Overall score
63.0
Rank #14 · A confidence
Alibaba Cloud · stable
Alibaba Cloud's documented Qwen model balancing capability, cost and built-in tools.
Overall score
63.0
Rank #14 · A confidence
Capability
63.5
31 eligible benchmark families
Coverage
86%
Confidence A
Benchmarks scored
31
32 raw result rows
Model specification
Identity, configuration and price are preserved as dated source records.
Category profile
A category remains Not evaluated until an eligible source-qualified result is attached.
Benchmark scores
Best published score per benchmark. Open any row for the full per-benchmark leaderboard.
| Benchmark | Category | Score | Date |
|---|---|---|---|
| IFEval | instruction following | 94.6% | 2026-07-15 |
| τ-benchRanking weighted | agents | 93% | 2026-07-15 |
| τ²-Bench TelecomRanking weighted | agents | 92.9825% | 2026-07-15 |
| HMMT Feb 2026Ranking weighted | mathematics | 92.9% | 2026-07-15 |
| LongBench v2 | long context | 91.7% | 2026-07-15 |
| GPQA DiamondRanking weighted | reasoning | 90.3% | 2026-07-15 |
| LiveCodeBenchRanking weighted | coding | 89.6% | 2026-07-15 |
| MMLU-ProRanking weighted | research | 88.5% | 2026-07-15 |
| CharXivRanking weighted | multimodal | 85.9% | 2026-07-15 |
| IFBench | instruction following | 79.1% | 2026-07-15 |
| MMMU-ProRanking weighted | multimodal | 79% | 2026-07-15 |
| SWE-bench VerifiedRanking weighted | coding | 77.7% | 2026-07-15 |
| OSWorld-VerifiedRanking weighted | agents | 73.3% | 2026-07-15 |
| MCP AtlasRanking weighted | agents | 73.2% | 2026-07-15 |
| Berkeley Function-Calling Leaderboard | agents | 72.9% | 2026-07-15 |
| SuperGPQARanking weighted | reasoning | 71.4% | 2026-07-15 |
| Terminal-BenchRanking weighted | agents | 70.3% | 2026-07-15 |
| AA Long Context ReasoningRanking weighted | research | 65% | 2026-07-15 |
| SWE-Bench ProRanking weighted | coding | 57.6% | 2026-07-15 |
| SciCodeRanking weighted | coding | 51.3% | 2026-07-15 |
| Long-Horizon-Terminal-BenchRanking weighted | agents | 47% | 2026-07-15 |
| Terminal-Bench HardRanking weighted | agents | 46.9697% | 2026-07-15 |
| EnterpriseOps-Gym-AARanking weighted | agents | 40.5551% | 2026-07-15 |
| Humanity's Last ExamRanking weighted | reasoning | 34.7% | 2026-07-15 |
| APEX-Agents-AARanking weighted | agents | 22.4189% | 2026-07-15 |
| GDPval-AA v2Ranking weighted | agents | 21.813% | 2026-07-15 |
| τ³-BankingRanking weighted | agents | 17.8694% | 2026-07-15 |
| CritPtRanking weighted | reasoning | 9.1429% | 2026-07-15 |
| OSWorldRanking weighted | agents | 2.8% | 2026-07-15 |
| AA-OmniscienceRanking weighted | research | 2.3667 index | 2026-07-15 |
| Harvey LAB-AARanking weighted | agents | 1.6667% | 2026-07-15 |
Showing the best of 32 raw result rows across 31 benchmark families.
Price and efficiency
Operational values are shown only when the source publishes a comparable measurement or a valid derivation.
Verification summary
News and X posts are structurally excluded from this model's evidence graph.
Missing publication dimensions: efficiency, value. The last source check for this exact model was 2026-07-14.
Related models
Exact variants remain separate even when they share a provider or family.