# SVGBench Arena

> Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/svgbench%3Aarena. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/svgbench%3Aarena.

Human pairwise preferences over SVG illustrations generated from the same prompts, reported on the publisher’s rating scale.

Canonical URL: https://benchize.com/benchmarks/svgbench%3Aarena
Last updated: Wed, 21 Oct 2026 18:52:20 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

Human pairwise preferences over SVG illustrations generated from the same prompts, reported on the publisher’s rating scale.

Writing & creativity · Models tested: 191 · Score publishers: [svgbench](https://svgbench.ai/api/leaderboard?shape=2)

## Model results

| # | Model | Score |  |
| --- | --- | --- | --- |
| 1 | [GPT-5.4 Pro](https://benchize.com/models/gpt-5-4-pro.md) | 2,058 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 2058 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_gpt54pro ### Reported statistics coverageCount 26 draws 39 judged 1073 losses 417 rank 1 ratingDeviation 28 wins 617 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5.4 Pro Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/0` |  |  |  |
| 2 | [MiMo-V2.5](https://benchize.com/models/mimo-v2-5.md) | 1,865 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1865 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_xiaomi_mimo_v2_5 ### Reported statistics coverageCount 26 draws 29 judged 629 losses 295 rank 3 ratingDeviation 28 wins 305 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label MiMo-V2.5 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/2` |  |  |  |
| 3 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7.md) | 1,802 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1802 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_anthropic_claude_opus_4_7 ### Reported statistics coverageCount 27 draws 39 judged 973 losses 449 rank 4 ratingDeviation 28 wins 485 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Claude Opus 4.7 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/3` |  |  |  |
| 4 | [GPT-5.4](https://benchize.com/models/gpt-5-4.md) | 1,795 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1795 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_gpt54 ### Reported statistics coverageCount 27 draws 7 judged 211 losses 78 rank 5 ratingDeviation 28 wins 126 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5.4 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/4` |  |  |  |
| 5 | [Claude Sonnet 4.6](https://benchize.com/models/claude-sonnet-4-6.md) | 1,771 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1771 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_anthropic_claude_sonnet_4_6 ### Reported statistics coverageCount 27 draws 5 judged 84 losses 32 rank 8 ratingDeviation 28 wins 47 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Claude Sonnet 4.6 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/7` |  |  |  |
| 6 | [Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6.md) | 1,744 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1744 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_claude46opus ### Reported statistics coverageCount 27 draws 30 judged 560 losses 240 rank 10 ratingDeviation 28 wins 290 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Claude Opus 4.6 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/9` |  |  |  |
| 7 | [MiMo-V2.5-Pro](https://benchize.com/models/mimo-v2-5-pro.md) | 1,723 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1723 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_xiaomi_mimo_v2_5_pro ### Reported statistics coverageCount 24 draws 29 judged 268 losses 106 rank 12 ratingDeviation 28 wins 133 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label MiMo-V2.5-Pro Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/11` |  |  |  |
| 8 | [GPT-5.2](https://benchize.com/models/gpt-5-2.md) | 1,698 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1698 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_5_2 ### Reported statistics coverageCount 27 draws 4 judged 105 losses 45 rank 13 ratingDeviation 28 wins 56 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5.2 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/12` |  |  |  |
| 9 | [GPT-5.2 Pro](https://benchize.com/models/gpt-5-2-pro.md) | 1,674 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1674 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_5_2_pro ### Reported statistics coverageCount 27 draws 3 judged 77 losses 36 rank 14 ratingDeviation 28 wins 38 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5.2 Pro Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/13` |  |  |  |
| 10 | [GPT-5](https://benchize.com/models/gpt-5.md) | 1,672 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1672 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_5 ### Reported statistics coverageCount 16 draws 2 judged 71 losses 31 rank 15 ratingDeviation 28 wins 38 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/14` |  |  |  |
| 11 | [Nano Banana Pro (Gemini 3 Pro Image Preview)](https://benchize.com/models/gemini-3-pro-image-preview.md) | 1,671 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1671 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_google_gemini_3_pro_image_preview ### Reported statistics coverageCount 27 draws 4 judged 86 losses 35 rank 16 ratingDeviation 28 wins 47 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Nano Banana Pro (Gemini 3 Pro Image Preview) Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/15` |  |  |  |
