Category scores
Out of 100: 100 = the best tracked model in the category.
| Reasoning | 70 | |
| Mathematics | 60 | |
| Code | 54 | |
| Agents & real work | 27 | |
| Knowledge | 49 | |
| Long context | 91 | |
| Multimodal | 94 |
EditionUpdated daily
Ranking / Qwen3.8 Max
Qwen3.8 Max
Alibaba · Proprietary · context 1M. Ranked #21 of 26 with 559 ERAZ points out of 1000.
ERAZ rank#21/ 26
Points559/ 1000
Coverage79%
Benchmarks won0/ 14
Input price / M$2
Output price / M$6
Points over time
| Day | Points | Change |
|---|
Results on each benchmark
| Benchmark | Score | Rank | Out of 100 | Source |
|---|---|---|---|---|
| Humanity's Last Exam | 43.1% | #18 / 26 | 70 | src ↗ |
| ARC-AGI-2 | not published | — | — | |
| ARC-AGI-3 | not published | — | — | |
| FrontierMath (Tiers 1-3) | 74.7% | #11 / 16 | 80 | src ↗ |
| FrontierMath (Tier 4) | 46.3% | #11 / 16 | 46 | src ↗ |
| SWE-bench Pro | 67.7% | #6 / 9 | 75 | src ↗ |
| FrontierSWE v2 | 15.8% | #14 / 14 | 24 | src ↗ |
| Terminal-Bench 2.1 | 67.4% | #11 / 12 | 77 | src ↗ |
| OSWorld 2.0 | 19.4% | #11 / 11 | 27 | src ↗ |
| GDPval-AA | not published | — | — | |
| GPQA Diamond | 92.6% | #10 / 15 | 95 | src ↗ |
| AA-Omniscience | 12 | #17 / 26 | 26 | src ↗ |
| AA-LCR | 80.3% | #19 / 26 | 91 | src ↗ |
| MMMU-Pro | 82.8% | #7 / 14 | 94 | src ↗ |
Artificial Analysis Intelligence Index : 45.4 · Source page ↗
Nearby models in the ranking
</> Embed this ranking
Show Qwen3.8 Max's ranking on your site or in a README. The badge updates every day.
