← All snapshotsView the live leaderboard
Benchmark snapshot: 2026-11-09
From Wikiprompt, the free prompt encyclopedia
Frozen photo of the rankings on this date. The live leaderboard is at /benchmarks.
← 2026-11-08
Text arena
| Rank | Model | Organization | Elo score | Votes |
|---|
| 5 | Claude Opus 5 (Max) | anthropic | 1,506 | 35,712 |
| 7 | Claude Opus 5 (High) | anthropic | 1,502 | 73,730 |
| 8 | Claude Opus 4.6 (High) | anthropic | 1,502 | 84,428 |
| 9 | Gemini 3.8 Flash (High) | google | 1,500 | 59,624 |
| 10 | Claude Opus 4.6 | anthropic | 1,497 | 89,224 |
| 12 | Claude Fable 5 (High) | anthropic | 1,491 | 45,562 |
| 13 | Muse Spark 1.3 (Max) | meta | 1,491 | 25,563 |
| 14 | Claude Opus 4.7 (High) | anthropic | 1,490 | 64,295 |
| 15 | Gemini 3.7 Flash (High) | google | 1,489 | 33,306 |
| 16 | Qwen3.8-Max | alibaba | 1,485 | 35,805 |
| 18 | Claude Opus 4.7 | anthropic | 1,483 | 65,387 |
| 19 | Gemini 3.5 Flash (High) | google | 1,483 | 47,646 |
| 20 | Gemini 3.1 Pro Preview | google | 1,480 | 132,347 |
| 21 | Gemini 3 Pro | google | 1,480 | 41,839 |
| 22 | Gemini 3.6 Flash (High) | google | 1,479 | 35,428 |
Web development arena
| Rank | Model | Organization | Elo score | Votes |
|---|
| 1 | Claude Opus 5.5 (Max) | anthropic | 1,818 | 4,034 |
| 2 | Claude Sonnet 5.5 (xHigh) | anthropic | 1,773 | 5,536 |
| 3 | Gemini 4 Carbon (High) | google | 1,768 | 2,130 |
| 4 | GPT-6 Astra (Max) | openai | 1,767 | 8,161 |
| 5 | Claude Fable 5.1 (Max) | anthropic | 1,744 | 9,507 |
| 6 | GPT-6.1 Sol (Max) | openai | 1,743 | 5,283 |
| 7 | Muse Wonder Full (Max) | meta | 1,724 | 2,080 |
| 8 | Claude Sonnet 5.5 (High) | anthropic | 1,713 | 7,582 |
| 9 | Claude Opus 5 (Max) | anthropic | 1,691 | 19,583 |
| 10 | Kimi K3.1 Pro (Max) | moonshot | 1,687 | 4,651 |
| 11 | Gemini 4 Argon (High) | google | 1,683 | 4,677 |
| 12 | GPT-6.1 Terra (Max) | openai | 1,678 | 3,626 |
| 13 | Qwen3.8-Max (0902) | alibaba | 1,677 | 21,409 |
| 14 | GPT-6 Sol (Max) | openai | 1,674 | 6,936 |
| 15 | Qwen3.8-Max | alibaba | 1,670 | 3,371 |
Vision arena
| Rank | Model | Organization | Elo score | Votes |
|---|
| 1 | Claude Fable 5 (High) | anthropic | 1,326 | 15,527 |
| 2 | Claude Opus 5.5 (High) | anthropic | 1,324 | 4,829 |
| 3 | Claude Fable 5.1 (Max) | anthropic | 1,322 | 6,330 |
| 4 | Claude Opus 4.7 | anthropic | 1,318 | 23,826 |
| 5 | Claude Opus 5 (High) | anthropic | 1,317 | 19,342 |
| 6 | Gemini 3.8 Flash (High) | google | 1,317 | 7,682 |
| 7 | Claude Opus 4.6 (High) | anthropic | 1,315 | 22,109 |
| 8 | Claude Opus 4.7 (High) | anthropic | 1,314 | 22,590 |
| 9 | Gemini 3.7 Flash (High) | google | 1,313 | 6,839 |
| 10 | Qwen3.8-Max | alibaba | 1,312 | 9,839 |
