Category scores
Out of 100: 100 = the best tracked model in the category.
| Reasoning | 87 | |
| Mathematics | 84 | |
| Code | 84 | |
| Agents & real work | 82 | |
| Knowledge | 94 | |
| Long context | 90 | |
| Multimodal | — |
EditionUpdated daily
Ranking / Gemini 4 Argon
Gemini 4 Argon
Google · Proprietary · context 1M. Ranked #6 of 26 with 821 ERAZ points out of 1000.
ERAZ rank#6/ 26
Points821/ 1000
Coverage81%
Benchmarks won1/ 14
Input price / M$2
Output price / M$10
Points over time
| Day | Points | Change |
|---|
Results on each benchmark
| Benchmark | Score | Rank | Out of 100 | Source |
|---|---|---|---|---|
| Humanity's Last Exam | 57.1% | #3 / 26 | 93 | src ↗ |
| ARC-AGI-2 | 91.3% | #5 / 13 | 96 | src ↗ |
| ARC-AGI-3 | 46.3% | #3 / 9 | 74 | src ↗ |
| FrontierMath (Tiers 1-3) | 86% | #7 / 16 | 92 | src ↗ |
| FrontierMath (Tier 4) | 78% | #7 / 16 | 78 | src ↗ |
| SWE-bench Pro | not published | — | — | |
| FrontierSWE v2 | 55% | #5 / 14 | 84 | src ↗ |
| Terminal-Bench 2.1 | not published | — | — | |
| OSWorld 2.0 | 69.2% | #3 / 11 | 95 | src ↗ |
| GDPval-AA | 1624 | #14 / 23 | 72 | src ↗ |
| GPQA Diamond | 96.5% | #1 / 15 | 100 | |
| AA-Omniscience | 42.4 | #4 / 26 | 91 | src ↗ |
| AA-LCR | 79.7% | #21 / 26 | 90 | src ↗ |
| MMMU-Pro | not published | — | — |
Artificial Analysis Intelligence Index : 52.6 · Source page ↗
Nearby models in the ranking
</> Embed this ranking
Show Gemini 4 Argon's ranking on your site or in a README. The badge updates every day.
