Alibaba
availableShows if the model has enough results for an index.Qwen3.7 Plus
Qwen3.7 Plus is a reasoning model from Alibaba. 49 benchmarks count toward its score, in 7 categories.
IndexOverall score out of 100.58.2 ±2.8
CoverageShare of the index weight with results.95%
SpeedOutput tokens per second.13/s
Input / 1MUS dollars per 1M input tokens.$0.32
Output / 1MUS dollars per 1M output tokens.$1.28
ContextMaximum tokens in one request.1M
EloLMArena rating and rank.1454 (#39)
The index is a score out of 100. The ± range shows how much it can change.
39,334 votes. Elo shows what people prefer. It does not change the score.
CapabilitiesScore per category, out of 100.
Out of 100Results
49 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. |
|---|---|---|---|---|---|---|
| Instruction-Following Eval | Instruction | 94.6% | 55.1 | — | — | Jeffrey Zhou et al. |
| MMLU-Redux | Knowledge | 94.5% | 53.2 | — | — | Qwen |
| τ²-Bench Tool-Agent-User Evaluation | Agentic | 93.0% | 65.5 | — | — | Victor Barres et al. |
| Harvard-MIT Mathematics Tournament February 2026 | Math | 92.9% | 59.7 | — | — | Qwen |
| MRCRv2 | Reasoning | 91.7% | — | — | — | OpenAI |
| OmniDocBench 1.5 | Multimodal | 91.4% | — | — | — | OpenAI |
| MathVision | Multimodal | 90.3% | — | — | — | Qwen |
| Graduate-Level Google-Proof Q&A | Knowledge | 90.3% | 61.6 | — | — | David Rein et al. |
| GPQA Diamond | Knowledge | 90.3% | 61.6 | — | — | David Rein et al. |
| Artificial Analysis GPQA Diamond | Knowledge | 90.0% | 60.8 | — | — | Artificial Analysis |
| LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code | Coding | 89.6% | 65.8 | — | — | Naman Jain et al. |
| MMMLU | Knowledge | 89.0% | — | — | — | OpenAI |
| MAXIFE | Multilingual | 88.8% | — | — | — | Qwen |
| Massive Multitask Language Understanding Professional | Knowledge | 88.5% | 60.0 | — | — | Yubo Wang et al. |
| Video-MME with subtitle | Multimodal | 88.0% | — | — | — | Qwen |
| MLVU mean average | Multimodal | 87.4% | — | — | — | Qwen |
| RealWorldQA | Multimodal | 86.9% | 60.0 | — | — | Qwen |
| IMOAnswerBench | Math | 86.0% | — | — | — | DeepSeek-AI |
| CharXiv Reasoning | Multimodal | 85.9% | 63.9 | — | — | CharXiv authors |
| VideoMMMU | Multimodal | 85.4% | — | — | — | Qwen |
| MMLU-ProX | Multilingual | 85.4% | — | — | — | MMLU-ProX authors |
| PolyMath | Multilingual | 84.0% | — | — | — | Qwen |
| INCLUDE | Multilingual | 83.0% | — | — | — | Qwen |
| GPQA diamond | Knowledge | 81.8% | 53.8 | none effort | — | Epoch AI |
| SimpleVQA | Multimodal | 81.7% | 76.1 | — | — | Z.AI |
| AndroidWorld | Agentic | 81.0% | — | — | — | Z.AI |
| Artificial Analysis MMMU-Pro | Multimodal | 80.5% | 65.5 | — | — | Artificial Analysis |
| OTIS Mock AIME 2024-2025 | Math | 80.0% | 56.3 | none effort | — | Epoch AI |
| Instruction Following Benchmark | Instruction | 79.1% | 58.1 | — | — | Benchmark authors |
| Massive Multi-discipline Multimodal Understanding Pro | Multimodal | 79.0% | 55.9 | — | — | MMMU-Pro authors |
| ScreenSpot Pro | Multimodal | 79.0% | 60.8 | — | — | Kaixin Li et al. |
| Artificial Analysis IFBench | Instruction | 78.0% | 68.2 | — | — | Artificial Analysis |
| Software Engineering Benchmark Verified | Coding | 77.7% | 59.9 | — | — | Carlos E. Jimenez et al. |
