ODINW13 (ODINW13)

A visual detection and grounding benchmark slice used to compare zero-shot object understanding across diverse domains.

Top Models on ODINW13 — March 2026

As of March 2026, Qwen3.6 Plus leads the ODINW13 leaderboard with 51.8% , followed by Qwen3.5 397B (47.0%) and Gemini 3 Pro (46.3%).

3 modelsMultimodal & GroundedCurrentDisplay onlyUpdated April 2, 2026

According to BenchLM.ai, Qwen3.6 Plus leads the ODINW13 benchmark with a score of 51.8%, followed by Qwen3.5 397B (47.0%) and Gemini 3 Pro (46.3%). The scores show moderate spread, with meaningful differences between the top tier and mid-tier models.

3 models have been evaluated on ODINW13. The benchmark falls in the Multimodal & Grounded category. This category carries a 12% weight in BenchLM.ai's overall scoring system. ODINW13 is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About ODINW13

Year

2026

Tasks

Out-of-distribution object understanding

Format

Detection and grounding

Difficulty

Robust visual grounding

ODINW-style scores matter because real deployment images often differ sharply from canonical internet photos. This benchmark checks whether object understanding transfers out of distribution.

Qwen3.6 launch benchmarks

BenchLM freshness & provenance

Version

ODINW13 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Leaderboard (3 models)

#1Qwen3.6 Plus
51.8%
#2Qwen3.5 397B
47.0%
#3Gemini 3 Pro
46.3%

FAQ

What does ODINW13 measure?

A visual detection and grounding benchmark slice used to compare zero-shot object understanding across diverse domains.

Which model scores highest on ODINW13?

Qwen3.6 Plus by Alibaba currently leads with a score of 51.8% on ODINW13.

How many models are evaluated on ODINW13?

3 AI models have been evaluated on ODINW13 on BenchLM.

Last updated: April 2, 2026 · BenchLM version ODINW13 2026

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.