Image, audio & video models
Rankings come from LMArena's blind side-by-side votes. Below them is a catalogue of media models with API prices.
Text to image ranking
82 models rated by LMArena voters
| # | Model | Rating | Confidence range | Votes | Licence |
|---|---|---|---|---|---|
| 1 | gpt-image-2.5-sunburstOpenAI | 1425 | 17,752 | Proprietary | |
| 2 | gpt-image-2.5-flareOpenAI | 1398 | 16,889 | Proprietary | |
| 3 | gpt-image-2 (medium)OpenAI | 1383 | 93,334 | Proprietary | |
| 4 | grok-imagine-image-2.0 (canvas)xAI | 1334 | 3,113 | Proprietary | |
| 5 | mai-image-2.6microsoft-ai | 1332 | 25,091 | Proprietary | |
| 6 | gemini-nano-banana-2.1Google | 1328 | 5,310 | Proprietary | |
| 7 | reve-2.1reve | 1302 | 8,249 | Proprietary | |
| 8 | grok-imagine-image-2.0 (20260801)xAI | 1294 | 14,483 | Proprietary | |
| 9 | muse-imageMeta | 1274 | 42,262 | Proprietary | |
| 10 | reve-2.0reve | 1269 | 15,773 | Proprietary | |
| 11 | gemini-3.1-flash-image (nano-banana-2) [web-search]Google | 1262 | 60,515 | Proprietary | |
| 12 | seedream-5.0-proByteDance | 1256 | 94,181 | Proprietary | |
| 13 | qwen-image-3.0-proAlibaba | 1255 | 11,440 | Proprietary | |
| 14 | mai-image-2.5microsoft-ai | 1254 | 61,265 | Proprietary | |
| 15 | gemini-3.1-flash-lite-image (nano-banana-2-lite)Google | 1250 | 17,804 | Proprietary |
Showing the top 15 of 82.
Image editing ranking
59 models rated by LMArena voters
| # | Model | Rating | Confidence range | Votes | Licence |
|---|---|---|---|---|---|
| 1 | gpt-image-2.5-sunburstOpenAI | 1524 | 59,825 | Proprietary | |
| 2 | gpt-image-2.5-flareOpenAI | 1481 | 57,408 | Proprietary | |
| 3 | gpt-image-2 (medium)OpenAI | 1462 | 305,825 | Proprietary | |
| 4 | grok-imagine-image-2.0 (canvas)xAI | 1439 | 11,589 | Proprietary | |
| 5 | mai-image-2.6microsoft-ai | 1428 | 51,384 | Proprietary | |
| 6 | gemini-nano-banana-2.1Google | 1428 | 12,985 | Proprietary | |
| 7 | grok-imagine-image-2.0 (20260801)xAI | 1425 | 50,427 | Proprietary | |
| 8 | muse-imageMeta | 1403 | 142,644 | Proprietary | |
| 9 | mai-image-2.5microsoft-ai | 1401 | 190,081 | Proprietary | |
| 10 | seedream-5.0-proByteDance | 1394 | 282,865 | Proprietary | |
| 11 | grok-imagine-image-quality (20260519)xAI | 1391 | 38,195 | Proprietary | |
| 12 | gemini-3-pro-image-2k (nano-banana-pro)Google | 1390 | 651,674 | Proprietary | |
| 13 | chatgpt-image-latest-high-fidelity (20251216)OpenAI | 1389 | 629,464 | Proprietary | |
| 14 | gemini-3.1-flash-image (nano-banana-2) [web-search]Google | 1387 | 229,782 | Proprietary | |
| 15 | gemini-3-pro-image-preview (nano-banana-pro)Google | 1386 | 540,775 | Proprietary |
Showing the top 15 of 59.
Text to video ranking
48 models rated by LMArena voters
| # | Model | Rating | Confidence range | Votes | Licence |
|---|---|---|---|---|---|
| 1 | gemini-omni-1.1-flashGoogle | 1516 | 1,784 | Proprietary | |
| 2 | gemini-omni-flashGoogle | 1513 | 26,576 | Proprietary | |
| 3 | flux-3-videoBlack Forest Labs | 1493 | 1,302 | Proprietary | |
| 4 | grok-imagine-video-1.5-agentxAI | 1492 | 1,218 | Proprietary | |
| 5 | dreamina-seedance-2.0-720pByteDance | 1479 | 56,318 | Proprietary | |
| 6 | wan3.0Alibaba | 1476 | 2,598 | Proprietary | |
| 7 | dreamina-seedance-2.5-720pByteDance | 1474 | 8,001 | Proprietary | |
| 8 | minimax-h3MiniMax | 1460 | 11,417 | minimax-h3-community-license-agreement | |
| 9 | muse-videoMeta | 1456 | 2,188 | Proprietary | |
| 10 | happyhorse-1.0aorizon | 1427 | 22,264 | Proprietary | |
| 11 | sora-2-proOpenAI | 1368 | 54,167 | Proprietary | |
| 12 | veo-3.1-audioGoogle | 1364 | 13,741 | Proprietary | |
| 13 | veo-3.1-audio-1080pGoogle | 1362 | 25,076 | Proprietary | |
| 14 | veo-3.1-fast-audioGoogle | 1362 | 39,484 | Proprietary | |
| 15 | veo-3.1-fast-audio-1080pGoogle | 1358 | 25,870 | Proprietary |
Showing the top 15 of 48.
