Qwen3 235B A22B Instruct 2507
Qwen / Qwen
44scores
33benchmarks
$0.071 / $0.1 per 1M tokenscost in/out
Metadata
Qwen Open source
Aliases: qwen-qwen3-235b-a22b-07-25, qwen-qwen3-235b-a22b-2507, qwen/qwen3-235b-a22b-07-25, qwen/qwen3-235b-a22b-2507, qwen3-235b-a22b-07-25, qwen3-235b-a22b-2507
| Benchmark | Category | Rank | Score | Sampled |
|---|---|---|---|---|
| ARC-AGI-1 | Agentic | 127 | 11 | 2026-05-05 |
| ARC-AGI-2 | Agentic | 111 | 1.25 | 2026-05-05 |
| Berkeley Function-Calling Leaderboard | Agentic | 23 | 52.15% | 2026-05-27 |
| Berkeley Function-Calling Leaderboard | Agentic | 31 | 47.99% | 2026-05-27 |
| Galileo Agent Leaderboard | Agentic | 6 | 0.53 | 2026-05-06 |
| MCP-Universe | Agentic | 26 | 18.18 | 2026-05-06 |
| Tau2 Airline | Agentic | 20 | 0.44 | 2026-05-06 |
| Tau2-Bench Telecom | Agentic | 171 | 53.2% | 2026-05-11 |
| Tau2-Bench Telecom | Agentic | 225 | 33.3% | 2026-05-11 |
| Terminal-Bench Hard | Agentic | 177 | 15.2% | 2026-05-11 |
| Terminal-Bench Hard | Agentic | 188 | 13.6% | 2026-05-11 |
| UAVBench | Agentic | 1 | 83.55 | 2026-05-06 |
| VitaBench | Agentic | 23 | 12.30 | 2026-05-06 |
| MultiPL-E | Coding | 1 | 0.879 | 2026-05-27 |
| SciCode | Coding | 67 | 42.4% | 2026-05-11 |
| SciCode | Coding | 177 | 36% | 2026-05-11 |
| MMTU | Data | 12 | 0.52 | 2026-05-06 |
| GSMA Open Telco Leaderboard | Domain | 22 | 63.62 | 2026-05-06 |
| IslamicLegalBench | Domain | 9 | 48.87 | 2026-05-06 |
| Arena-Hard v2 | General Knowledge | 4 | 0.79 | 2026-05-06 |
| CSimpleQA | General Knowledge | 2 | 0.84 | 2026-05-06 |
| MMLU-ProX | General Knowledge | 8 | 0.79 | 2026-05-06 |
| MMLU-Redux | General Knowledge | 12 | 0.93 | 2026-05-06 |
| HUMAINE | Human Preference | 33 | 3.40 | 2026-05-06 |
| Multi-IF | Instruction Following | 6 | 0.78 | 2026-05-06 |
| Artificial Analysis Intelligence Index | Intelligence | 153 | 29.54 | 2026-05-11 |
| Artificial Analysis Intelligence Index | Intelligence | 193 | 24.96 | 2026-05-11 |
| Humanity's Last Exam | Intelligence | 95 | 15% | 2026-05-11 |
| Humanity's Last Exam | Intelligence | 144 | 10.6% | 2026-05-11 |
| MMLU-Pro | Intelligence | 39 | 84.3% | 2026-05-11 |
| MMLU-Pro | Intelligence | 66 | 82.8% | 2026-05-11 |
| AIME 2025 | Math | 22 | 91% | 2026-05-11 |
| AIME 2025 | Math | 92 | 71.7% | 2026-05-11 |
| PolyMATH | Mathematics | 12 | 0.50 | 2026-05-06 |
| Design Arena | Multimodal | 94 | 1097 | 2026-05-06 |
| Artificial Analysis Openness Index | Openness | 95 | 44.44 | 2026-05-11 |
| Artificial Analysis Openness Index | Openness | 96 | 44.44 | 2026-05-11 |
| GPQA Diamond | Reasoning | 112 | 79% | 2026-05-11 |
| GPQA Diamond | Reasoning | 154 | 75.3% | 2026-05-11 |
| CritPt | Science | 347 | 0% | 2026-05-11 |
| CritPt | Science | 348 | 0% | 2026-05-11 |
| BFCL-v3 | Tool Use | 8 | 0.71 | 2026-05-06 |
| Creative Writing v3 | Writing | 3 | 0.88 | 2026-05-06 |
| WritingBench | Writing | 7 | 0.85 | 2026-05-06 |
No matching rows.