| 12 | [GPT-5.3 Codex](https://benchize.com/models/gpt-5-3-codex.md) | 1,668 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1668 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_5_3_codex ### Reported statistics coverageCount 27 draws 24 judged 611 losses 293 rank 17 ratingDeviation 28 wins 294 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5.3-Codex Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/16` |  |  |  |
| 13 | [MiniMax M2](https://benchize.com/models/minimax-m2.md) | 1,665 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1665 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_minimax_minimax_m2 ### Reported statistics coverageCount 27 draws 2 judged 113 losses 53 rank 18 ratingDeviation 28 wins 58 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label MiniMax M2 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/17` |  |  |  |
| 14 | [Claude Opus 4.5](https://benchize.com/models/claude-opus-4-5.md) | 1,656 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1656 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_anthropic_claude_opus_4_5 ### Reported statistics coverageCount 27 draws 15 judged 296 losses 140 rank 19 ratingDeviation 28 wins 141 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Claude Opus 4.5 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/18` |  |  |  |
| 15 | [Gemini 3 Flash Preview](https://benchize.com/models/gemini-3-flash-preview.md) | 1,655 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1655 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_google_gemini_3_flash_preview ### Reported statistics coverageCount 27 draws 9 judged 209 losses 60 rank 20 ratingDeviation 28 wins 140 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Gemini 3 Flash Preview Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/19` |  |  |  |
| 16 | [MiniMax M2.7](https://benchize.com/models/minimax-m2-7.md) | 1,650 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1650 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_minimax_minimax_m2_7 ### Reported statistics coverageCount 27 draws 5 judged 99 losses 43 rank 21 ratingDeviation 28 wins 51 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label MiniMax M2.7 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/20` |  |  |  |
| 17 | [GPT-5.4 Image 2](https://benchize.com/models/gpt-5-4-image-2.md) | 1,647 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1647 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_5_4_image_2 ### Reported statistics coverageCount 27 draws 1 judged 37 losses 13 rank 23 ratingDeviation 28 wins 23 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5.4 Image 2 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/22` |  |  |  |
| 18 | [Kimi K2.5](https://benchize.com/models/kimi-k2-5.md) | 1,642 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1642 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_kimik25 ### Reported statistics coverageCount 27 draws 0 judged 76 losses 31 rank 25 ratingDeviation 28 wins 45 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Kimi K2.5 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/23` |  |  |  |
| 19 | [GPT-5.1 Codex Max](https://benchize.com/models/gpt-5-1-codex-max.md) | 1,633 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1633 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_5_1_codex_max ### Reported statistics coverageCount 27 draws 3 judged 69 losses 25 rank 27 ratingDeviation 28 wins 41 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5.1-Codex-Max Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/25` |  |  |  |
| 20 | [GPT-5.2 Codex](https://benchize.com/models/gpt-5-2-codex.md) | 1,628 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1628 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_5_2_codex ### Reported statistics coverageCount 27 draws 1 judged 87 losses 35 rank 28 ratingDeviation 28 wins 51 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5.2-Codex Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/26` |  |  |  |
| 20 | [GPT-5 Image](https://benchize.com/models/gpt-5-image.md) | 1,628 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1628 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_5_image ### Reported statistics coverageCount 23 draws 6 judged 76 losses 29 rank 29 ratingDeviation 28 wins 41 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5 Image Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/27` |  |  |  |
| 22 | [MiniMax M1](https://benchize.com/models/minimax-m1.md) | 1,619 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1619 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_minimax_minimax_m1 ### Reported statistics coverageCount 27 draws 4 judged 76 losses 30 rank 30 ratingDeviation 28 wins 42 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label MiniMax M1 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/28` |  |  |  |
| 23 | [GPT-5.2 Chat](https://benchize.com/models/gpt-5-2-chat.md) | 1,615 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1615 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_5_2_chat ### Reported statistics coverageCount 27 draws 2 judged 70 losses 27 rank 31 ratingDeviation 28 wins 41 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5.2 Chat Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/29` |  |  |  |
| 24 | [GPT-5.1](https://benchize.com/models/gpt-5-1.md) | 1,612 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1612 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_5_1 ### Reported statistics coverageCount 27 draws 2 judged 72 losses 28 rank 32 ratingDeviation 28 wins 42 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5.1 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/30` |  |  |  |
| 24 | [GPT-5.3 Chat](https://benchize.com/models/gpt-5-3-chat.md) | 1,612 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1612 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_5_3_chat ### Reported statistics coverageCount 27 draws 3 judged 90 losses 37 rank 33 ratingDeviation 28 wins 50 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5.3 Chat Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/31` |  |  |  |
