Leaderboard Changelog

This page documents notable updates to our leaderboard—new models, new arenas, updates to the methodology, and more. Stay tuned!

For model deprecations, check the public updates on GitHub.

Image Battles in Agent Mode are now counted in the Image Arena leaderboard. You can now filter specifically for image battles in Agentic sessions, straight from the Image Arena (Text to Image, Single Image Edit, and Multi Image Edit)

Kimi K3.1 Pro (Max) has been added to the Agent Arena leaderboard.

NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4) has been added to the Agent Arena leaderboard.

Kimi K3.1 Pro (Max) has been added to the Code Arena: WebDev leaderboard.

Claude Haiku 5.5 (High) has been added to the Text Arena leaderboard.

Krea 3 Ultra has been added to the Single Image Edit Arena & Multi Image Edit Arena leaderboards.

beam-1.0-501b-a23b has been added to the Text Arena leaderboard.

Muse Wonder Full (Max) has been added to the Agent Arena leaderboard.

MiniMax-M3.1-Flash has been added to the Code Arena: WebDev leaderboards.

Muse Wonder Full (Max) has been added to the Code Arena: WebDev leaderboards.

NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4) has been added to the Code Arena: WebDev, Image-to-WebDev Arena and Vision Arena.

DeepSeek-V4.1-Flash-20261017 (Max) has been added to the Agent Arena leaderboard.

DeepSeek-V4.1-Flash-20261017 (Max) has been added to the Code Arena: WebDev leaderboards.

beam-1.0-501b-a23b has been added to the Agent Arena and Code Arena: WebDev leaderboards.

MiMo V2.6 Pro & MiMo V2.6 Flash has been added to the Agent Arena leaderboard.

Claude Haiku 5.5 (High) has been added to the Agent Arena leaderboard.

Muse Wonder (Max) has been added to the Agent Arena leaderboard.

qwen3.8-max, claude-fable-5.1-high, claude-opus-5-high, gpt-6-astra-max, gpt-6.1-sol-max, claude-opus-5.5-medium, gpt-6-sol-max & gpt-6-luna-max has been added to the Search Arena leaderboard.

muse-spark-1.3-max has been added to the Code Arena: WebDev & Text Arena leaderboards.

We’ve updated how the Bash Recovery score is calculated on the Agent Arena signal leaderboard and are now naming this signal, Bash Reliability. There are two changes: how we detect bash failures, and how we turn them into a score.

• Detecting failures. Previously, we used a simple set of rules to decide whether a bash call failed because of the agent’s mistake. The previous rules sometimes misjudged which bash calls were real failures, flagging correct tests and empty searches; sometimes missing errors were hidden by piped commands. We now use an LLM judge that looks at each call’s purpose, outcome, and cause of any error, and whether or not the error was fixed within the call. This results in a more accurate assessment of whether a bash call failed.
• Scoring. Previously, the score measured how many consecutive turns it took a model to recover after a bash error. This only looked at sessions where something went wrong, so a model with flawless bash use wasn’t being credited. It also treated any successful call after a failure as a "recovery," even though sometimes the subsequent call was not directly related to the original failure. The new score measures bash failures per call, so a session with no bash failures now counts in a model’s favor.

Together, these changes mean the score better reflects how reliably a model uses the command line. The updates are reflected on the new Bash Reliability signal leaderboard. Many models have shifted, so we’re sharing this update because we want the community and our customers to understand exactly how and why it’s changing, and how it shows up on the leaderboard. Backfilled scores under this new methodology will be available in our public HuggingFace datasets soon. The full technical breakdown of the new definition is available on the Agent Arena signal definitions page.

claude-opus-5.5-max has been added to the Image-to-WebDev leaderboard.

claude-opus-5.5-high, muse-spark-1.3 (xHigh), gpt-6-sol-max, deepseek-v4.1-flash-max, grok-4.7-xhigh and gpt-6-luna-max has been added to the Vision Arena leaderboard.

Introducing the Alignment Index: A new leaderboard built from real-world agent sessions to measure agent reliability across key failure signals like unauthorized actions, false attribution, and deceptive completion.

mistral-large-4 has been added to the Text Arena leaderboard.

mistral-large-4 has been added to the Agent Arena leaderboard.

mimo-v2.6-flash has been added to the Code Arena: WebDev & Image-to-WebDev leaderboards.

mimo-v2.6-pro has been added to the Image-to-WebDev leaderboard.

mistral-large-4 has been added to the Code Arena: WebDev leaderboard.

gemini-nano-banana-2.1 has been added to the Text-to-Image & Image Edit leaderboard.

grok-imagine-image-2.0 (canvas) has been added to the Text-to-Image & Image Edit leaderboard.

claude-sonnet-5.5-xhigh has been added to the Text Arena & Vision Arena leaderboard.

Claude Sonnet 5.5 (Max) has been added to the Agent Arena leaderboard.

GPT 6.1 Sol (Max) has been added to the Agent Arena leaderboard.

claude-sonnet-5.5-xhigh has been added to the Code Arena: WebDev leaderboard.

We’ve updated how the Steerability score is calculated on the Agent Arena signal leaderboard. Previously, it only measured whether a model fixed a mistake right after being corrected by a user. This meant that the signal rewarded corrected turns, but it didn’t reward a model for needing fewer corrections in the first place. That made the signal not as accurate as it could be: a model that made more mistakes had more chances to "pass," while a model that got things right the first time earned no credit.

The newest frontier models require corrections less often than other models, but the old score didn’t capture that advantage. The updated methodology now evaluates every assistant turn in a conversation we can judge, so getting things right the first time counts. It also continues to weigh repeated corrections more heavily than one-off corrections that are resolved immediately.

We're sharing this update because we want the community and our customers to understand exactly how and why it's changing, not just see scores move. Backfilled scores under the new methodology will be available in our public HuggingFace datasets soon. Full technical breakdown of the new definition is available on the signal definitions page.

ideogram-4.5 has been added to the Image Edit leaderboard.

gpt-6.1-sol-max has been added to the Code Arena: WebDev leaderboard.

gemini-4-argon-high has been added to Code Arena: WebDev, Agent Arena, and Text Arena leaderboards.

hidream-o1-video-1.0 has been added to the Image-to-Video Arena leaderboard.

claude-sonnet-5.5-high has been added to the Code Arena: WebDev leaderboard.

mimo-v2.6-flash and mimo-v2.6-pro has been added to the Vision Arena leaderboard.

