Category scores
Out of 100: 100 = the best tracked model in the category.
| Reasoning | 69 | |
| Mathematics | — | |
| Code | — | |
| Agents & real work | — | |
| Knowledge | 38 | |
| Long context | 91 | |
| Multimodal | — |
EditionUpdated daily
Ranking / Qwen3.8 2.4T A95B
Qwen3.8 2.4T A95B
Alibaba · Open · context not disclosed. Ranked #25 of 26 with 522 ERAZ points out of 1000.
ERAZ rank#25/ 26
Points522/ 1000
Coverage29%
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 | 42.4% | #20 / 26 | 69 | src ↗ |
| ARC-AGI-2 | not published | — | — | |
| ARC-AGI-3 | not published | — | — | |
| FrontierMath (Tiers 1-3) | not published | — | — | |
| FrontierMath (Tier 4) | not published | — | — | |
| SWE-bench Pro | not published | — | — | |
| FrontierSWE v2 | not published | — | — | |
| Terminal-Bench 2.1 | not published | — | — | |
| OSWorld 2.0 | not published | — | — | |
| GDPval-AA | not published | — | — | |
| GPQA Diamond | 93.5% | #8 / 15 | 96 | src ↗ |
| AA-Omniscience | 4.3 | #21 / 26 | 9 | src ↗ |
| AA-LCR | 80.3% | #18 / 26 | 91 | src ↗ |
| MMMU-Pro | not published | — | — |
Artificial Analysis Intelligence Index : 39.9 · Source page ↗
Nearby models in the ranking
</> Embed this ranking
Show Qwen3.8 2.4T A95B's ranking on your site or in a README. The badge updates every day.
