Alibaba
availableShows if the model has enough results for an index.Qwen3.8-Omni-Flash
Qwen3.8-Omni-Flash is a reasoning model from Alibaba. 10 benchmarks count toward its score, in 5 categories.
IndexOverall score out of 100.62.5 ±8.1
CoverageShare of the index weight with results.70%
SpeedOutput tokens per second.—
Input / 1MUS dollars per 1M input tokens.N/A
Output / 1MUS dollars per 1M output tokens.N/A
ContextMaximum tokens in one request.1M
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
10 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 | 96.2% | — | — | — | Moonshot AI / MathVision authors |
| LiveCodeBench v6 | Coding | 92.6% | 61.3 | — | — | LiveCodeBench maintainers |
| MathVision | Multimodal | 91.8% | — | — | — | Qwen |
| CharXiv Reasoning | Multimodal | 91.4% | 70.2 | — | — | CharXiv authors |
| Graduate-Level Google-Proof Q&A | Knowledge | 91.0% | 62.3 | — | — | David Rein et al. |
| GPQA Diamond | Knowledge | 91.0% | 62.3 | — | — | David Rein et al. |
| RealWorldQA | Multimodal | 87.7% | 61.6 | — | — | Qwen |
| AndroidWorld | Agentic | 87.1% | — | — | — | Z.AI |
| CharXiv Reasoning without tools | Multimodal | 83.5% | — | — | — | CharXiv authors |
| Instruction Following Benchmark | Instruction | 81.5% | 60.9 | — | — | Benchmark authors |
| LVBench | Multimodal | 76.9% | — | — | — | Qwen Team |
| CoWorkBench | Agentic | 75.3% | — | — | — | Qwen Team |
| ERQA | Multimodal | 71.0% | 65.3 | — | — | Qwen |
| SWE-bench Pro | Coding | 63.3% | 65.2 | — | — | Xiang Deng et al. |
| Vision2Web | Multimodal | 62.9% | — | — | — | Z.AI |
| DeepSWE | Agentic | 57.8% | 65.8 | — | — | Datacurve AI |
| NL2Repo | Coding | 48.9% | 63.4 | — | — | MiniMax |
| Humanity's Last Exam | Knowledge | 36.5% | 59.7 | — | — | Center for AI Safety et al. |
10 benchmarks count, from 11 of 18 results. A grey row does not count. Too few models took that benchmark.