Pokémon SVG Bench
Pokémon SVG Bench evaluates LLM's knowledge of Pokémon and its ability to generate SVGs.
Learn moreTest cases
15
Models tested
50
X: SVG anchors Y: Visual Score
|V1.1 |
| Rank | Model | ||||
|---|---|---|---|---|---|
 | Gemini 3.7 Flash Official API. thinking_level: high | 53.08 | 65.20 | 47.20 | 52.60 |
 | Gemini 3.6 Flash Official API. thinking_level: high | 50.49 | 61.00 | 48.00 | 48.60 |
 | Gemini 3.8 Flash Official API. thinking_level: high | 46.49 | 68.80 | 46.00 | 39.80 |
| 4 | Gemini 3.1 Pro Official API. reasoning_effort: medium | 40.58 | 58.40 | 47.00 | 31.40 |
| 5 | Gemini 3.5 Flash Official API. reasoning_effort: medium | 40.53 | 57.20 | 40.40 | 35.40 |
| 6 | Arrow 1.1 Official API | 40.45 | 37.00 | 55.60 | 33.00 |
| 7 | GPT-5.6 Sol Cloudflare Proxy API. Reasoning_effortt: medium | 39.66 | 63.20 | 43.40 | 30.20 |
| 8 | Claude Fable 5.1 Cloudflare Proxy API. Thinking: adaptive. Effort: high | 38.87 | 58.00 | 44.00 | 30.00 |
| 9 | Claude Fable 5 Cloudflare Proxy API. Thinking: adaptive. Effort: high | 36.59 | 52.40 | 47.00 | 25.80 |
| 10 | Qwen3.8-Max Official API. Thinking mode enabled. | 33.58 | 48.00 | 39.40 | 25.80 |
| 11 | GPT-5.5 Cloudflare Proxy API. Reasoning_effortt: medium | 33.56 | 53.60 | 38.00 | 24.80 |
| 12 | Kimi K3 Official API. Reasoning_effortt: max | 32.73 | 52.80 | 37.80 | 23.60 |
| 13 | Claude Opus 5 Cloudflare Proxy API. Thinking: adaptive. Effort: high | 32.32 | 53.20 | 38.00 | 22.60 |
| 14 | Gemini 3.5 Flash-Lite Official API. thinking_level: high | 32.03 | 43.60 | 32.40 | 28.20 |
| 15 | Muse Spark 1.2 OpenRouter API | 27.62 | 51.80 | 25.60 | 21.20 |
| 16 | Gemini 3 Flash Official API. reasoning_effort: minimal | 27.30 | 46.60 | 35.60 | 16.60 |
| 17 | Qwen3.7-Max Official API. Thinking mode enabled. | 26.99 | 34.60 | 30.20 | 22.80 |
| 18 | Claude Opus 4.8 Cloudflare Proxy API. Thinking: adaptive. Effort: high | 26.44 | 41.00 | 29.80 | 20.00 |
| 19 | Muse Spark 1.3 OpenRouter API | 26.33 | 38.20 | 26.00 | 22.80 |
| 20 | GLM-5.3 Official API | 25.76 | 48.00 | 33.60 | 14.40 |
| 21 | GPT-5.6 Terra Cloudflare Proxy API. Reasoning_effortt: medium | 25.43 | 35.60 | 29.80 | 19.80 |
| 22 | Doubao-Seed-2.1-pro Official API | 23.65 | 32.80 | 25.40 | 19.80 |
| 23 | GLM-5.3-Flash Official API | 23.18 | 35.60 | 29.40 | 15.80 |
| 24 | Grok 4.5 Official API | 22.64 | 32.60 | 25.00 | 18.20 |
| 25 | GLM-5.2 Official API | 22.55 | 37.80 | 23.60 | 17.20 |
| 26 | Qwen3.6-Max-Preview Official API. Thinking mode enabled. | 22.05 | 24.40 | 25.80 | 19.20 |
| 27 | DeepSeek-V4-Pro-0813 Official API. Default reasoning_effort (high). | 21.95 | 32.20 | 24.00 | 17.60 |
| 28 | Claude Opus 4.7 Cloudflare Proxy API. Thinking: adaptive. Effort: medium | 21.67 | 31.20 | 25.40 | 16.60 |
| 29 | Claude Sonnet 4.6 Cloudflare Proxy API. Effort: medium | 21.23 | 30.20 | 22.00 | 18.00 |
| 30 | GLM-5.1 Official API | 20.79 | 33.00 | 23.60 | 15.40 |
| 31 | DeepSeek v4 Flash 0731 Official API. Default reasoning_effort (high). | 20.53 | 29.20 | 22.00 | 17.00 |
| 32 | Grok 4.6 Official API | 20.20 | 28.00 | 27.60 | 13.60 |
| 33 | Qwen3.7-Plus Official API. Thinking mode enabled. | 19.32 | 22.40 | 22.80 | 16.40 |
| 34 | MiMo-V2.5-Pro Official API | 18.66 | 27.60 | 23.40 | 13.20 |
| 35 | Hy3 OpenRouter API | 18.65 | 26.40 | 22.60 | 14.00 |
| 36 | MiMo-V2.5 Official API | 17.78 | 22.80 | 21.00 | 14.40 |
| 37 | DeepSeek v4 Pro Preview Official API. Thinking mode enabled. reasoning_effort: high | 17.76 | 29.20 | 18.80 | 13.60 |
| 38 | Qwen3.6-Plus Official API. Thinking mode enabled. | 17.54 | 15.40 | 23.60 | 14.80 |
| 39 | Doubao-Seed-2.0-pro Official API | 17.39 | 27.40 | 24.60 | 10.20 |
| 40 | Inkling OpenRouter API | 15.63 | 20.60 | 18.60 | 12.40 |
| 41 | Composer 2.5 Generated by Cursor Subagents | 15.61 | 26.00 | 23.00 | 8.20 |
| 42 | Composer 2 Generated by Cursor Subagents | 14.13 | 21.00 | 21.20 | 8.00 |
| 43 | Grok 4.3 Official API | 13.82 | 20.00 | 15.40 | 11.00 |
| 44 | DeepSeek v4 Flash Preview Official API. Thinking mode disabled. | 13.25 | 19.80 | 16.80 | 9.20 |
| 45 | Hy3 preview OpenRouter API | 9.89 | 19.20 | 15.20 | 4.00 |
| 46 | Step 3.7 Flash OpenRouter API | 9.77 | 17.80 | 12.00 | 6.00 |
| 47 | Gemini 3.1 Flash-Lite Official API. reasoning_effort: minimal | 9.05 | 28.00 | 11.40 | 1.80 |
| 48 | Kimi K2.6 Official API. Thinking mode enabled. | 7.55 | 21.00 | 6.40 | 4.00 |
| 49 | Step 3.5 Flash OpenRouter API | 3.93 | 10.20 | 4.60 | 1.60 |
| 50 | Laguna S 2.1 OpenRouter API | 0.47 | 2.80 | 0.00 | 0.00 |