GPT 6 Luna (Max) has been added to the Agent Arena leaderboard.

Claude Opus 5.5 (High) has been added to the Agent Arena leaderboard.

step-5-preview-high has been added to the Code Arena: WebDev leaderboard.

GPT 6 Sol (Max) has been added to the Agent Arena leaderboard.

deepseek-v4.1-flash-max, grok-4.7-xhigh, gpt-6-sol-max, gpt-6-luna-max, and claude-opus-5.5-high has been added to the Text Arena leaderboard.

Released a fully redesigned leaderboard overview page. This new hub provides insights on model performance across categories, bringing all our live signals into one place for researchers, builders, and our global community of users who power our model evaluations.

recraft-v4.1-flash has been added to the Text-to-Image Arena leaderboard.

gpt-6-luna-max has been added to the Code Arena: WebDev leaderboard.

Grok 4.7 (xHigh) has been added to the Agent Arena leaderboard.

gpt-6-sol-max has been added to the Code Arena: WebDev leaderboard.

claude-opus-5.5-max has been added to the Code Arena: WebDev leaderboard.

qwen-image-2.1 has been added to the Text-to-Image Arena and the Image Edit Arena leaderboard.

grok-4.7-xhigh has been added to the Code Arena: WebDev leaderboard.

mimo-v2.6-pro has been added to the Code Arena: WebDev leaderboard.

Deepseek V4.1 Flash (Max) has been added to the Agent Arena leaderboard.

hidream-o1-video has been added to the Image-to-Video Arena leaderboard.

Muse Spark 1.3 (Max), gpt-6-astra-max, claude-fable-5.1-max, and glm-5.3-flash have been added to the Image-to-WebDev Arena leaderboard.

Muse Spark 1.3 (Max), gpt-6-astra-max and claude-fable-5.1-max have been added to the Document & Vision Arena leaderboards.

Muse Spark 1.3 (Max) has been added to the Text Arena leaderboard.

Muse Spark 1.3 (Max) has been added to the Agent Arena leaderboard.

gpt-6-astra-max has been added to the Text Arena leaderboard.

deepseek-v4.1-flash-max has been added to the Code Arena: WebDev leaderboard.

GPT 6 Astra (Max) has been added to the Agent Arena leaderboard.

gpt-image-2.5-sunburst & gpt-image-2.5-flare has been added to the Text-to-Image Arena, Image Edit Arena and Multi Image Edit leaderboards.

muse-spark-1.3-max has been added to the Code Arena: WebDev leaderboard.

gpt-6-astra-max has been added to the Code Arena: WebDev leaderboard.

Claude Fable 5.1 (Max) has been added to the Agent Arena leaverboard.

grok-imagine-video-1.5-agent has been added to the Text-to-Video Arena leaderboard.

wan3.0 has been added to the Text-to-Video Arena leaderboard.

Gemini 3.8 Flash (High) has been added to the Agent Arena, Code Arena:WebDev and Text Arena leaderboards.

claude-fable-5.1-max has been added to the Code Arena: WebDev and Text Arena leaderboards.

wan3.0 has been added to the Image-to-Video Arena leaderboard.

Hy4 preview has been added to the Agent Arena leaderboard.

granite-4.2-30b, granite-4.2-3b and granite-4.2-8b has been added to the Text Arena leaderboard.

qwen3.8-max-0902 has been added to the Code Arena leaderboard.

glm-5.3-flash has been added to the Agent Arena leaderboard.

Qwen3.8 Flash Next has been added to the Agent Arena leaderboard.

glm-5.3-flash has been added to the Text Arena and Vision Arena leaderboards.

gemini-omni-1.1-flash has been added to the Text-to-Video Arena and Image-to-Video leaderboards.

Grok 4.6 (xHigh) has been added to the Agent Arena leaderboard.

wan3.0 has been added to the Video Edit Arena leaderboard.

hy4-preview has been added to the Code Arena leaderboard.

glm-5.3-flash has been added to the Code Arena:WebDev leaderboard.

qwen3.8-flash-next has been added to the Code Arena:WebDev leaderboard.

Qwen 3.8 27B has been added to the Agent Arena leaderboard.

qwen3.8-27b has been added to the Image-to-WebDev Arena leaderboard.

GLM 5.3 (Max) has been added to the Agent Arena leaderboard.

gpt-5.6-sol-xhigh & grok-4.5 has been added to the Search Arena leaderboard.

qwen3.8-27b has been aded to the Text, Vision and Code Arena leaderboards.

Muse Spark 1.2 (xHigh) has been added to the Agent Arena leaderboard.

deepseek-v4-pro-high has been added to the Agent Arena and Text Arena leaderboard.

glm-5.3-max has been added to the Text Arena and Code Arena leaderboard.

Inkling-Small has been added to Agent Arena leaderboard.

MAI-Image-2.6 has been added to Image Edit Arena leaderboard.

Qwen3.8 Max has been added to the Agent Arena leaderboard.

dreamina-seedance-2.5-720p has been added to the Text-to-Video, Image-to-Video, and Video Edit leaderboards.

deepseek-v4-pro-high-20260813 has been added to the Code Arena leaderboard.

flux-3-video-20260811 has been added to the Image-to-Video leaderboard.

minimax-h3 has been added to the Video Edit leaderboard.

Gemini 3.7 Flash (High) has been added to the Agent Arena, Text Arena, and Code Arena leaderboards.

grok-4.6-high has been added to the Code Arena and Text Arena leaderboards.

nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4 has been added to the Text Arena leaderboard.

Solar Pro 4 has been added to Agent Arena, Text Arena and Code Arena leaderboards.

mai-image-2.6-preview has been added to the Text-to-Image Arena leaderboard.

muse-glimmer has been added to the Text and Code Arena leaderboards.

grok-imagine-image-2.0 (low) has been added to the Text-to-Image Arena and Image Edit Arena leaderboards.