| 26 | [Gemma 4 26B A4B](https://benchize.com/models/gemma-4-26b-a4b-it.md) | 1,609 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1609 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_google_gemma_4_26b_a4b_it ### Reported statistics coverageCount 26 draws 6 judged 77 losses 26 rank 34 ratingDeviation 28 wins 45 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Gemma 4 26B A4B Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/32` |  |  |  |
| 27 | [Gemma 4 31B](https://benchize.com/models/gemma-4-31b-it.md) | 1,602 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1602 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_google_gemma_4_31b_it ### Reported statistics coverageCount 27 draws 4 judged 72 losses 28 rank 35 ratingDeviation 28 wins 40 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Gemma 4 31B Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/33` |  |  |  |
| 28 | [Qwen3.5-35B-A3B](https://benchize.com/models/qwen3-5-35b-a3b.md) | 1,601 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1601 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_qwen_qwen3_5_35b_a3b ### Reported statistics coverageCount 27 draws 3 judged 79 losses 31 rank 36 ratingDeviation 28 wins 45 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Qwen3.5-35B-A3B Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/34` |  |  |  |
| 28 | [MiniMax M2.5](https://benchize.com/models/minimax-m2-5.md) | 1,601 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1601 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_minimax_minimax_m2_5 ### Reported statistics coverageCount 27 draws 2 judged 110 losses 47 rank 37 ratingDeviation 28 wins 61 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label MiniMax M2.5 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/35` |  |  |  |
| 30 | [Claude Opus 4.1](https://benchize.com/models/claude-opus-4-1.md) | 1,597 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1597 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_anthropic_claude_opus_4_1 ### Reported statistics coverageCount 27 draws 5 judged 68 losses 27 rank 38 ratingDeviation 28 wins 36 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Claude Opus 4.1 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/36` |  |  |  |
| 31 | [GPT-5.4 Nano](https://benchize.com/models/gpt-5-4-nano.md) | 1,596 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1596 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_5_4_nano ### Reported statistics coverageCount 27 draws 4 judged 81 losses 33 rank 39 ratingDeviation 28 wins 44 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5.4 Nano Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/37` |  |  |  |
| 32 | [Qwen3.5-122B-A10B](https://benchize.com/models/qwen3-5-122b-a10b.md) | 1,595 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1595 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_qwen_qwen3_5_122b_a10b ### Reported statistics coverageCount 27 draws 2 judged 62 losses 25 rank 40 ratingDeviation 28 wins 35 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Qwen3.5-122B-A10B Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/38` |  |  |  |
| 33 | [Qwen3.5-27B](https://benchize.com/models/qwen3-5-27b.md) | 1,590 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1590 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_qwen_qwen3_5_27b ### Reported statistics coverageCount 27 draws 3 judged 74 losses 30 rank 41 ratingDeviation 28 wins 41 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Qwen3.5-27B Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/39` |  |  |  |
| 34 | [Kat Coder Pro V2](https://benchize.com/models/kat-coder-pro-v2.md) | 1,588 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1588 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_kwaipilot_kat_coder_pro_v2 ### Reported statistics coverageCount 27 draws 4 judged 88 losses 35 rank 42 ratingDeviation 28 wins 49 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label KAT-Coder-Pro V2 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/40` |  |  |  |
| 35 | [O3 Pro](https://benchize.com/models/o3-pro.md) | 1,587 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1587 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_o3_pro ### Reported statistics coverageCount 27 draws 4 judged 57 losses 22 rank 43 ratingDeviation 28 wins 31 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label o3 Pro Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/41` |  |  |  |
| 36 | [Qwen3.5 397B A17B](https://benchize.com/models/qwen3-5-397b-a17b.md) | 1,586 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1586 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_qwen_qwen3_5_397b_a17b ### Reported statistics coverageCount 27 draws 7 judged 73 losses 28 rank 44 ratingDeviation 28 wins 38 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Qwen3.5 397B A17B Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/42` |  |  |  |
| 37 | [Gemini 2.5 Pro](https://benchize.com/models/gemini-2-5-pro.md) | 1,585 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1585 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_google_gemini_2_5_pro ### Reported statistics coverageCount 22 draws 6 judged 74 losses 29 rank 45 ratingDeviation 28 wins 39 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Gemini 2.5 Pro Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/43` |  |  |  |