Image to video ranking
48 models rated by LMArena voters
| # | Model | Rating | Confidence range | Votes | Licence |
|---|---|---|---|---|---|
| 1 | minimax-h3MiniMax | 1495 | 57,112 | minimax-h3-community-license-agreement | |
| 2 | gemini-omni-1.1-flashGoogle | 1489 | 3,734 | Proprietary | |
| 3 | wan3.0Alibaba | 1480 | 3,442 | Proprietary | |
| 4 | dreamina-seedance-2.5-720pByteDance | 1477 | 15,729 | Proprietary | |
| 5 | dreamina-seedance-2.0-720pByteDance | 1475 | 121,427 | Proprietary | |
| 6 | gemini-omni-flashGoogle | 1465 | 87,155 | Proprietary | |
| 7 | hidream-o1-video-1.0hidream | 1457 | 6,488 | Proprietary | |
| 8 | grok-imagine-video-1.5-720pxAI | 1456 | 137,459 | Proprietary | |
| 9 | flux-3-video-20260811Black Forest Labs | 1449 | 37,042 | Proprietary | |
| 10 | happyhorse-1.0aorizon | 1442 | 70,640 | Proprietary | |
| 11 | wan2.7-i2vwan | 1428 | 85,521 | Proprietary | |
| 12 | grok-imagine-video-720pxAI | 1415 | 554,050 | Proprietary | |
| 13 | veo-3.1-audioGoogle | 1398 | 25,116 | Proprietary | |
| 14 | veo-3.1-audio-1080pGoogle | 1390 | 53,089 | Proprietary | |
| 15 | veo-3.1-fast-audioGoogle | 1385 | 99,804 | Proprietary |
Showing the top 15 of 48.
Catalogue with API prices
Image generation (10)
| Model | Inputs → outputs | Context | Input / output $ per 1M tokens | Released |
|---|---|---|---|---|
| Nano Banana 2.1Google | imagetext→imagetext | 66K | $1.50 / $7.50 | Oct 6, 2026 |
| Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google | imagetext→imagetext | 66K | $0.25 / $1.50 | Jun 30, 2026 |
| Nano Banana 2 (Gemini 3.1 Flash Image)Google | imagetext→imagetext | 131K | $0.50 / $3.00 | Jun 18, 2026 |
| Nano Banana Pro (Gemini 3 Pro Image)Google | imagetext→imagetext | 131K | $2.00 / $12.00 | Jun 18, 2026 |
| GPT-5.4 Image 2OpenAI | imagetextfile→imagetext | 272K | $8.00 / $15.00 | Apr 21, 2026 |
| Nano Banana 2 (Gemini 3.1 Flash Image Preview)Google | imagetext→imagetext | 66K | $0.50 / $3.00 | Feb 26, 2026 |
| Nano Banana Pro (Gemini 3 Pro Image Preview)Google | imagetext→imagetext | 66K | $2.00 / $12.00 | Nov 20, 2025 |
| GPT-5 Image MiniOpenAI | fileimagetext→imagetext | 400K | $2.50 / $2.00 | Oct 16, 2025 |
| GPT-5 ImageOpenAI | imagetextfile→imagetext | 400K | $10.00 / $10.00 | Oct 14, 2025 |
| Nano Banana (Gemini 2.5 Flash Image)Google | imagetext→imagetext | 33K | $0.30 / $2.50 | Oct 7, 2025 |
Audio and music generation (4)
| Model | Inputs → outputs | Context | Input / output $ per 1M tokens | Released |
|---|---|---|---|---|
| Lyria 3 Clip PreviewGoogle | textimage→textaudio | 1.05M | Free / Free | Mar 30, 2026 |
| Lyria 3 Pro PreviewGoogle | textimage→textaudio | 1.05M | Free / Free | Mar 30, 2026 |
| GPT AudioOpenAI | textaudio→textaudio | 128K | $2.50 / $10.00 | Jan 19, 2026 |
| GPT Audio MiniOpenAI | textaudio→textaudio | 128K | $0.60 / $2.40 | Jan 19, 2026 |
Video generation (0)
No models of this kind are listed by our sources yet.