Mistral Medium 3.5 has been added to the Agent Arena leaderboard.

claude-opus-5-max has been added to the Fullstack Code Arena leaderboard.

Deepseek V4 Flash (High) (20260731) has been added to the Agent Arena leaderboard.

qwen-image-3.0-pro has been added to the Text-to-Image Arena leaderboard.

qwen3.8-max has been added to the Image-to-WebDev Arena leaderboard.

Cosmos3-Super-Text2Image and Cosmos3-Super-Text2Image (Agentic) scores now reflect the models' native endpoints instead of fal.ai on the Text-to-Image Arena leaderboard.

minimax-h3 has been added to the Text-to-Video Arena and Image-to-Video Arena leaderboards.

qwen3.8-max has been added to the Frontend Code Arena, Text Arena and Vision Arena leaderboards.

Code Arena | Image-to-WebDev Leaderboard update.

gpt-5.6-sol-xhigh, gpt-5.6-terra-xhigh, and gpt-5.6-luna-xhigh has been added to the Code Arena, Document Arena, Vision Arena and Text Arena leaderboards.

deepseek-v4-flash-high has been added to the Code Arena leaderboard.

Single Image Edit and Multi-Image Edit categories in Image Edit Arena now have the same seven categories as the Text-to-Image Arena.

inkling-small has been added to the Text Arena leaderboard.

Claude Opus 5 (Max) and Claude Opus 5 (High) has been added to the Agent Arena leaderboard.

The Code Arena Fullstack leaderboard is now live. View overall rankings across AI models on full-stack web development tasks: multi-step reasoning, tool use, and end-to-end app generation. Read our blog post to learn more about how Code Arena now provides fullstack capabilities.

claude-opus-5-high and claude-opus-5-max have been added to to the Text Arena, Vision Arena, Document Arena and Code Arena leaderboards.

muse-spark-1.1 and grok-4.5 have been added to the Vision Arena and Document Arena leaderboards.

GPT 5.6 Terra (xHigh) and GPT 5.6 Luna (xHigh), have been added to the Agent Arena leaderboard. Kimi K3 (Max) has been renamed on the Agent leaderboard to reflect Max level of reasoning.

Kimi K3 and Inkling has been added to the Agent Arena leaderboard.

claude-fable-5 and claude-sonnet-5-high has been added to the Image-to-WebDev Arena leaderboard.

inkling has been added to the Text Arena & Code Arena leaderboards.

kimi-k3 has been added to Text Arena & Code Arena leaderboards.

Muse Spark 1.1 has been added to the Agent Arena leaderboard.

GPT 5.6 Sol (xHigh) has been added to the Agent Arena leaderboard.
Grok 4.5 has been added to the Agent Arena leaderboard.

The claude-fable-5 scores have been updated to reflect only votes collected on or after July 1 for the Code Arena, Vision Arena, Document Arena and Search Arena leaderboards.

seedream-5.0-pro has been added to the Image Arena leaderboard.

muse-spark-1.1 has been added to the Text Arena & Code Arena leaderboards.
gpt-5.6-sol-xhigh (codex-harness) has been added to the Code Arena leaderboard.

reve-2.1 has been added to the Text-to-Image Arena leaderboard.

muse-image has been added to the Text-to-Image Arena & Image Edit Arena leaderboard.

muse-video has been added to the Text-to-Video Arena leaderboard.

Claude Opus 4.7 (Thinking) has been added to the Agent Arena leaderboard.

krea-2-turbo has been added to the Text-to-Image Arena leaderboard.

claude-sonnet-5-thinking has been added to Code Arena, Text Arena, Search Arena, Vision Arena, and Document Arena leaderboards.

gemini-3.1-flash-lite-image (nano-banana-2-lite) has been added to the Text-to-Image Arena and Image Edit Arena leaderboards.

gemini-omni-flash has been added to the Video Edit Arena leaderboard.

qwen-image-2.0-pro-2026-06-22 has been added to the Text-to-Image Arena and Image Edit Arena leaderboards.

qwen3.7-plus-preview has been deprecated from the Vision Arena leaderboard.

qwen3.7-plus has been added to the Vision Arena leaderboard.

wan2.7-i2v has been added to the Image-to-Video Arena leaderboard.

seed-2.1-pro-preview has been added to the Code Arena leaderboard.

muse-spark has been deprecated from the Code Arena leaderboard.

Kimi K2.7 Code has been added to the Agent Arena leaderboard.

Minimax M3 and GLM 5.2 (Max) has been added to the Agent Arena leaderboard.

GLM 5.2 (Max) has been added to Text Arena and Code Arena leaderboards.

claude-opus-4-8 and claude-fable-5 has been added to the Search Arena leaderboard.

kimi-k2.7-code has been added to the Code Arena leaderboard.

Nemotron 3 Ultra has been added to the Agent Arena leaderboard.

gemini-omni-flash has been added to the Text-to-Video Arena leaderboard.

GPT 5.5 (xHigh) has been added to the Agent Arena leaderboard.

claude-fable-5 has been added to the Code Arena, Text Arena, Document Arena, Vision Arena, and Agent Arena leaderboard.

Claude Opus 4.8 (Thinking) & Claude Opus 4.8 has been added to the Agent Arena leaderboard.

Grok Build 0.1 & Grok 4.3 (High) has been added to the Agent Arena leaderboard.

claude-opus-4-8, and claude-opus-4-8-thinking has been added to the Text Arena, Vision Arena, Document Arena, and Code Arena leaderboards.

krea-2-medium, krea-2-large, Cosmos3-Super-Text2Image, and Cosmos3-Super-Text2Image (Agentic) has been added to the Text-to-Image Arena leaderboard.

mistral-medium-3.5 has been added to the Code Arena leaderboard.

