pith:NGQGVISH
Ovis2.5 Technical Report
Ovis2.5 processes images at native resolutions and adds reflection to reach 78.3 on the OpenCompass multimodal leaderboard.
arxiv:2508.11737 v1 · 2025-08-15 · cs.CV · cs.AI · cs.CL · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{NGQGVISHEUGLHCFXJU4WYWMCX7}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Ovis2.5-9B averages 78.3 on the OpenCompass multimodal leaderboard, marking a substantial improvement over Ovis2-8B and achieving state-of-the-art results among open-source MLLMs in the sub-40B parameter range; Ovis2.5-2B scores 73.9 and establishes SOTA for its size.
That the benchmark gains are primarily attributable to the native-resolution vision transformer and reflection mechanism rather than differences in training data volume, quality, or undisclosed hyperparameter tuning.
Ovis2.5 introduces native-resolution visual processing and reflective chain-of-thought to reach SOTA open-source multimodal performance at 9B and 2B scales on benchmarks including STEM and chart analysis.
Formal links
Cited by
Receipt and verification
| First computed | 2026-05-17T23:38:50.260604Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
69a06aa247250cb388b74d396c5982bff1897a4b4e5fcd96726618264aa54fdd
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/NGQGVISHEUGLHCFXJU4WYWMCX7 \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 69a06aa247250cb388b74d396c5982bff1897a4b4e5fcd96726618264aa54fdd
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "a1d9b04e4e2d7624437f702c0157551661eccfa59b8bfbd4cd315543c7e0a673",
"cross_cats_sorted": [
"cs.AI",
"cs.CL",
"cs.LG"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CV",
"submitted_at": "2025-08-15T17:01:08Z",
"title_canon_sha256": "fc99a4c0a3021fc73f0bfa752295498c9fc389733691ba767bc28f3dddb295dc"
},
"schema_version": "1.0",
"source": {
"id": "2508.11737",
"kind": "arxiv",
"version": 1
}
}