| 11 | Claude Opus 4.6 | anthropic | 1,312 | 26,605 |
| 12 | Muse Spark 1.3 (Max) | meta | 1,309 | 7,723 |
| 13 | Gemini 3.5 Flash (High) | google | 1,308 | 15,311 |
| 14 | Muse Spark | meta | 1,306 | 5,841 |
| 15 | Gemini 3.5 Flash (Medium) | google | 1,305 | 15,410 |
Text to image arena
| Rank | Model | Organization | Elo score | Votes |
|---|
| 1 | GPT-Image-2.5 Sunburst | openai | 1,428 | 58,604 |
| 2 | GPT-Image-2.6 Sunburst (Medium) | openai | 1,406 | 2,720 |
| 3 | GPT-Image-2.5 Flare | openai | 1,400 | 57,645 |
| 4 | GPT-Image-2.6 Flare (Medium) | openai | 1,383 | 2,552 |
| 5 | GPT-Image-2 (Medium) | openai | 1,382 | 106,289 |
| 6 | MAI-Image-2.6 | microsoft-ai | 1,330 | 38,967 |
| 7 | Gemini Nano Banana 2.1 | google | 1,328 | 4,966 |
| 8 | Grok Imagine Image 2.0 | xai | 1,319 | 9,961 |
| 9 | Reve 2.1 | reve | 1,302 | 7,909 |
| 10 | Grok Imagine Image 2.0 (20260801) | xai | 1,290 | 32,993 |
| 11 | Reve 2.0 | reve | 1,268 | 15,323 |
| 12 | Muse Image | meta | 1,266 | 57,616 |
| 13 | Gemini 3.1 Flash Image (nano-banana-2, Web Search) | google | 1,257 | 77,983 |
| 14 | Qwen-Image-3.0-Pro | alibaba | 1,254 | 10,915 |
| 15 | MAI-Image-2.5 | microsoft-ai | 1,253 | 59,125 |
Image editing arena
| Rank | Model | Organization | Elo score | Votes |
|---|
| 1 | GPT-Image-2.5 Sunburst | openai | 1,520 | 121,193 |
| 2 | GPT-Image-2.5 Flare | openai | 1,485 | 118,252 |
| 3 | GPT-Image-2.6 Sunburst (Medium) | openai | 1,477 | 3,519 |
| 4 | MAI-Image-2.7-Preview | microsoft-ai | 1,468 | 20,942 |
| 5 | GPT-Image-2 (Medium) | openai | 1,461 | 356,134 |
| 6 | GPT-Image-2.6 Flare (Medium) | openai | 1,460 | 3,554 |
| 7 | Grok Imagine Image 2.0 | xai | 1,437 | 33,971 |
| 8 | MAI-Image-2.6 | microsoft-ai | 1,428 | 82,981 |
| 9 | Gemini Nano Banana 2.1 | google | 1,427 | 12,071 |
| 10 | Grok Imagine Image 2.0 (20260801) | xai | 1,418 | 122,753 |
| 11 | Krea 3 Ultra | krea | 1,411 | 2,629 |
| 12 | MAI-Image-2.5 | microsoft-ai | 1,400 | 183,604 |
| 13 | Muse Image | meta | 1,400 | 196,190 |
| 14 | Seedream 5.0 Pro | bytedance | 1,392 | 338,416 |
| 15 | Grok Imagine Image (Quality, 20260519) | xai | 1,391 | 37,154 |
Text to video arena
| Rank | Model | Organization | Elo score | Votes |
|---|
| 1 | Gemini Omni 1.2 Flash | google | 1,540 | 1,714 |
| 2 | Gemini Omni 1.1 Flash | google | 1,513 | 1,790 |
| 3 | gemini-omni-flash | google | 1,509 | 46,890 |
| 4 | FLUX 3 Video | bfl | 1,491 | 1,314 |
| 5 | Grok Imagine Video 1.5 | xai | 1,488 | 1,249 |
| 6 | Dreamina Seedance 2.0 (720p) | bytedance | 1,483 | 72,281 |
| 7 | Dreamina Seedance 2.5 (720p) | bytedance | 1,479 | 25,595 |
| 8 | Wan 3.0 | alibaba | 1,476 | 3,060 |
| 9 | SkyReels V4 | skyreel | 1,459 | 1,060 |