| 38 | [Claude Opus 4](https://benchize.com/models/claude-opus-4.md) | 1,582 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1582 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_anthropic_claude_opus_4 ### Reported statistics coverageCount 27 draws 4 judged 67 losses 28 rank 46 ratingDeviation 28 wins 35 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Claude Opus 4 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/44` |  |  |  |
| 39 | [MiniMax M2.1](https://benchize.com/models/minimax-m2-1.md) | 1,581 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1581 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_minimax_minimax_m2_1 ### Reported statistics coverageCount 27 draws 1 judged 68 losses 29 rank 47 ratingDeviation 28 wins 38 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label MiniMax M2.1 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/45` |  |  |  |
| 40 | [Claude 3.7 Sonnet](https://benchize.com/models/claude-3-7-sonnet.md) | 1,580 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1580 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_anthropic_claude_3_7_sonnet ### Reported statistics coverageCount 27 draws 4 judged 96 losses 39 rank 48 ratingDeviation 28 wins 53 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Claude 3.7 Sonnet Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/46` |  |  |  |
| 41 | [Claude Sonnet 4](https://benchize.com/models/claude-sonnet-4.md) | 1,579 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1579 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_anthropic_claude_sonnet_4 ### Reported statistics coverageCount 27 draws 1 judged 68 losses 28 rank 49 ratingDeviation 28 wins 39 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Claude Sonnet 4 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/47` |  |  |  |
| 42 | [Qwen3.5 Plus 2026-02-15](https://benchize.com/models/qwen3-5-plus-02-15.md) | 1,575 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1575 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_qwen_qwen3_5_plus_02_15 ### Reported statistics coverageCount 27 draws 5 judged 79 losses 32 rank 52 ratingDeviation 28 wins 42 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Qwen3.5 Plus 2026-02-15 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/50` |  |  |  |
| 43 | [Kimi K2.6](https://benchize.com/models/kimi-k2-6.md) | 1,570 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1570 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_moonshotai_kimi_k2_6 ### Reported statistics coverageCount 27 draws 3 judged 106 losses 47 rank 53 ratingDeviation 28 wins 56 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Kimi K2.6 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/51` |  |  |  |
| 44 | [Claude Sonnet 4.5](https://benchize.com/models/claude-sonnet-4-5.md) | 1,569 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1569 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_anthropic_claude_sonnet_4_5 ### Reported statistics coverageCount 27 draws 5 judged 90 losses 37 rank 54 ratingDeviation 28 wins 48 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Claude Sonnet 4.5 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/52` |  |  |  |
| 45 | [MiMo-V2-Flash](https://benchize.com/models/mimo-v2-flash.md) | 1,566 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1566 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_xiaomi_mimo_v2_flash ### Reported statistics coverageCount 27 draws 6 judged 74 losses 29 rank 55 ratingDeviation 28 wins 39 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label MiMo-V2-Flash Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/53` |  |  |  |
| 46 | [MiMo-V2-Pro](https://benchize.com/models/mimo-v2-pro.md) | 1,564 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1564 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_xiaomi_mimo_v2_pro ### Reported statistics coverageCount 27 draws 5 judged 82 losses 34 rank 56 ratingDeviation 28 wins 43 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label MiMo-V2-Pro Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/54` |  |  |  |
| 47 | [GPT-5.1 Codex](https://benchize.com/models/gpt-5-1-codex.md) | 1,560 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1560 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_5_1_codex ### Reported statistics coverageCount 27 draws 1 judged 88 losses 39 rank 57 ratingDeviation 28 wins 48 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5.1-Codex Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/55` |  |  |  |
| 48 | [GPT-5.4 Mini](https://benchize.com/models/gpt-5-4-mini.md) | 1,554 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1554 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_5_4_mini ### Reported statistics coverageCount 27 draws 6 judged 102 losses 42 rank 59 ratingDeviation 28 wins 54 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5.4 Mini Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/57` |  |  |  |
| 49 | [GPT-5 Image Mini](https://benchize.com/models/gpt-5-image-mini.md) | 1,546 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1546 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_5_image_mini ### Reported statistics coverageCount 27 draws 2 judged 47 losses 19 rank 62 ratingDeviation 28 wins 26 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5 Image Mini Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/60` |  |  |  |
| 49 | [GPT-4.1](https://benchize.com/models/gpt-4-1.md) | 1,546 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1546 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_4_1 ### Reported statistics coverageCount 27 draws 3 judged 75 losses 31 rank 61 ratingDeviation 28 wins 41 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-4.1 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/59` |  |  |  |
