ERQA
ERQA - embodied/spatial reasoning question answering benchmark.
Category
Spatial Intelligence
Max Score
100.0
Score Type
percent
Active
Yes
Model Scores
Scores for ERQA
| Model | Score | Date | Verified |
|---|---|---|---|
| Qwen3.6-27B |
68.89%
|
22.04.2026 | Verified |
| Qwen3.5-397B-A17B |
84.76%
|
22.04.2026 | Unverified |
| Gemma4-31B-it |
53.02%
|
22.04.2026 | Unverified |
| Claude 4.5 Opus |
19.05%
|
22.04.2026 | Unverified |
| Qwen3.6-35B-A3B |
66.67%
|
22.04.2026 | Unverified |
| Qwen3.5-27B |
62.54%
|
22.04.2026 | Unverified |
| Qwen3.8-27B |
78.41%
|
18.08.2026 | Verified |
| Qwen3.7-Plus |
92.06%
|
18.08.2026 | Unverified |
| Qwen3.5-4B |
41.90%
|
01.02.2026 | Verified |
| Qwen3.5-122B-A10B |
67.30%
|
01.02.2026 | Verified |
| Claude-Sonnet-4.5 |
13.33%
|
01.02.2026 | Unverified |
| Qwen3.5-35B-A3B |
76.19%
|
01.02.2026 | Unverified |
| GPT-5-mini 2025-08-07 |
41.90%
|
01.02.2026 | Unverified |
| Qwen3-235B-A22B |
37.14%
|
01.02.2026 | Unverified |
| Qwen3-VL-235B-A22B |
37.14%
|
01.02.2026 | Verified |
| Qwen3.8-Flash-Next |
100.00%
|
26.08.2026 | Verified |
| Claude-Opus-4.6 (Max) |
40.80
|
26.08.2026 | Unverified |
| Opus4.6 Max |
40.80
|
18.08.2026 | Unverified |