| OSWorld-Verified | Agentic | 73.3% | 62.0 | — | — | Tianbao Xie et al. |
| MCP Atlas | Agentic | 73.2% | 63.3 | — | — | OpenAI |
| Artificial Analysis Long Context Reasoning | Reasoning | 73.0% | 58.7 | — | — | Artificial Analysis |
| Berkeley Function Calling Leaderboard v4 | Agentic | 72.9% | 57.9 | — | — | Arcee AI |
| SuperGPQA: Scaling LLM Evaluation Across 285 Graduate Disciplines | Knowledge | 71.4% | 56.6 | — | — | Xiaoxuan Du et al. |
| MedXpertQA Multimodal | Multimodal | 71.0% | — | — | — | Meta AI |
| OCRBench V2 | Multimodal | 70.7% | — | — | — | OCRBench authors |
| ERQA | Multimodal | 69.8% | 64.2 | — | — | Qwen |
| Claw-Eval | Agentic | 62.7% | 57.0 | — | — | Bowen Ye et al. |
| DeepPlanning | Agentic | 62.3% | — | — | — | DeepPlanning authors |
| QwenClawBench | Agentic | 61.8% | 60.5 | — | — | Qwen |
| NOVA-63 | Multilingual | 58.8% | — | — | — | Qwen |
| SWE-bench Pro | Coding | 57.6% | 59.7 | — | — | Xiang Deng et al. |
| Artificial Analysis Coding Index | Coding | 55.9% | 58.3 | — | — | Artificial Analysis |
| SkillsBench | Coding | 54.3% | 69.0 | OpenHands | 11 Sept 2026 | Vals AI |
| Terminal-Bench 2.1 | Agentic | 52.8% | 55.2 | — | 21 Sept 2026 | Vals AI |
| Scientific Code Benchmark | Coding | 51.3% | 61.9 | — | — | Benchmark authors |
| ODINW13 | Multimodal | 51.1% | — | — | — | Qwen |
| Vibe Code Bench v1.1 | Coding | 46.4% | 61.5 | OpenHands | 21 Sept 2026 | Vals AI |
| Artificial Analysis SciCode | Coding | 46.1% | 56.8 | — | — | Artificial Analysis |
| VITA-Bench | Agentic | 45.6% | 60.8 | — | — | Meituan LongCat Team |
| MMSearch-Plus | Multimodal | 41.4% | — | — | — | Z.AI |
| NL2Repo | Coding | 41.1% | 57.1 | — | — | MiniMax |
| Artificial Analysis Humanity's Last Exam | Knowledge | 35.6% | 63.2 | — | — | Artificial Analysis |
| Humanity's Last Exam | Knowledge | 34.7% | 58.2 | — | — | Center for AI Safety et al. |
| FrontierMath-Tiers-1-3-v2-Private | Math | 34.4% | 50.8 | none effort | — | Epoch AI |
| Artificial Analysis Intelligence Index | Knowledge | 25.2% | 53.9 | — | — | Artificial Analysis |
| Apex | Math | 22.7% | — | — | — | DeepSeek-AI |
| Artificial Analysis Omniscience Accuracy | Knowledge | 22.5% | 41.7 | — | — | Artificial Analysis |
| APEX-Agents-AA | Agentic | 22.4% | 58.8 | — | — | Artificial Analysis / Mercor |
| Artificial Analysis Agentic Index | Agentic | 19.7% | 53.2 | — | — | Artificial Analysis |
| Mystery Game Puzzles | Reasoning | 17.0% | 52.0 | — | — | Epoch AI |
| Code Migration | Coding | 12.9% | 53.1 | — | 21 Sept 2026 | Vals AI |
| GDPval-AA normalized | Agentic | 12.8% | 45.4 | — | — | Artificial Analysis |
| Critical Physics Tasks | Reasoning | 9.1% | 57.5 | — | — | Artificial Analysis |
| Chess Puzzles | Reasoning | 9.0% | 35.2 | none effort | — | Epoch AI |
| OSWorld 2.0 | Agentic | 2.8% | 57.3 | — | — | Mengqi Yuan et al. |
| Agent Arena command recovery | Agentic | -4.4 | 62.4 | — | 15 Sept 2026 | LMArena |
| Agent Arena steerability | Agentic | -5.4 | 61.3 | — | 15 Sept 2026 | LMArena |
| Agent Arena task outcome | Agentic | -7.1 | 59.3 | — | 15 Sept 2026 | LMArena |
49 benchmarks count, from 53 of 73 results. A grey row does not count. Too few models took that benchmark.