| 10 | Muse Video | meta | 1,457 | 2,225 |
| 11 | MiniMax H3 | minimax | 1,456 | 29,442 |
| 12 | HappyHorse 1.0 | aorizon | 1,429 | 22,898 |
| 13 | Sora 2 Pro | openai | 1,367 | 55,962 |
| 14 | Veo 3.1 (Audio) | google | 1,363 | 13,790 |
| 15 | Veo 3.1 (Audio, 1080p) | google | 1,363 | 25,636 |
Video editing arena
| Rank | Model | Organization | Elo score | Votes |
|---|
| 1 | Wan 3.0 | alibaba | 1,424 | 2,060 |
| 2 | Dreamina Seedance 2.5 (720p) | bytedance | 1,417 | 5,062 |
| 3 | Gemini Omni 1.2 Flash | google | 1,396 | 1,167 |
| 4 | MiniMax H3 | minimax | 1,383 | 8,088 |
| 5 | gemini-omni-flash | google | 1,378 | 4,915 |
| 6 | Dreamina Seedance 2.0 (720p) | bytedance | 1,369 | 7,282 |
| 7 | HappyHorse 1.0 | aorizon | 1,305 | 3,253 |
| 8 | Kling O3 Pro | kling | 1,263 | 14,330 |
| 9 | Grok Imagine Video | xai | 1,250 | 18,648 |
| 10 | Kling O1 Pro | kling | 1,190 | 17,534 |
| 11 | Runway Gen-4 Aleph | runway | 1,181 | 10,161 |
Search arena
| Rank | Model | Organization | Elo score | Votes |
|---|
| 1 | Qwen3.8-Max | alibaba | 1,259 | 2,059 |
| 2 | GPT-5.6 Sol (xHigh) | openai | 1,258 | 62,627 |
| 3 | Claude Opus 4.6 (Search) | anthropic | 1,252 | 166,748 |
| 4 | GPT-5.5 (Search) | openai | 1,245 | 121,707 |
| 5 | Claude Opus 5 (High) | anthropic | 1,239 | 34,226 |
| 6 | Claude Fable 5.1 (High) | anthropic | 1,239 | 34,006 |
| 7 | GPT-6 Astra (Max) | openai | 1,231 | 17,457 |
| 8 | GPT-6.1 Sol (Max) | openai | 1,231 | 26,802 |
| 9 | Claude Opus 4.7 | anthropic | 1,230 | 121,903 |
| 10 | Claude Fable 5 (High) | anthropic | 1,228 | 69,533 |
| 11 | ERNIE 5.1 | baidu | 1,227 | 3,925 |
| 12 | Claude Sonnet 4.6 (Search) | anthropic | 1,221 | 167,506 |
| 13 | Grok 4.5 | xai | 1,216 | 105,720 |
| 14 | Claude Opus 5.5 (Medium) | anthropic | 1,214 | 32,009 |
| 15 | Gemini 3.1 Pro (Grounding) | google | 1,210 | 172,042 |
Agentic arena
| Rank | Model | Organization | Elo score | Votes |
|---|
| 1 | Claude Opus 5.5 (Max) | anthropic | | |
| 2 | Gemini 4 Carbon (High) | google | | |
| 3 | Claude Sonnet 5.5 (Max) | anthropic | | |
| 4 | Claude Fable 5.1 (Max) | anthropic | | |
| 5 | GPT-6 Astra (Max) | openai | | |
| 6 | GPT-6.1 Sol (Max) | openai | | |
| 7 | GPT-6.1 Terra (Max) | openai | | |
| 8 | Gemini 4 Argon (High) | google | | |
| 9 | Muse Wonder Full (Max) | meta | | |
| 10 | Claude Fable 5 (High) | anthropic | | |
| 11 | Claude Opus 5 (Max) | anthropic | | |
| 12 | GPT-6 Sol (Max) | openai | | |
| 13 | Kimi K3.1 Pro (Max) | moonshot | | |
| 14 | Hy4 | tencent | | |
| 15 | GPT-5.6 Sol (xHigh) | openai | | |
Document arena
| Rank | Model | Organization | Elo score | Votes |
|---|
| 1 | Claude Fable 5.1 (Max) | anthropic | 1,515 | 1,452 |
