerability | Agentic | -4.7 | 62.1 | — | 15 Sept 2026 | LMArena |
31 benchmarks count, from 36 of 43 results. A grey row does not count. Too few models took that benchmark.