| 51 | [GPT-5.1 Chat](https://benchize.com/models/gpt-5-1-chat.md) | 1,545 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1545 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_5_1_chat ### Reported statistics coverageCount 27 draws 5 judged 110 losses 46 rank 65 ratingDeviation 28 wins 59 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5.1 Chat Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/62` |  |  |  |
| 51 | [GPT-5 Chat](https://benchize.com/models/gpt-5-chat.md) | 1,545 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1545 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_5_chat ### Reported statistics coverageCount 27 draws 2 judged 92 losses 38 rank 64 ratingDeviation 28 wins 52 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5 Chat Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/61` |  |  |  |
| 53 | [MiMo-V2-Omni](https://benchize.com/models/mimo-v2-omni.md) | 1,543 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1543 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_xiaomi_mimo_v2_omni ### Reported statistics coverageCount 27 draws 3 judged 84 losses 36 rank 66 ratingDeviation 28 wins 45 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label MiMo-V2-Omni Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/63` |  |  |  |
| 53 | [GPT-5 Mini](https://benchize.com/models/gpt-5-mini.md) | 1,543 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1543 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_gpt5mini ### Reported statistics coverageCount 27 draws 1 judged 87 losses 41 rank 67 ratingDeviation 28 wins 45 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5 Mini Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/64` |  |  |  |
| 55 | [Gemini 3.1 Flash Lite Preview](https://benchize.com/models/gemini-3-1-flash-lite-preview.md) | 1,538 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1538 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_gemini31flashlite ### Reported statistics coverageCount 27 draws 0 judged 100 losses 47 rank 69 ratingDeviation 28 wins 53 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Gemini 3.1 Flash Lite Preview Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/66` |  |  |  |
| 56 | [O1](https://benchize.com/models/o1.md) | 1,537 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1537 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_o1 ### Reported statistics coverageCount 27 draws 1 judged 74 losses 33 rank 70 ratingDeviation 28 wins 40 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label o1 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/67` |  |  |  |
| 57 | [O3](https://benchize.com/models/o3.md) | 1,534 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1534 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_o3 ### Reported statistics coverageCount 27 draws 8 judged 93 losses 40 rank 71 ratingDeviation 28 wins 45 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label o3 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/68` |  |  |  |
| 58 | [Claude Haiku 4.5](https://benchize.com/models/claude-haiku-4-5.md) | 1,532 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1532 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_claudehaiku45 ### Reported statistics coverageCount 27 draws 7 judged 226 losses 62 rank 72 ratingDeviation 28 wins 157 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Claude Haiku 4.5 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/69` |  |  |  |
| 59 | [Claude 3.7 Sonnet](https://benchize.com/models/claude-3-7-sonnet-thinking.md)Thinking | 1,531 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1531 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_anthropic_claude_3_7_sonnet_thinking thinkingEnabled true ### Reported statistics coverageCount 27 draws 4 judged 77 losses 31 rank 73 ratingDeviation 28 wins 42 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Claude 3.7 Sonnet (thinking) Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/70` |  |  |  |
| 60 | [Gemini 2.5 Flash](https://benchize.com/models/gemini-2-5-flash.md) | 1,525 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1525 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_google_gemini_2_5_flash ### Reported statistics coverageCount 27 draws 5 judged 122 losses 54 rank 77 ratingDeviation 28 wins 63 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Gemini 2.5 Flash Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/74` |  |  |  |
| 60 | [Sonar Reasoning Pro](https://benchize.com/models/sonar-reasoning-pro.md) | 1,525 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1525 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_perplexity_sonar_reasoning_pro ### Reported statistics coverageCount 27 draws 5 judged 71 losses 28 rank 76 ratingDeviation 28 wins 38 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Sonar Reasoning Pro Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/73` |  |  |  |
| 62 | [Kimi K2 Thinking](https://benchize.com/models/kimi-k2-thinking.md) | 1,517 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1517 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_moonshotai_kimi_k2_thinking ### Reported statistics coverageCount 27 draws 3 judged 63 losses 26 rank 78 ratingDeviation 28 wins 34 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Kimi K2 Thinking Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/75` |  |  |  |
| 63 | [Qwen3 235B A22B Instruct 2507](https://benchize.com/models/qwen3-235b-a22b-2507.md) | 1,511 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1511 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_qwen_qwen3_235b_a22b_2507 ### Reported statistics coverageCount 27 draws 2 judged 98 losses 42 rank 79 ratingDeviation 28 wins 54 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Qwen3 235B A22B Instruct 2507 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/76` |  |  |  |
