Individual benchmark scores plotted by date.
| Organisation | Model | Reported | Top Score | Info | Self Reported | Source |
|---|---|---|---|---|---|---|
| Gemini 3.1 Pro Preview | 19 Feb 2026 | 99.30% | - | Yes | Source | |
| Gemini 3.1 Pro Preview Customtools | 19 Feb 2026 | 99.30% | inferred alias of gemini-3.1-pro-preview | Yes | Source | |
| Gemini 3 Flash Preview | 17 Dec 2025 | 90.20% | - | Yes | Source | |
| GLM 5 | 11 Feb 2026 | 89.70% | - | Yes | Source | |
| Qwen 3.5 397B A17B | 16 Feb 2026 | 86.70% | - | Yes | Source | |
| Gemini 3 Pro Preview | 18 Nov 2025 | 85.40% | - | Yes | Source | |
| Gemini 3 Pro Image Preview (Nano Banana Pro) | 20 Nov 2025 | 85.40% | inferred modality/version alias from gemini-3-pro-preview | Yes | Source | |
| Qwen 3.5 35B A3B | 24 Feb 2026 | 81.20% | - | Yes | Source | |
| DeepSeek V3.2 Speciale | 01 Dec 2025 | 80.30% | - | Yes | Source | |
| Qwen 3.5 4B | 02 Mar 2026 | 79.90% | - | Yes | Source | |
| Qwen 3.5 122B A10B | 24 Feb 2026 | 79.50% | - | Yes | Source | |
| Qwen 3.5 9B | 02 Mar 2026 | 79.10% | - | Yes | Source | |
| Qwen 3.5 27B | 24 Feb 2026 | 79% | - | Yes | Source | |
| Qwen 3.5 Flash | 23 Feb 2026 | 79% | inferred family alias from qwen3.5-27b (score=0.4147; benches=81) | Yes | Source | |
| Gemma 4 31B | 02 Apr 2026 | 76.90% | Average over 3 | Yes | Source | |
| Qwen 3 TTS (2025-11-27) | - | 74.80% | inferred family alias from qwen3-max (score=0.3833; benches=6) | Yes | Source | |
| Qwen 3 14B | - | 74.80% | inferred family alias from qwen3-max (score=0.3333; benches=6) | Yes | Source | |
| Qwen 3 Max Thinking | 26 Jan 2026 | 74.80% | inferred alias from qwen3-max | Yes | Source | |
| K EXAONE | 31 Dec 2025 | 73.20% | inferred modality/version alias from k-exaone-236b-a23b | Yes | Source | |
| GLM 5.1 | - | 70.60% | τ³-Bench | Yes | Source | |
| Gemma 4 26B A4B | 02 Apr 2026 | 68.20% | Average over 3 | Yes | Source | |
| Qwen 3.5 2B | 02 Mar 2026 | 48.80% | - | Yes | Source | |
| Qwen 3.5 0.8B | 02 Mar 2026 | 11.60% | - | Yes | Source |