Individual benchmark scores plotted by date.
| Organisation | Model | Reported | Top Score | Info | Self Reported | Source |
|---|---|---|---|---|---|---|
| Qwen 3 VL 235B A22B Instruct | - | 920.00 | LLM Stats (ZeroEval) | Yes | Source | |
| Qwen 3 VL 30B A3B Instruct | - | 903.00 | LLM Stats (ZeroEval) | Yes | Source | |
| Qwen 3 VL 8B Instruct | - | 896.00 | LLM Stats (ZeroEval) | Yes | Source | |
| Qwen 3 VL 32B Instruct | - | 895.00 | LLM Stats (ZeroEval) | Yes | Source | |
| Qwen 3 VL 4B Instruct | - | 881.00 | LLM Stats (ZeroEval) | Yes | Source | |
| Qwen 3 VL 235B A22B Thinking | - | 875.00 | LLM Stats (ZeroEval) | Yes | Source | |
| Qwen 3 VL 32B Thinking | - | 855.00 | LLM Stats (ZeroEval) | Yes | Source | |
| Qwen 3 VL 30B A3B Thinking | - | 839.00 | LLM Stats (ZeroEval) | Yes | Source | |
| Qwen 3 8B | - | 819.00 | LLM Stats (ZeroEval) | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.4600; benches=50) | Yes | Source | |
| Qwen 3 Embedding 8B | - | 819.00 | LLM Stats (ZeroEval) | inferred family alias from qwen3-vl-8b-thinking (score=0.3850; benches=50) | Yes | Source | |
| Qwen 3 Guard Gen 8B | - | 819.00 | LLM Stats (ZeroEval) | inferred family alias from qwen3-vl-8b-thinking (score=0.3400; benches=50) | Yes | Source | |
| Qwen 3 Guard Stream 8B | - | 819.00 | LLM Stats (ZeroEval) | inferred family alias from qwen3-vl-8b-thinking (score=0.3371; benches=50) | Yes | Source | |
| Qwen 3 Reranker 8B | - | 819.00 | LLM Stats (ZeroEval) | inferred family alias from qwen3-vl-8b-thinking (score=0.3850; benches=50) | Yes | Source | |
| Qwen 3 VL 8B Thinking | - | 819.00 | LLM Stats (ZeroEval) | Yes | Source | |
| Qwen 3 VL Embedding 8B | - | 819.00 | LLM Stats (ZeroEval) | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5232; benches=50) | Yes | Source | |
| Qwen 3 VL Reranker 8B | - | 819.00 | LLM Stats (ZeroEval) | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5275; benches=50) | Yes | Source | |
| Qwen 3 4B Instruct 2507 | - | 808.00 | LLM Stats (ZeroEval) | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | Yes | Source | |
| Qwen 3 4B SafeRL | - | 808.00 | LLM Stats (ZeroEval) | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Yes | Source | |
| Qwen 3 4B Thinking 2507 | - | 808.00 | LLM Stats (ZeroEval) | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | Yes | Source | |
| Qwen 3 Embedding 4B | - | 808.00 | LLM Stats (ZeroEval) | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Yes | Source | |
| Qwen 3 Guard Gen 4B | - | 808.00 | LLM Stats (ZeroEval) | inferred family alias from qwen3-vl-4b-thinking (score=0.3400; benches=48) | Yes | Source | |
| Qwen 3 Guard Stream 4B | - | 808.00 | LLM Stats (ZeroEval) | inferred family alias from qwen3-vl-4b-thinking (score=0.3371; benches=48) | Yes | Source | |
| Qwen 3 Reranker 4B | - | 808.00 | LLM Stats (ZeroEval) | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Yes | Source | |
| Qwen 3 VL 4B Thinking | - | 808.00 | LLM Stats (ZeroEval) | Yes | Source | |
| Kimi K2.5 | 27 Jan 2026 | 92.30 | LLM Stats (ZeroEval) | Yes | Source | |
| Qwen 3.5 122B A10B | 24 Feb 2026 | 92.10 | LLM Stats (ZeroEval) | Raw score: 92.1 | Yes | Source | |
| Qwen 3.5 35B A3B | 24 Feb 2026 | 91.00 | LLM Stats (ZeroEval) | Raw score: 91.0 | Yes | Source | |
| Qwen 3.5 27B | 24 Feb 2026 | 89.40 | LLM Stats (ZeroEval) | Raw score: 89.4 | Yes | Source | |
| Qwen 3.5 Flash | 23 Feb 2026 | 89.40 | LLM Stats (ZeroEval) | inferred family alias from qwen3.5-27b (score=0.4147; benches=81) | Yes | Source | |
| Qwen 2.5 Math 72B | - | 88.50 | LLM Stats (ZeroEval) | inferred high-confidence family alias from qwen2.5-vl-72b (score=0.4700; benches=30) | Yes | Source | |
| Qwen 2.5 Math PRM 72B | - | 88.50 | LLM Stats (ZeroEval) | inferred family alias from qwen2.5-vl-72b (score=0.4050; benches=30) | Yes | Source | |
| Qwen 2.5 Math RM 72B | - | 88.50 | LLM Stats (ZeroEval) | inferred family alias from qwen2.5-vl-72b (score=0.4092; benches=30) | Yes | Source | |
| Qwen 2.5 VL 72B Instruct | - | 88.50 | LLM Stats (ZeroEval) | Yes | Source | |
| Qwen 2 VL 2B | - | 87.70 | LLM Stats (ZeroEval) | inferred family alias from qwen2-vl-72b (score=0.4083; benches=15) | Yes | Source | |
| Qwen 2 VL 72B | - | 87.70 | LLM Stats (ZeroEval) | Yes | Source | |
| Qwen 2.5 0.5B | - | 86.40 | LLM Stats (ZeroEval) | inferred family alias from qwen2.5-vl-7b (score=0.3131; benches=32) | Yes | Source | |
| Qwen 2.5 1.5B | - | 86.40 | LLM Stats (ZeroEval) | inferred family alias from qwen2.5-vl-7b (score=0.3131; benches=32) | Yes | Source | |
| Qwen 2.5 3B | - | 86.40 | LLM Stats (ZeroEval) | inferred family alias from qwen2.5-vl-7b (score=0.3531; benches=32) | Yes | Source | |
| Qwen 2.5 VL 7B Instruct | - | 86.40 | LLM Stats (ZeroEval) | Yes | Source | |
| Phi 4 multimodal instruct | 01 Feb 2025 | 84.40 | LLM Stats (ZeroEval) | Yes | Source | |
| DeepSeek VL2 Small | 13 Dec 2024 | 83.40 | LLM Stats (ZeroEval) | Yes | Source | |
| DeepSeek VL2 | 13 Dec 2024 | 81.10 | LLM Stats (ZeroEval) | Yes | Source | |
| DeepSeek VL2 Tiny | 13 Dec 2024 | 80.90 | LLM Stats (ZeroEval) | Yes | Source |