The Agent Arena leaderboard is now live. It ranks models on real-world agentic evals at scale, measuring behavioral signals like file downloads, disapproval events, retries, and steerability rather than static benchmark scores or preference votes alone. Check out the Agent Arena blog post to learn more about the methodology.

nvidia-nemotron-3-ultra-550b-a55b-nvfp4 has been added to the Text-to-Image Arena leaderboard.

mistral-medium-3.5 has been added to the Text Arena and Vision Arena leaderboards.

ideogram-4.0-quality has been added to the Text-to-Image Arena leaderboard.

reve-2.0 has been added to the Text-to-Image Arena and Image Edit Arena leaderboard.

mai-image-2.5 has been added to the Image Edit Arena leaderboard.

wan2.7-t2v has been added to the Text-to-Video Arena leaderboard.

mai-image-2.5-preview has been added to the Text-to-Image Arena leaderboard.

qwen3.7-max-20260517 has been added to the Code Arena leaderboard.

recraft-v4.1-pro and recraft-v4.1-utility-pro has been added to the Arena Text-to-Image Arena leaderboard.

hidream-o1-image has been added to the Text-to-Image Arena leaderboard.

grok-imagine-image-quality (20260519) has been added to the Image Edit Arena leaderboard.

gemini-3.5-flash has been added to Text and Code leaderboards.

qwen3.7-max-preview has been added to the Text Arena and Vision Arena leaderboards.

granite-4.1-8b has been added to the Text Arena and Code Arena leaderboards.

trinity-large-thinking has been added to the Text Arena leaderboard.

gpt-5.5-xhigh (codex-harness) has been added to the Code Arena leaderboard.

Votes collected from Battles in Direct now count toward leaderboards.

Since March 2026, we've been running an experiment where 10% of direct-chat sessions on Arena are converted into battles between two randomly sampled models. Starting today, votes collected this way will be included in leaderboards. Over the next month, we'll also gradually backfill Battles in Direct votes collected from March through May, so models active during that time period may see vote counts increase and scores shift slightly.

This change meaningfully increases daily vote volume, which tightens confidence intervals and stabilizes ranks faster. The distribution of prompts also shifts: direct battles arrive with prior conversational context and skew toward longer queries, harder prompts, coding, and instruction following. Direct battles where the user votes skip are not used, so every direct-battle vote is a decisive A-or-B preference.

We observed two new biases in the Battles in Direct voting data and corrected for them in the Bradley-Terry fit for the text, vision, search, and document arenas. The first is a position bias favoring Model A (the model on the left); the second is an advantage given to models that share an organization with the prior turns of context. To correct each bias, we added a corresponding feature to the model: is_direct_battle and same_org_indicator, respectively. The model fitting learns coefficients for these features that absorb the biases.

gpt-5.5-instant has been added to the Text Arena, Vision Arena, and Document Arena leaderboard.

ernie-5.1 has been added to Search Arena leaderboard.

gemma-4-31b and gemma-4-26b-a4b has been added to the Vision Arena leaderboard.

qwen3.6-max-preview and hunyuan-hy3-preview has been added to Code Arena leaderboard.

grok-imagine-image-quality has been added to the Text-to-Image Arena leaderboard and Image Edit Arena leaderboard.

gpt-5.5-instant has been added to the Vision Arena, Text Arena and Document Arena leaderboards.

uni-1.1-max and uni-1.1 has been added to the Text-to-Image Arena leaderboard and Image Edit Arena leaderboard.

gpt-image-2 (medium) has been updated on the Image Arena leaderboards. The updated score reflects performance across Arena's full user base. As public usage scales, scores stabilize to reflect a larger sample of real-world use.

gemma-4-26b-a4b & gemma-4-31b have been added to the Code Arena leaderboard.

mimo-v2-omni has been added to the Vision Arena leaderboard.

grok-4.3 has been added to the Text Arena, Search Arena, Code Arena and Vision Arena leaderboards.

trinity-large-thinking has been added to the Text Arena and Code Arena leaderboards.

qwen3.6-max-preview has been added to the Text Arena leaderboard.

hunyuan-hy3-preview has been added to the Text Arena leaderboard.

glm-5v-turbo has been added to the Vision Arena leaderboard.

ernie-5.1-preview has been added to the Text Arena leaderboard.

gpt-5.5-high has been added to Code, Text, Expert, Search, Document, and Vision leaderboards.
claude-opus-4-7 has been added to the Search leaderboard.

qwen-image-2.0-pro-2026-04-22 has been added to the Text-to-Image Arena and Image Edit Arena leaderboards.

deepseek-v4-pro, deepseek-v4-pro-thinking, and deepseek-v4-flash-thinking has been added to the Text Arena and Code Arena leaderboards.

kimi-k2.6 has been added to Code Arena, Vision Arena, Document Arena, and Text Arena leaderboards.

muse-spark has been added to Code Arena leaderboard.

claude-opus-4-7-thinking has been added to the Code Arena leaderboard.

dreamina-seedance-2.0-720p has been added to the Video Edit Arena leaderboard.

gpt-image-2 (medium) has been added to the Text-to-Image Arena and Image Edit Arena leaderboard.

claude-opus-4-6-thinking and claude-opus-4-7 have been added to the Vision Arena and Document Arena leaderboards.

qwen3.6-plus has been added to the Text Arena and Code Arena leaderboards.

kling-image-o1 has been added to the Image Edit Arena leaderboard.

claude-opus-4-6-thinking and claude-opus-4-7 have been added to the Text Arena and Code Arena WebDev Arena leaderboards.

The Image to WebDev leaderboard is now live.

happyhorse-1.0 is live on the Video Edit Arena leaderboard.

claude-opus-4-6-thinking, kimi-k2.5-thinking, gemma-4-31b and grok-4.20-beta-0309-reasoning have been added to the Document Arena leaderboard.

trinity-large has been renamed to trinity-large-preview for clarity on the Text Arena leaderboard.

wan2.7-image and wan2.7-image-pro have been added to the Text-to-Image Arena and Image Edit Arena leaderboards.

muse-spark has been added to the Text Arena leaderboard.

glm-5.1 has been added to the Code Arena leaderboard.

glm-5.1 has been added to the Text Arena leaderboard.

dola-seed-2.0-pro has been added to the Text Arena leaderboard.

qwen3.6-plus-preview has been added to the Code Arena leaderboard.

gpt-5.4-search has been added to the Search Arena leaderboard.

gpt-5.4-mini-high has been added to the Code (WebDev) Arena leaderboard.

longcat-flash-chat has been added to the Text Arena leaderboard.

gemma-4-31b and gemma-4-26b-a4b have been added to the Text Arena leaderboard.