| 64 | [DeepSeek V3.2](https://benchize.com/models/deepseek-v3-2.md) | 1,510 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1510 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_deepseekv32 ### Reported statistics coverageCount 27 draws 6 judged 173 losses 80 rank 80 ratingDeviation 28 wins 87 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label DeepSeek V3.2 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/77` |  |  |  |
| 65 | [GPT-3.5 Turbo (older v0613)](https://benchize.com/models/gpt-3-5-turbo-0613.md) | 1,509 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1509 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_3_5_turbo_0613 ### Reported statistics coverageCount 27 draws 2 judged 95 losses 42 rank 81 ratingDeviation 28 wins 51 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-3.5 Turbo (older v0613) Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/78` |  |  |  |
| 66 | [Aion 2.0](https://benchize.com/models/aion-2-0.md) | 1,502 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1502 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_aion_labs_aion_2_0 ### Reported statistics coverageCount 27 draws 2 judged 110 losses 41 rank 85 ratingDeviation 28 wins 67 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Aion-2.0 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/82` |  |  |  |
| 66 | [O4 Mini](https://benchize.com/models/o4-mini.md) | 1,502 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1502 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_o4_mini ### Reported statistics coverageCount 27 draws 1 judged 62 losses 27 rank 87 ratingDeviation 28 wins 34 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label o4 Mini Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/84` |  |  |  |
| 66 | [o4 Mini High](https://benchize.com/models/o4-mini-high.md) | 1,502 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1502 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_o4_mini_high ### Reported statistics coverageCount 26 draws 4 judged 63 losses 27 rank 86 ratingDeviation 28 wins 32 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label o4 Mini High Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/83` |  |  |  |
| 69 | [O3 Mini](https://benchize.com/models/o3-mini.md) | 1,501 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1501 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_o3_mini ### Reported statistics coverageCount 27 draws 0 judged 85 losses 39 rank 88 ratingDeviation 28 wins 46 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label o3 Mini Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/85` |  |  |  |
| 70 | [Nano Banana 2 (Gemini 3.1 Flash Image Preview)](https://benchize.com/models/gemini-3-1-flash-image-preview.md) | 1,495 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1495 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_google_gemini_3_1_flash_image_preview ### Reported statistics coverageCount 27 draws 5 judged 85 losses 37 rank 91 ratingDeviation 28 wins 43 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Nano Banana 2 (Gemini 3.1 Flash Image Preview) Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/88` |  |  |  |
| 71 | [GPT-5 Codex](https://benchize.com/models/gpt-5-codex.md) | 1,491 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1491 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_5_codex ### Reported statistics coverageCount 26 draws 2 judged 91 losses 40 rank 94 ratingDeviation 28 wins 49 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5 Codex Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/90` |  |  |  |
| 72 | [Qwen Plus 0728](https://benchize.com/models/qwen-plus-2025-07-28-thinking.md)Thinking | 1,488 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1488 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_qwen_qwen_plus_2025_07_28_thinking thinkingEnabled true ### Reported statistics coverageCount 27 draws 4 judged 84 losses 37 rank 97 ratingDeviation 28 wins 43 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Qwen Plus 0728 (thinking) Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/93` |  |  |  |
| 73 | [Qwen3 Max Thinking](https://benchize.com/models/qwen3-max-thinking.md) | 1,485 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1485 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_qwen_qwen3_max_thinking ### Reported statistics coverageCount 27 draws 1 judged 89 losses 40 rank 98 ratingDeviation 28 wins 48 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Qwen3 Max Thinking Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/94` |  |  |  |
| 74 | [Sonar Deep Research](https://benchize.com/models/sonar-deep-research.md) | 1,482 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1482 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_perplexity_sonar_deep_research ### Reported statistics coverageCount 27 draws 0 judged 100 losses 48 rank 100 ratingDeviation 28 wins 52 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Sonar Deep Research Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/96` |  |  |  |
| 75 | [Mercury 2](https://benchize.com/models/mercury-2.md) | 1,478 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1478 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_inception_mercury_2 ### Reported statistics coverageCount 27 draws 6 judged 78 losses 34 rank 103 ratingDeviation 28 wins 38 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Mercury 2 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/99` |  |  |  |
| 75 | [Qwen3 Max](https://benchize.com/models/qwen3-max.md) | 1,478 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1478 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_qwen_qwen3_max ### Reported statistics coverageCount 27 draws 4 judged 80 losses 34 rank 102 ratingDeviation 28 wins 42 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Qwen3 Max Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/98` |  |  |  |
