Category scores
Out of 100: 100 = the best tracked model in the category.
| Reasoning | 69 | |
| Mathematics | 45 | |
| Code | 85 | |
| Agents & real work | — | |
| Knowledge | 31 | |
| Long context | 95 | |
| Multimodal | 86 |
EditionUpdated daily
Ranking / DeepSeek V4.1 Flash
DeepSeek V4.1 Flash
DeepSeek · Open · context 1M. Ranked #17 of 26 with 600 ERAZ points out of 1000.
ERAZ rank#17/ 26
Points600/ 1000
Coverage64%
Benchmarks won0/ 14
Input price / M$0.3
Output price / M$1.20
Points over time
| Day | Points | Change |
|---|
Results on each benchmark
| Benchmark | Score | Rank | Out of 100 | Source |
|---|---|---|---|---|
| Humanity's Last Exam | 39.2% | #24 / 26 | 64 | src ↗ |
| ARC-AGI-2 | 72.9% | #10 / 13 | 77 | |
| ARC-AGI-3 | not published | — | — | |
| FrontierMath (Tiers 1-3) | 67.4% | #14 / 16 | 72 | src ↗ |
| FrontierMath (Tier 4) | 26.8% | #13 / 16 | 27 | src ↗ |
| SWE-bench Pro | not published | — | — | |
| FrontierSWE v2 | not published | — | — | |
| Terminal-Bench 2.1 | 74.5% | #8 / 12 | 85 | src ↗ |
| OSWorld 2.0 | not published | — | — | |
| GDPval-AA | not published | — | — | |
| GPQA Diamond | 90.9% | #15 / 15 | 92 | src ↗ |
| AA-Omniscience | -5.3 | #24 / 26 | 0 | src ↗ |
| AA-LCR | 84% | #7 / 26 | 95 | src ↗ |
| MMMU-Pro | 77% | #12 / 14 | 86 | src ↗ |
Artificial Analysis Intelligence Index : 45.1 · Source page ↗
Nearby models in the ranking
</> Embed this ranking
Show DeepSeek V4.1 Flash's ranking on your site or in a README. The badge updates every day.