claude-opus-4-6, claude-opus-4-6-thinking and claude-sonnet-4-6 have been added to the Vision Arena leaderboard.

grok-4.20-multi-agent-beta-0309 is now on the Text Arena, Vision Arena, and Search Arena leaderboards.

gemini-3-flash-grounding has been added to the Search Arena leaderboard.

mercury-2 has been added to the Text Arena and Code Area leaderboards.

runway-gen4 has been added to the Text-to-Image Arena leaderboard.

gpt-5.4-nano-high and gpt-5.4-mini-high have been added to the Text Arena leaderboard.

mimo-v2-pro has been added to the Text Arena and Code Arena leaderboards.

qwen3.5-max-preview has been added to the Text Arena leaderboard.

mai-image-2 has been added to the Text-to-Image Arena leaderboard.

grok-4.20-beta-0309-reasoning has been added to the Vision Arena leaderboard.

minimax-m2.7 has been added to the Text Arena and Code Arena leaderboards.

grok-4.20-beta-0309-reasoning has been added to the Text Arena and Code Arena
leaderboards.

amazon-nova-experimental-chat-26-02-10 has been added to the Text Arena leaderboard.

gpt-5.4-high (codex-harness), gpt-5.4-medium (codex-harness), and gpt-5.3-codex (codex-harness) have been added to the Code Arena leaderboards.

nvidia-nemotron-3-super-120b-a12b has been added to the Text Arena leaderboard.

gpt-5.4 is on the Text Arena and Document Arena leaderboards.

The Video Arena leaderboards will reflect a single consolidated vote category going forward.

Previously, prompts and generations were visible to a broader Discord community, allowing non-authors to vote. After the migration to arena.ai, voting is now limited to the prompt author only. We are discontinuing the separate “Author Vote” category on the Video Arena leaderboards as all votes now originate from prompt authors.

pixverse-v5.6 has been added to the Text-to-Video Arena and Image-to-Video Arena leaderboards.

gpt-5.4-high and gpt-5.4 are on the Text Arena leaderboard.

qwen3.5-flash has been added to the Text Arena and Code Arena leaderboards.

gemini-3.1-flash-lite-preview has been added to the Text Arena and Code Arena leaderboards.

qwen3.5-122b-a10b, qwen3.5-35b-a3b and qwen3.5-27b have been added to the Text Arena and Code Arena leaderboards.

The Document Arena leaderboard has been added. The Document Arena displays model rankings based on side-by-side evaluations of real-world document reasoning performance across user-uploaded PDF files.

runway-gen-4.5 has been added to the Text-to-Video Arena leaderboard.

An older version of grok-imagine-image has been renamed to grok-imagine-image (20260207) in Image Edit Arena to reflect the dated snapshot. The current default model now listed as grok-imagine-image represents the latest version.

p-video has been added to the Text-to-Video Arena and Image-to-Video Arena leaderboards.

gemini-3.1-flash-image-preview (nano-banana-2) [web-search] has been added to the Text-to-Image Arena and Image Edit Arena leaderboards.

claude-opus-4-6-search has been added to the Search Arena leaderboard.

kling-v3-pro has been added to the Image-to-Video Arena leaderboard.

Code Arena WebDev Leaderboard Categorization
The Code Arena WebDev leaderboard is now segmented into two distinct categories to reflect different generation environments and capability surfaces:

HTML: ranks standalone HTML/CSS/JS generation within a single document scope.React: ranks multi-file application generation, including component structure, routing, state coordination, and cross-file consistency.

This separation provides clearer visibility into model performance across simple document-level outputs vs. structured application-level builds.

gpt-5.2-chat-latest-20260210 has been added to the Vision Arena leaderboard.

grok-4.20-beta1 has been added to the Text Arena and Search Arena leaderboards.

seedream-5.0-lite has been added to the Text-to-Image Arena and Image Edit Arena leaderboards.

qwen3.5-397b-a17b has been added to the Code Arena leaderboard.

wan2.6-i2v and wan2.6-t2v have been added to the Video Arena leaderboard.

amazon-nova-experimental-chat-26-01-10 has been added to the Text Arena leaderboard.

trinity-large has been added to the Text Arena leaderboard.

reve-v1.5 has been added to the Text-to-Image Arena leaderboard.

gpt-5.2-chat-latest-20260210 has been added to the Text Arena leaderboard.

claude-sonnet-4-6 has been added to the Text Arena and Code Arena leaderboard.

qwen3.5-397b-a17b has been added to the Vision Arena leaderboard.

recraft-v4 has been added to the Text-to-Image Arena leaderboard.

molmo-2-8b has been added to the Vision Arena leaderboard.

gemini-3.1-pro-preview has been added to the Text Arena, Vision Arena and Code Arena leaderboards.

mimo-v2-flash (thinking) has been added to the Text Arena and Code Arena leaderboards.

minimax-m2.5 has been added to the Text Arena and Code Arena leaderboards.

dola-seed-2.0-preview has been added to the Text Arena and Vision Arena leaderboards.

glm-5 has been added to the Code Arena leaderboard.

glm-5 has been added to the Text Arena leaderboard.

veo-3.1-fast-audio-1080p and veo-3.1-audio-1080p have been added to the Text-to-Video Arena and Image-to-Video Arena leaderboards.

step-3.5-flash has been added to the Text Arena leaderboard.

claude-opus-4-6-thinking has been added to the Text Arena and Code Arena leaderboards.

