A task with its own rules.
A multimodal benchmark for fine-grained visual perception and grounded reasoning tasks.
- Organisation
- Meta AI
- Version
- 2026
Loading benchmark header
Loading benchmark registry
Multimodal / Benchmark profile
A multimodal benchmark for fine-grained visual perception and grounded reasoning tasks.
Observed results
2 ranked models · higher is better · labels show rank and score
| Model | Rank | Model ID | Provider | Score | Unit |
|---|---|---|---|---|---|
| Qwen3.8-27B | #1 | qwen-3-8-27b | Alibaba Cloud | 85.6 | percent |
| Muse Spark 1.1 | #2 | muse-spark-1-1 | Meta | 76.3 | percent |
One best compatible score per canonical product · higher is better
| Rank | Model | Weights | Evidence | Score |
|---|---|---|---|---|
| 01 | Qwen3.8-27BAlibaba Cloud | Open weights | Public reference | 85.6% |
| 02 | Muse Spark 1.1Meta | Closed weights | Source carrier | 76.3% |
Each distinct published measurement is retained. Same-snapshot canonical and configuration projections appear once.
| Published model / configuration | Score | Evidence & protocol | Source & dates |
|---|---|---|---|
Qwen3.8-27B (xhigh)Qwen3.8-27BExact identityqwen-3-8-27b-xhigh Canonical product: qwen-3-8-27b | 85.6% | Public referenceprovider-reportedVersion & systemWith CI Qwen3.8-27B official VL table | Qwen3.8-27B official model cardObserved Checked |
Qwen3.7-Plus as published by QwenQwen3.7-PlusExact identityqwen-3-7-plus-unspecified Canonical product: qwen-3-7-plus | 70.4% | Relative comparisonprovider-reportedVersion & systemWith CI Qwen3.8-27B official VL table | Qwen3.8-27B official model cardObserved Checked |
Qwen3.8-27B (xhigh)Qwen3.8-27BExact identityqwen-3-8-27b-xhigh Canonical product: qwen-3-8-27b | 65.7% | Public referenceprovider-reportedVersion & systemWithout CI Qwen3.8-27B official VL table | Qwen3.8-27B official model cardObserved Checked |
Qwen3.7-Plus as published by QwenQwen3.7-PlusExact identityqwen-3-7-plus-unspecified Canonical product: qwen-3-7-plus | 64.7% | Relative comparisonprovider-reportedVersion & systemWithout CI Qwen3.8-27B official VL table | Qwen3.8-27B official model cardObserved Checked |
Qwen3.6-27B as published by QwenQwen3.6 27BExact identityqwen3-6-27b-default Canonical product: qwen3-6-27b | 28.9% | Relative comparisonprovider-reportedVersion & systemWithout CI Qwen3.8-27B official VL table | Qwen3.8-27B official model cardObserved Checked |
Claude Opus 4.6 Max as published by QwenClaude Opus 4.6Exact identityclaude-opus-4-6-max Canonical product: claude-opus-4-6 | 12.6% | Relative comparisonprovider-reportedVersion & systemWithout CI Qwen3.8-27B official VL table | Qwen3.8-27B official model cardObserved Checked |
Exact BenchLM registry variant Muse Spark 1.1; bulk export does not retain a complete upstream harness configuration.Muse Spark 1.1Exact identitySource label without a registered configuration ID Canonical product: muse-spark-1-1 | 76.3% | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Muse Spark 1.1; bulk export does not retain a complete upstream harness configuration.Muse Spark 1.1Exact identitySource label without a registered configuration ID Canonical product: muse-spark-1-1 | 76.3% | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-07-27Observed Checked |
Exact BenchLM registry variant Muse Spark 1.1; bulk export does not retain a complete upstream harness configuration.Muse Spark 1.1Exact identitySource label without a registered configuration ID Canonical product: muse-spark-1-1 | 76.3% | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 21 July 2026Observed Checked |
From result to context
A multimodal benchmark for fine-grained visual perception and grounded reasoning tasks.
The summary shows one best compatible source result per canonical product. Versions, effort settings and execution systems remain attached to the underlying records.
Scores from different versions or harnesses may not be interchangeable. The published source rows preserve those distinctions and their original units. A source result is not automatically an input to a current index.
This catalogue entry preserves available source evidence. Current indices admit only their specifically reviewed tracks and configurations.
Contamination risk: Unknown. Lifecycle: Active.