| 77 | [Mistral Large 2407](https://benchize.com/models/mistral-large-2407.md) | 1,477 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1477 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_mistralai_mistral_large_2407 ### Reported statistics coverageCount 27 draws 5 judged 88 losses 39 rank 104 ratingDeviation 28 wins 44 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Mistral Large 2407 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/100` |  |  |  |
| 78 | [Qwen3.5-9B](https://benchize.com/models/qwen3-5-9b.md) | 1,473 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1473 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_qwen_qwen3_5_9b ### Reported statistics coverageCount 27 draws 3 judged 84 losses 36 rank 106 ratingDeviation 28 wins 45 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Qwen3.5-9B Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/102` |  |  |  |
| 79 | [Sonar](https://benchize.com/models/sonar.md) | 1,471 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1471 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_perplexity_sonar ### Reported statistics coverageCount 27 draws 2 judged 97 losses 45 rank 107 ratingDeviation 28 wins 50 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Sonar Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/103` |  |  |  |
| 79 | [R1 0528](https://benchize.com/models/deepseek-r1-0528.md) | 1,471 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1471 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_deepseek_deepseek_r1_0528 ### Reported statistics coverageCount 27 draws 0 judged 125 losses 57 rank 108 ratingDeviation 28 wins 68 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label R1 0528 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/104` |  |  |  |
| 81 | [Sonar Pro](https://benchize.com/models/sonar-pro.md) | 1,469 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1469 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_perplexity_sonar_pro ### Reported statistics coverageCount 27 draws 0 judged 115 losses 53 rank 109 ratingDeviation 28 wins 62 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Sonar Pro Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/105` |  |  |  |
| 82 | [WizardLM-2 8x22B](https://benchize.com/models/wizardlm-2-8x22b.md) | 1,468 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1468 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_microsoft_wizardlm_2_8x22b ### Reported statistics coverageCount 26 draws 5 judged 134 losses 58 rank 110 ratingDeviation 28 wins 71 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Wizardlm 2 8x22b Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/106` |  |  |  |
| 83 | [Kimi K2 0905](https://benchize.com/models/kimi-k2-0905.md) | 1,466 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1466 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_moonshotai_kimi_k2_0905 ### Reported statistics coverageCount 27 draws 0 judged 76 losses 34 rank 111 ratingDeviation 28 wins 42 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Kimi K2 0905 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/107` |  |  |  |
| 84 | [GPT-4o Search Preview](https://benchize.com/models/gpt-4o-search-preview.md) | 1,464 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1464 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_4o_search_preview ### Reported statistics coverageCount 27 draws 6 judged 147 losses 62 rank 112 ratingDeviation 28 wins 79 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-4o Search Preview Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/108` |  |  |  |
| 85 | [DeepSeek V3.2 Exp](https://benchize.com/models/deepseek-v3-2-exp.md) | 1,462 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1462 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_deepseek_deepseek_v3_2_exp ### Reported statistics coverageCount 27 draws 4 judged 83 losses 36 rank 114 ratingDeviation 28 wins 43 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label DeepSeek V3.2 Exp Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/110` |  |  |  |
| 86 | [Grok 3](https://benchize.com/models/grok-3.md) | 1,461 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1461 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_x_ai_grok_3 ### Reported statistics coverageCount 27 draws 3 judged 84 losses 40 rank 116 ratingDeviation 28 wins 41 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Grok 3 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/112` |  |  |  |
| 87 | [Gemini 2.5 Flash Lite](https://benchize.com/models/gemini-2-5-flash-lite.md) | 1,453 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1453 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_google_gemini_2_5_flash_lite ### Reported statistics coverageCount 27 draws 4 judged 79 losses 35 rank 118 ratingDeviation 28 wins 40 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Gemini 2.5 Flash Lite Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/114` |  |  |  |
| 88 | [Qwen3 Next 80B A3B Instruct](https://benchize.com/models/qwen3-next-80b-a3b-instruct.md) | 1,452 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1452 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_qwen_qwen3_next_80b_a3b_instruct ### Reported statistics coverageCount 27 draws 1 judged 87 losses 40 rank 119 ratingDeviation 28 wins 46 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Qwen3 Next 80B A3B Instruct Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/115` |  |  |  |