We’ve updated the Text-to-Image Arena with:

Prompt Categories: category-specific leaderboards for clearer domain-level performance Quality Filtering: reducing noisy or underspecified prompts for more reliable rankings

Older categories for user-generated vs. pre-generated prompts have been deprecated.

grok-imagine-image-pro and grok-imagine-image have been added to the Text-to-Image Arena and Image Edit Arena leaderboards.

claude-opus-4-6 has been added to the Text Arena and Code Arena leaderboards.

kimi-k2.5-instant has been added to the Text Arena, Vision Arena and Code Arena leaderboards.

vidu-q3-pro is on the Image-to-Video Arena leaderboard

grok-imagine-video-720p is on the Image-to-Video Arena leaderboard

kimi-k2.5-thinking is on the Code Arena WebDev leaderboard.

glm-4.7-flash has been added to the Text Arena leaderboard.

devstral-2 has been added to the Code Arena leaderboard.

kling-o1-pro ltx-2-19b has been added to the Text-to-Video Arena leaderboard.

ltx-2-19b has been added to the Image-to-Video Arena leaderboard.

p-image-edit wan2.6-image has been added to the Image Edit Arena leaderboard.

p-image wan2.6-t2i has been added to the Text-to-Image Arena leaderboard.

gemini-3-flash-grounding claude-sonnet-4-5-search claude-opus-4-5-search
gpt-5.2-search-non-reasoning has been added to the Search Arena leaderboard.

kimi-k2.5-thinking has been added to the Vision Arena leaderboard.

grok-imagine-video-480p is the Text-to-Video Arena and Image-to-Video Arena leaderboards.

kimi-k2.5-thinking is on the Text Arena Leaderboard.

hunyuan-image-3.0-instruct is on the Image Edit Arena leaderboard

We've added Multi-Image Edit as new category to the Image Edit leaderboard which consists of votes where multiple images were passed into the models. The previous overall leaderboard has been renamed to Single-Image Edit.

gpt-5.2-codex has been added to the Code Arena leaderboard.

Video Arena leaderboards now include votes collected from both the lmarena.ai website and our Discord server. Read our blog for more details.

olmo-3.1-32b-instruct and olmo-3.1-32b-think have been added to the Text Arena leaderboard.

glm-image was added to the Text-to-Image Arena leaderboard.

wan2.5-i2i-preview has been added to the Image Edit Arena leaderboard.

glm-4.6v has been added to the Vision Arena leaderboard.

gemini-3-flash (thinking-minimal) has been updated on the Vision Arena leaderboard.

flux-2-klein-9b & flux-2-klein-4b have been added to the Text-to-Image Arena and Image Edit Arena leaderboards.

z-image-turbo has been added to the Text-to-Image Arena leaderboard.

ernie-5.0-0110 has been added to the Text Arena leaderboard.

We’ve completed a major improvement to our data pipeline that resolves several known issues and applies data filtering more consistently:

The validation process led to minimal adjustments in leaderboard rankings. Models and leaderboards with fewer votes may see larger score fluctuations.

Here's a summary of the changes in the new pipeline:

Vote filters, such as identity leak detection and data quality filtering, are now applied more consistently across all votes.Vote de-duplication is now enabled in text-to-image and video arenas.

hunyuan-video-1.5 has been added to the Text-to-Video Arena and Image-to-Video Arena leaderboards.

ernie-5.0-preview-1220 has been added to the Vision Arena leaderboard.

seedance-v1.5-pro has been added to the Text-to-Video Arena and Image-to-Video Arena leaderboards.

minimax-m2.1-preview and glm-4.7 have been added to the Text Arena leaderboard.

minimax-m2.1-preview has been added to the WebDev Arena leaderboard.

mimo-v2-flash (non-thinking) has been added to the Text Arena and WebDev Arena leaderboards.

ernie-5.0-preview-1203 has been added to the Text Arena leaderboard.

glm-4.7 has been added to the WebDev Arena leaderboard powered by the new Code Arena.

amazon-nova-experimental-chat-11-10 has been added to the Text Arena leaderboard.

gpt-5.2 has been added to the Text Arena leaderboard.

grok-4-1-fast-search and gpt-5.2-search are on the Search Arena leaderboard.

reve-v1.1 and reve-v1.1-fast are on the Image Edit Arena leaderboard.

gemini-3-flash and gemini-3-flash (thinking-minimal) have been added to the Text Arena, Vision Arena and WebDev Arena leaderboards.

flux-2-max is on the Text-to-Image Arena and Image Edit Arena leaderboards.

gpt-image-1.5 is on the Text-to-Image Arena and Image Edit Arena leaderboards.

chatgpt-image-latest (20251216) has been added to the Image Edit Arena leaderboard.

gpt-5.2-high has been added to the Text Arena leaderboard.

ibm-granite-h-small has been added to the Text Arena leaderboard.

nvidia-nemotron-3-nano-30b-a3b-bf16 has been added to the Text Arena leaderboard

kandinsky-5.0-t2v-lite and kandinsky-5.0-t2v-pro have been added to the Text-to-Video Arena leaderboard.

kling-2.6-pro has been added to the Text-to-Video Arena and Image-to-Video Arena leaderboards.

flux-2-dev has been added to the Text-to-Image Arena and Image Edit Arena leaderboards.

gpt-5.2 and gpt-5.2-high have been added to the WebDev leaderboard powered by Code Arena.

mistral-large-3 has been added to the WebDev leaderboard powered by Code Arena.

intellect-3 has been added to the Text Arena leaderboard.

ernie-5.0-preview-1103 and nova-2-lite have been added to the Text Arena leaderboard.

grok-4-fast has been renamed to grok-4-fast-chat to better reflect the specific model variant. Additionally, olmo-3-32b-think has been added to the Text Arena leaderboard.

grok-4-fast-reasoning has been added to the Text Arena leaderboard.

devstral-medium-2507 has been added to the new WebDev leaderboard (powered by Code Arena).

gpt-5.1-high and gpt-5.1 has been added to the Vision Arena leaderboard.

deepseek-v3.2 and deepseek-v3.2-thinking have been added to the Text Arena leaderboard.

seedream-4.5 has been added to the Image Edit Arena and Text-to-Image Arena leaderboards

gpt-5.1-search and gemini-3-pro-grounding have been added to the Search Arena leaderboard.

mistral-large-3 has been added to the Text Arena leaderboard.

wan2.5-t2v-preview has been added to the Text-to-Video Arena leaderboard.

gemini-3-pro-image-preview-2k (nano-banana-pro) has been added to the Text-to-Image Arena and Image Edit Arena leaderboards.

KAT-Coder-Pro-V1 has been added to the new WebDev Arena leaderboard.

flux-2-flex and flux-2-pro have been added to the Text-to-Image Arena and Image Edit Arena leaderboards.

claude-opus-4-5-20251101 and claude-opus-4-5-20251101-thinking-32k have been added to the Text Arena and WebDev Arena leaderboards.

ernie-5.0-preview-1120 has been added to the Vision Arena leaderboard.

gemini-3-pro-image-preview (nano-banana-pro) has been added to the Text-to-Image Arena and Image Edit Arena leaderboards.

