Category scores
Out of 100: 100 = the best tracked model in the category.
| Reasoning | 62 | |
| Mathematics | — | |
| Code | 70 | |
| Agents & real work | 56 | |
| Knowledge | 31 | |
| Long context | 90 | |
| Multimodal | 90 |
EditionUpdated daily
Ranking / Qwen3.8-Flash-Next
Qwen3.8-Flash-Next
Alibaba · Open · context 262K. Ranked #18 of 26 with 569 ERAZ points out of 1000.
ERAZ rank#18/ 26
Points569/ 1000
Coverage60%
Benchmarks won0/ 14
Input price / M$0.15
Output price / M$0.47
Points over time
| Day | Points | Change |
|---|
Results on each benchmark
| Benchmark | Score | Rank | Out of 100 | Source |
|---|---|---|---|---|
| Humanity's Last Exam | 38% | #25 / 26 | 62 | 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 | 62.5% | #9 / 9 | 70 | src ↗ |
| FrontierSWE v2 | not published | — | — | |
| Terminal-Bench 2.1 | not published | — | — | |
| OSWorld 2.0 | 19.4% | #10 / 11 | 27 | src ↗ |
| GDPval-AA | 1648 | #13 / 23 | 75 | src ↗ |
| GPQA Diamond | 92.3% | #12 / 15 | 94 | src ↗ |
| AA-Omniscience | -9.7 | #26 / 26 | 0 | src ↗ |
| AA-LCR | 79.7% | #24 / 26 | 90 | src ↗ |
| MMMU-Pro | 79.8% | #10 / 14 | 90 | src ↗ |
Artificial Analysis Intelligence Index : 39.8 · Source page ↗
Nearby models in the ranking
</> Embed this ranking
Show Qwen3.8-Flash-Next's ranking on your site or in a README. The badge updates every day.