| 89 | [Qwen3 VL 235B A22B Thinking](https://benchize.com/models/qwen3-vl-235b-a22b-thinking.md) | 1,448 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1448 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_qwen_qwen3_vl_235b_a22b_thinking ### Reported statistics coverageCount 27 draws 1 judged 75 losses 35 rank 120 ratingDeviation 28 wins 39 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Qwen3 VL 235B A22B Thinking Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/116` |  |  |  |
| 90 | [Qwen3 Coder Next](https://benchize.com/models/qwen3-coder-next.md) | 1,447 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1447 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_qwen_qwen3_coder_next ### Reported statistics coverageCount 27 draws 4 judged 103 losses 46 rank 121 ratingDeviation 28 wins 53 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Qwen3 Coder Next Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/117` |  |  |  |
| 91 | [Sonar Pro Search](https://benchize.com/models/sonar-pro-search.md) | 1,446 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1446 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_perplexity_sonar_pro_search ### Reported statistics coverageCount 27 draws 6 judged 120 losses 53 rank 122 ratingDeviation 28 wins 61 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Sonar Pro Search Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/118` |  |  |  |
| 92 | [gpt-oss-120b](https://benchize.com/models/gpt-oss-120b.md) | 1,445 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1445 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_oss_120b ### Reported statistics coverageCount 27 draws 2 judged 76 losses 35 rank 123 ratingDeviation 28 wins 39 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label gpt-oss-120b Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/119` |  |  |  |
| 93 | [Mistral Large](https://benchize.com/models/mistral-large.md) | 1,438 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1438 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_mistralai_mistral_large ### Reported statistics coverageCount 27 draws 2 judged 101 losses 47 rank 127 ratingDeviation 28 wins 52 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Mistral Large Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/123` |  |  |  |
| 94 | [DeepSeek V3.1 Terminus](https://benchize.com/models/deepseek-v3-1-terminus.md) | 1,427 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1427 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_deepseek_deepseek_v3_1_terminus ### Reported statistics coverageCount 27 draws 3 judged 85 losses 38 rank 133 ratingDeviation 28 wins 44 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label DeepSeek V3.1 Terminus Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/129` |  |  |  |
| 95 | [Mistral Medium 3.1](https://benchize.com/models/mistral-medium-3-1.md) | 1,426 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1426 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_mistralai_mistral_medium_3_1 ### Reported statistics coverageCount 27 draws 6 judged 84 losses 36 rank 134 ratingDeviation 28 wins 42 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Mistral Medium 3.1 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/130` |  |  |  |
| 96 | [Devstral 2 2512](https://benchize.com/models/devstral-2512.md) | 1,418 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1418 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_mistralai_devstral_2512 ### Reported statistics coverageCount 27 draws 0 judged 98 losses 46 rank 136 ratingDeviation 28 wins 52 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Devstral 2 2512 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/132` |  |  |  |
| 97 | [Gemini 2.5 Flash Lite Preview 09-2025](https://benchize.com/models/gemini-2-5-flash-lite-preview-09-2025.md) | 1,417 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1417 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_google_gemini_2_5_flash_lite_preview_09_2025 ### Reported statistics coverageCount 27 draws 2 judged 107 losses 49 rank 138 ratingDeviation 28 wins 56 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Gemini 2.5 Flash Lite Preview 09-2025 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/134` |  |  |  |
| 97 | [Qwen3 235B A22B Thinking 2507](https://benchize.com/models/qwen3-235b-a22b-thinking-2507.md) | 1,417 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1417 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_qwen_qwen3_235b_a22b_thinking_2507 ### Reported statistics coverageCount 27 draws 4 judged 154 losses 67 rank 137 ratingDeviation 28 wins 83 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Qwen3 235B A22B Thinking 2507 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/133` |  |  |  |
| 99 | [GPT-4.1 Mini](https://benchize.com/models/gpt-4-1-mini.md) | 1,414 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1414 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_4_1_mini ### Reported statistics coverageCount 27 draws 3 judged 91 losses 42 rank 139 ratingDeviation 28 wins 46 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-4.1 Mini Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/135` |  |  |  |
| 100 | [Mistral Large 3 2512](https://benchize.com/models/mistral-large-2512.md) | 1,412 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1412 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_mistralai_mistral_large_2512 ### Reported statistics coverageCount 27 draws 1 judged 85 losses 41 rank 140 ratingDeviation 28 wins 43 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Mistral Large 3 2512 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/136` |  |  |  |

[Next page](https://benchize.com/benchmarks/svgbench%3Aarena.md?cursor=%7B%22score%22%3A1412%2C%22id%22%3A%22a44f269f7df2278a3ac3774f69f645da9f685365cd7ef1592e000d6ac1f27618%22%7D)

---
Cite as: SVGBench Arena — Benchize, https://benchize.com/benchmarks/svgbench%3Aarena (retrieved 2026-10-21)