| 2 | Claude Opus 5 (High) | anthropic | 1,509 | 16,176 |
| 3 | Claude Opus 4.6 (High) | anthropic | 1,508 | 29,449 |
| 4 | Claude Opus 4.6 | anthropic | 1,506 | 47,255 |
| 5 | Claude Fable 5 (High) | anthropic | 1,496 | 12,352 |
| 6 | Claude Opus 4.7 (High) | anthropic | 1,496 | 23,319 |
| 7 | Claude Opus 4.7 | anthropic | 1,495 | 23,622 |
| 8 | GPT-5.5 (High) | openai | 1,484 | 27,316 |
| 9 | Gemini 3.8 Flash (High) | google | 1,482 | 7,000 |
| 10 | Claude Sonnet 4.6 | anthropic | 1,482 | 61,051 |
| 11 | GPT-5.5 | openai | 1,481 | 27,746 |
| 12 | GPT-5.6 Sol (xHigh) | openai | 1,480 | 9,666 |
| 13 | Gemini 3.7 Flash (High) | google | 1,476 | 7,732 |
| 14 | Claude Opus 4.8 (High) | anthropic | 1,475 | 12,062 |
| 15 | Muse Spark 1.3 (Max) | meta | 1,473 | 7,234 |
Other leaderboards
Aider polyglot (coding)
Metric: pass rate 2 (%) · aider.chat/docs/leaderboards/
| Rank | Model | Organization | Score | Votes |
|---|
| 1 | gpt-5 (high) | | 88 | |
| 2 | gpt-5 (medium) | | 86.7 | |
| 3 | o3-pro (high) | | 84.9 | |
| 4 | gemini-2.5-pro-preview-06-05 (32k think) | | 83.1 | |
| 5 | o3 (high) | | 81.3 | |
| 6 | gpt-5 (low) | | 81.3 | |
| 7 | grok-4 (high) | | 79.6 | |
| 8 | gemini-2.5-pro-preview-06-05 (default think) | | 79.1 | |
| 9 | o3 (high) + gpt-4.1 | | 78.2 | |
| 10 | Gemini 2.5 Pro Preview 05-06 | | 76.9 | |
| 11 | o3 | | 76.9 | |
| 12 | DeepSeek-V3.2-Exp (Reasoner) | | 74.2 | |
| 13 | Gemini 2.5 Pro Preview 03-25 | | 72.9 | |
| 14 | o4-mini (high) | | 72 | |
| 15 | claude-opus-4-20250514 (32k thinking) | | 72 | |
BenchLM
Metric: aggregated display score · benchlm.ai
| Rank | Model | Organization | Score | Votes |
|---|
| 1 | Gemini 4 Carbon | Google | 88.7 | |
| 2 | Claude Opus 5.5 | Anthropic | 86.3 | |
| 3 | GPT-6 Astra | OpenAI | 85.8 | |
| 4 | GPT-6.1 Sol | OpenAI | 85.4 | |
| 5 | Gemini 4 Argon | Google | 82.1 | |
| 6 | Claude Sonnet 5.5 | Anthropic | 81.8 | |
| 7 | Claude Fable 5.1 | Anthropic | 81.3 | |
| 8 | Claude Fable 5 | Anthropic | 80.7 | |
| 9 | GPT-6.1 Terra | OpenAI | 80.7 | |
| 10 | Claude Opus 5 | Anthropic | 79.6 | |
| 11 | GPT-6 Sol | OpenAI | 78.1 | |
| 12 | Kimi K3.1 Pro | Moonshot AI | 75 | |
| 13 | GPT-5.6 Sol | OpenAI | 74.8 | |
| 14 | GPT-5.5 Pro | OpenAI | 72.8 | |
| 15 | GPT-5.6 Terra | OpenAI | 69.8 | |
Sources and methodology
Rankings above are aggregated from open community evaluations. Elo ratings, confidence intervals and vote counts come from LMArena (crowdsourced head-to-head model battles, published as an open dataset). Model pricing and context metadata come from the public OpenRouter API. Wikiprompt snapshots these sources daily and preserves the history; we run no proprietary evaluations of our own.