InfoVQAtest
AIベンチマーク結果とモデルの性能
種類: percentageMultimodal
記録された結果
24
平均スコア
85.08%
スコアの範囲
80.30% - 92.60%
最上位モデル
92.60% - Kimi K2.5
スコアの推移
日付ごとの個別ベンチマークスコアです。
モデル結果
| 組織 | モデル | 報告日 | 最高スコア | 情報 | 自己申告 | 出典 |
|---|---|---|---|---|---|---|
| Kimi K2.5 | 2026年1月27日 | 92.60% | - | はい | 出典 | |
| Qwen 3 VL 235B A22B Thinking | - | 89.50% | - | はい | - | |
| Qwen 3 VL 235B A22B Instruct | - | 89.20% | - | はい | - | |
| Qwen 3 VL 32B Thinking | - | 89.20% | - | はい | - | |
| Qwen 3 VL 32B Instruct | - | 87% | - | はい | - | |
| Qwen 3 8B | - | 86% | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.4600; benches=50) | はい | - | |
| Qwen 3 Guard Stream 8B | - | 86% | inferred family alias from qwen3-vl-8b-thinking (score=0.3371; benches=50) | はい | - | |
| Qwen 3 VL 30B A3B Thinking | - | 86% | - | はい | - | |
| Qwen 3 VL 8B Thinking | - | 86% | - | はい | - | |
| Qwen 3 VL Embedding 8B | - | 86% | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5232; benches=50) | はい | - | |
| Qwen 3 VL Reranker 8B | - | 86% | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5275; benches=50) | はい | - | |
| Qwen 2 VL 2B | - | 84.50% | inferred family alias from qwen2-vl-72b (score=0.4083; benches=15) | はい | 出典 | |
| Qwen 2 VL 72B | - | 84.50% | - | はい | 出典 | |
| Qwen 3 VL 8B Instruct | - | 83.10% | - | はい | - | |
| Qwen 3 4B Instruct 2507 | - | 83% | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | はい | - | |
| Qwen 3 4B SafeRL | - | 83% | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | はい | - | |
| Qwen 3 4B Thinking 2507 | - | 83% | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | はい | - | |
| Qwen 3 Embedding 4B | - | 83% | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | はい | - | |
| Qwen 3 Guard Gen 4B | - | 83% | inferred family alias from qwen3-vl-4b-thinking (score=0.3400; benches=48) | はい | - | |
| Qwen 3 Guard Stream 4B | - | 83% | inferred family alias from qwen3-vl-4b-thinking (score=0.3371; benches=48) | はい | - | |
| Qwen 3 Reranker 4B | - | 83% | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | はい | - | |
| Qwen 3 VL 4B Thinking | - | 83% | - | はい | - | |
| Qwen 3 VL 30B A3B Instruct | - | 82% | - | はい | - | |
| Qwen 3 VL 4B Instruct | - | 80.30% | - | はい | - |