Alibaba
availableShows if the model has enough results for an index.Qwen3.5-27B
Qwen3.5-27B is a reasoning model from Alibaba. 19 benchmarks count toward its score, in 6 categories.
IndexOverall score. 50 is the middle.53.2 ±5.2
CoverageShare of the index weight with results.85%
SpeedOutput tokens per second.34/s
Input / 1MUS dollars per 1M input tokens.$0.195
Output / 1MUS dollars per 1M output tokens.$1.56
ContextMaximum tokens in one request.262K
EloLMArena rating and rank.1408 (#131)
50 is the middle of the board. The range shows the doubt in the index.
27,227 votes. Elo shows what people prefer. It does not change the score.
CapabilitiesScore per category. 50 is the middle.
50 is the middleResults
19 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result on the index scale. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| Instruction-Following Eval | Instruction | 95.0% | 56.0 | — | — | Jeffrey Zhou et al. |
| τ²-Bench Tool-Agent-User Evaluation | Agentic | 93.9% | 66.2 | — | — | Victor Barres et al. |
| V* | Multimodal | 93.7% | 53.7 | — | — | Z.AI |
| Massive Multitask Language Understanding Professional | Knowledge | 86.1% | 56.2 | — | — | Yubo Wang et al. |
| MathVision | Multimodal | 86.0% | — | — | — | Qwen |
| Artificial Analysis GPQA Diamond | Knowledge | 85.8% | 56.5 | — | — | Artificial Analysis |
| Graduate-Level Google-Proof Q&A | Knowledge | 85.5% | 57.2 | — | — | David Rein et al. |
| Massive Multi-discipline Multimodal Understanding | Multimodal | 82.3% | 51.5 | — | — | MMMU authors |
| MMLU-ProX | Multilingual | 82.2% | — | — | — | MMLU-ProX authors |
| Artificial Analysis Long Context Reasoning | Reasoning | 77.7% | 62.0 | — | — | Artificial Analysis |
| Artificial Analysis IFBench | Instruction | 75.6% | 65.8 | — | — | Artificial Analysis |
| Artificial Analysis MMMU-Pro | Multimodal | 75.0% | 58.7 | — | — | Artificial Analysis |
| Multimodal Multi-disciplinary Video Understanding | Multimodal | 73.3% | — | — | — | MMVU benchmark maintainers |
| Software Engineering Benchmark Verified | Coding | 72.4% | 55.6 | — | — | Carlos E. Jimenez et al. |
| SuperGPQA: Scaling LLM Evaluation Across 285 Graduate Disciplines | Knowledge | 65.6% | 51.8 | — | — | Xiaoxuan Du et al. |
| BrowseComp | Agentic | 61.0% | 51.1 | — | — | OpenAI |
| LongBench v2 | Reasoning | 60.6% | — | — | — | LongBench v2 authors |
| SWE-Rebench | Coding | 58.9% | — | — | — | Nebius |
| OSWorld-Verified | Agentic | 56.2% | 46.0 | — | — | Tianbao Xie et al. |
| Gert Labs Composite Game Benchmark | Agentic | 39.4% | 47.5 | — | — | Gert Labs |
| Artificial Analysis Humanity's Last Exam | Knowledge | 23.9% | 50.5 | — | — | Artificial Analysis |
| Artificial Analysis Intelligence Index | Knowledge | 22.9% | 51.0 | — | — | Artificial Analysis |
| Artificial Analysis Omniscience Accuracy | Knowledge | 20.7% | 39.5 | — | — | Artificial Analysis |
| Critical Physics Tasks | Reasoning | 0.9% | 40.3 | — | — | Artificial Analysis |
19 benchmarks count, from 19 of 24 results. A grey row does not count. Too few models took that benchmark.