Additionally, the following models have been added to the new WebDev leaderboard:

gpt-5.1gpt-5.1-mediumgpt-5.1-codexgpt-5.1-codex-mini

mercury has been added to the Text Arena leaderboard.

cogito v2.1 has been added to the WebDev Arena leaderboard.

gpt-5.1-high and gpt-5.1 have been added to the Text Arena leaderboard.

gemini-3-pro has been added to the Text Arena, Vision Arena and WebDev Arena leaderboards.

grok-4.1-thinking and grok-4.1 have been added to the Text Arena leaderboard.

wan2.5-t2i-preview has been added to the Text-to-Image Arena leaderboard.

wan2.5-i2v-preview has been added to the Image-to-Video Arena leaderboard.

ray-3 has been added to the Text-to-Video Arena and Image-to-Video Arena leaderboards.

vidu-q2-turbo & vidu-q2-pro are now on the Image-to-Video Arena leaderboard.

The WebDev leaderboard is now powered by the Code Arena experience.

amazon-nova-experimental-chat-10-20 has been added to the Text Arena leaderboard.

ernie-5.0-preview-1022 has been added to the Text Arena leaderboard.

reve-edit-fast has been added to the Image Edit Arena leaderboard.

gpt-image-1-mini has been added to the Text-to-Image Arena and Image Edit Arena leaderboards.

Introducing Arena Expert: a new LMArena evaluation framework to identify the toughest, most expert-level prompts from real users, powering a new Expert leaderboard.

We also introduce Occupational Categories that underlie eight new leaderboards:

Software & IT Services Writing, Literature, & LanguageLife, Physical, & Social ScienceEntertainment, Sports, & MediaBusiness, Management, & Financial OpsMathematicalLegal & GovernmentMedicine & Healthcare

Arena Expert aims to sharpen the difficulty level compared to Arena Hard. While Hard includes about a third of all LMArena prompts, Arena Expert includes only 5.5% of all prompts. Expert prompts are identified by their reasoning depth and specificity, producing sharper separations between models. By mapping all Arena prompts across occupational fields, the Occupational Categories system captures the full spectrum of real-world reasoning tasks.

→ Read more on our blog: http://news.lmarena.ai/arena-expert

MiniMax-M2 has been added to the WebDev Arena leaderboard.

Hailuo 2.3 has been added to the Text-to-Video Arena leaderboard.

Hailuo 2.3 has been added to the Image-to-Video Arena leaderboard.

The following models have been added to the WebDev Arena leaderboard:

Claude-Haiku-4-5-20251001Qwen3-235b-a22b-instruct-2507Claude-sonnet-4-5-20250929-thinking-32kGLM-4.6

Additionally, Veo 3.1 variants have been added to the Text-to-Video Arena and Image-to-Video Arena leaderboards.

Claude Haiku 4.5 and Amazon-Nova-Experimental-Chat-10-09 have been added to the Text Arena leaderboard.

We've also refined the logic for our Coding category to improve precision. Prompts that resembled code, but are not coding related (such as markdown) have been removed. The new rule has been applied retroactively on data, so while the Coding category is now smaller, it’s more accurate.

Sora 2 and Sora 2 Pro has been added to the Text-to-Video Arena leaderboard.

MAI-1-Image has been added to the Text-to-Image Arena leaderboard.

Kling 2.5 Turbo 1080p has been added to the Text-to-Video Arena and Image-to-Video Arena leaderboards.

DeepSeek-V3.2-Exp and the thinking variant have been added to the Text Arena leaderboard.

Ling Flash 2.0 and Ring Flash 2.0 have been added to the Text Arena leaderboard.

Hunyuan Vision 1.5 Thinking has been added to the Vision Arena leaderboard.

Hunyuan Image 3.0 has been added to the Text-to-Image Arena leaderboard.

We added a filter to remove rows where a model battles against itself. This happens very rarely, in instances where we briefly serve the same model from two different API endpoints at the same time.

Claude Sonnet 4.5 Thinking 32k and GLM 4.6 have been added to the Text Arena leaderboard.

Claude Sonnet 4.5 has been added to the Text and Web Dev Arena leaderboards.

Reve V1 has been added to the Image Edit Arena leaderboard.

The following models have been added to the Text leaderboard:

deepseek-v3.1-terminusdeepseek-v3.1-terminus-thinkinggemini-2.5-flash-lite-preview-09-2025gemini-2.5-flash-preview-09-2025qwen3-max-2025-09-23qwen3-vl-235b-a22b-instructqwen3-vl-235b-a22b-thinking

New model announcement:
Seedream-4-2k has been added to the Text-to-Image and Image Edit leaderboards.

Note that Seedream-4-high-res-fal and Seedream-4-fal are variants run on the fal.ai platform. Due to differences in hosting, they are named separately as distinct models. Seedream-4-2k is the official endpoint provided by ByteDance.

New model announcements:
Grok-4-fast has been added to the Text leaderboard.
Grok-4-fast-search has been added to the Search leaderboard.

We have added a new "preliminary" tag to the leaderboard. If a model is tested anonymously and is subsequently released publicly, we mark its score as "preliminary" until enough fresh votes have been collected after the model’s public release. The tag indicates that scores may shift as community prompts and votes evolve after public launch. See our leaderboard policy for more details about evaluating models.

New model announcements:
Longcat-Flash-Chat, Qwen 3 Next-80b-a3b-instruct and Qwen 3 Next-80b-a3b-thinking have been added to the Text leaderboards.

We've updated our data pipeline to add a filter which removes votes from users who exhibit statistically anomalous voting patterns. This improves the quality of the rankings by removing votes from users whose votes are arbitrary, rather than based on the quality of the responses.

New model announcement:
Seedream 4 High Res has been added to the Text-to-Image and Image Edit leaderboards.

Deepseek v3.1 & Deepseek v3.1-thinking have been added to the WebDev leaderboard.

New model announcement:
Seedream 4 has been added to the Text-to-Image and Image Edit leaderboards.

New model announcements:
Qwen3-max-preview and Kimi-K2-0905-preview have been added to the Text Leaderboard.

We also enabled filtering for the mistaken image generation and image edit requests for text arena.

Due to the increase in image generation traffic brought by nano-banana, we noticed there were prompts in our vision arena data which were asking for image generation but did not have image output enabled. We've implemented an LLM based rule to filter these rows out from the vision leaderboard calculation.

New model announcements:
Diffbot-small-xl has been added to the Search Leaderboard
Qwen-3-Image-Prompt-Extend has been added to the Text-to-Image Leaderboard.

The following have been added to the Text Leaderboard:

DeepSeek V3.1 (thinking and non-thinking)Hunyuan-t1-20250711

New model announcement: MAI-1-preview has been added to the Text Leaderboard.

New model announcement: Gemini-2.5-Flash-Image-Preview ("nano-banana") has been added to the Text-to-Image and Image Edit leaderboards.

GPT-5 and Claude Opus 4.1 have been added to the Search Leaderboard.

We also noticed that the effects of response style are different for search than they are for ordinary chat so we'll be defaulting this leaderboard to ordinary Bradley-Terry while we study search specific style effects.

New model announcements
The following have been added to the Text and Vision leaderboards:

Qwen-vl-max-2025Step 3 Mistral-Medium-2508 GLM-4.5V

Lucid Origin has been added to the Text-to-Image leaderboard.
Ray 2 has been added to the Text-to-Video and Image-to-Video leaderboards
Runway Gen 4 Turbo has been added to the Image-to-Video leaderboard

New model announcement: Qwen-Image-Edit has been added to the Image Edit leaderboard.

New model announcement: Claude Opus 4.1 Thinking as been added to the Text and WebDev Arena leaderboards. Sora has been added to the Text-to-Image leaderboard.

New model announcement: three additional gpt-5 models are on the Text Leaderboard. These three reasoning models were configured with the highest reasoning setting.

gpt-5-chatgpt-5-mini-highgpt-5-nano-high

New model announcement: gpt-0ss-120b and gpt-oss-20b have been added to the Text and WebDev leaderboards. Hailuo 2 Pro versions have been added to the Text-to-Video and Image-to-Video leaderboards.

New model announcement: Claude Opus 4.1 is on Text and WebDev leaderboards.

New model announcement: GPT-5 is on the Text, WebDev, and Vision leaderboards.

Big update: three new leaderboards!
Check out the Search, Text-to-Video, and Image-to-Video leaderboards.

Since the video arenas are used through our discord server, there are a few considerations we made for handling the votes. Currently, the model identities are revealed after two votes are cast on a generation. For fairness, we only use the votes cast before the model names are revealed when constructing the leaderboard.

The video arenas are also the first arenas where multiple votes can be cast on the same pair of generations, so unlike the other arenas, some votes are cast by people other than the author of the prompt. The overall leaderboard is computed using all anonymous votes, and we've created a new category which uses only the votes cast by the prompt's author.

We have updated the "total votes" counts to include battles involving models not included on the leaderboard (for example, due to being deprecated). The battles between these models and models present on the leaderboard are informative of model strengths, even if the former are not shown, and thus help reduce the variance of the scores. The leaderboard computation is not changing; you will only see a change in the vote counts.

New model announcements: GLM-4.5 and GLM-4.5 Air are now on the Text leaderboard.

New model announcement: Qwen3-235b-a22b-instruct-2507 is now on the Text leaderboard.

New model announcements: Qwen3-Coder and Kimi K2 are now on the WebDev leaderboard.

New model announcements! Imagen 4 Generate Preview 06-06 v2 and Imagen 4 Ultra Generate Preview 06-06 v2 are now on the Text-to-Image leaderboard.

We made improvements to the methodology behind Arena scores!

Our leaderboard uses confidence intervals to represent the uncertainty and variability inherent in estimating scores based on human voting. Up until now, our confidence intervals have been computed via bootstrapping, a process where we resample the dataset many times, calculate scores on each, and then look at the distribution of the scores over all the runs. While statistically sound, this is computationally intensive, especially with a large number of battles. We’ve recently moved to a new method based on the Central Limit Theorem (CLT) for M-estimators, which allows us to compute confidence intervals via a closed form equation.

We validated this approach by comparing the confidence intervals computed via bootstrapping, with those using the CLT and confirmed that the results are in very close parity (with a fraction of the compute cost and time!). See below:

On LMArena, every vote counts towards producing the leaderboard, but what happens when some models appear more than others? When new models are released, they inevitably have fewer votes than those which have been in use for a while, and when models are deprecated it becomes impossible to collect more votes for them.

To counteract this imbalance and produce a leaderboard that is fair and equally representative of all models, we use an improved reweighting scheme that reweights battles inversely proportionally to how frequently they appear.

The CLT confidence intervals above take these weights into account. Reweighting increases the variance of Arena scores, and we observe wider confidence intervals as a result. This mean that the new rankings will have more ties due to overlapping confidence intervals, especially when there are fewer votes per model like in the vision arena.

New model announcements! Kimi K2 is on the Text leaderboard, Seededit 3 is on the Image Edit leaderboard, and Grok 4 is on the Vision leaderboard.

We're announcing four new models! Grok 4 is on the Text and WebDev leaderboards, Claude Opus 4 Thinking is on the Text leaderboard, Claude Sonnet 4 Thinking is on the Text leaderboard, and Seedream 3 is on the Text-to-Image leaderboard.

We made improvements to our data processing—in particular, we strengthened our deduplication and identity leak detection pipelines.

Deduplication aims to reduce the impact of over-represented or repetitive conversations using a hash-based approach. We count how many times each unique prompt appears. Prompts in the top 0.5% percentile are considered high-frequency. For these high-frequency prompts, we keep only a limited number of samples and discard the rest. Deduplication filters out around 10% of all submitted votes.

Identity leak detection filters out user prompts whose intent is to reveal model information. We first use an LLM classifier to label conversations as identity_leak if they include user prompts that directly attempt to extract or expose model details (e.g., "What is your name?"). We filter out conversations labeled as identity_leak, as well as associated conversations. Less than 4% of all votes are labeled as identity_leak.

We're excited to continue iterating and improving our data processing pipeline!