OverviewAll LeaderboardsMethodology
New Chat

Text Arena

Which model is the best at everyday chat?

Nov 20, 2026
1,981,372 votes
421 models

Text Arena

Frontier
Gemini 4 Carbon (High)1,568 rating. 9 points above rank 2.
Daily Driver
MiMo-V2.6-ProNear-frontier performance at 1/10th the price.
Efficient
DeepSeek-V4-FlashSolid performance at 1/100th the price.
1,500
  1. 1,568
    Gemini 4 CarbonHigh
  2. 1,559
    Gemini 4 NeonHigh
  3. 1,552
    Gemini 4 ArgonHigh
  4. 1,551
    Anthropic
    Claude Fable 5High
  5. 1,551
    Anthropic
    Claude Opus 4.7High
  6. 1,550
    Meta
    Muse WonderMax
  7. 1,548
    Anthropic
    Claude Opus 5.5High
  8. 1,548
    GPT-6 AstraMax
  9. 1,547
    Anthropic
    Claude Opus 4.6High
  10. 1,547
    Anthropic
    Claude Opus 4.6
  11. 1,546
    Anthropic
    Claude Opus 4.7
  12. 1,544
    GPT-6.1 SolMax
  13. 1,541
    GPT-6.1 TerraMax
  14. 1,540
    Meta
    Muse Spark 1.2xHigh
  15. 1,539
    MiMo-V2.6-Pro
Model RankingScoreCost per task (P50)Blended price $/M (3:1)
  1. 1Gemini 4 Carbon (High)1,568$0.05$8
  2. 2Gemini 4 Neon (High)1,559$0.08$6
  3. 3Gemini 4 Argon (High)1,552$0.03$8
  4. 4AnthropicClaude Fable 5 (High)1,551$0.14$40
  5. 5AnthropicClaude Opus 4.7 (High)1,551$0.06$20
  6. 6MetaMuse Wonder (Max)1,550$0.10$16
  7. 7AnthropicClaude Opus 5.5 (High)1,548$0.08$16
  8. 8GPT-6 Astra (Max)1,548$0.24N/A
  9. 9AnthropicClaude Opus 4.6 (High)1,547$0.07$20
  10. 10AnthropicClaude Opus 4.61,547$0.06$20
  11. 11AnthropicClaude Opus 4.71,546$0.06$20
  12. 12GPT-6.1 Sol (Max)1,544$0.04$8
  13. 13GPT-6.1 Terra (Max)1,541$0.04$4
  14. 14MetaMuse Spark 1.2 (xHigh)1,540$0.01$3.50
  15. 15MiMo-V2.6-Pro1,539$0.01$0.76

Pareto frontier

Best score for the cost
1,3501,4001,4501,5001,550
Meta
$0.001$0.01$0.10

Median cost per task

Frontier
Gemini 4 Carbon (High)1,568 rating. 9 points above rank 2.
Daily Driver
MiMo-V2.6-ProNear-frontier performance at 1/10th the price.
Efficient
DeepSeek-V4-FlashSolid performance at 1/100th the price.
On the frontierScore$/task
  1. Gemini 4 Carbon (High)1,568$0.05
  2. Gemini 4 Argon (High)1,552$0.03
  3. MetaMuse Spark 1.2 (xHigh)1,540$0.01
  4. MiMo-V2.6-Pro1,539$0.01
  5. GLM-5.3-Flash1,526$0.01
  6. MiMo-V2.5-Pro1,520$0.01
  7. MiMo-V2.6-Flash1,510$0.01
  8. DeepSeek-V4-Flash1,484$0.01
  9. Granite 4.1 8B1,354$0.01
310 models not plotted

These models are on the leaderboard but do not appear on the Pareto chart because they have insufficient cost data. The numbers beside their names show their leaderboard ranks.

  • 24Claude Opus 4.5 (High, 32K, 20251101)
  • 26Muse Spark
  • 37Claude Opus 4.5 (20251101)
  • 44Claude Sonnet 4.5 (High, 32K, 20250929)
  • 48Gemini 3 Pro
  • 58Claude Sonnet 4.5 (20250929)
  • 62Claude Opus 4.1 (Thinking 16K, 20250805)
  • 64Qwen3.6-Max-Preview
  • 73Gemini 3 Flash
  • 74Beam 1.0 501B A23B
  • 75Kimi K2.5 (Instant)
  • 76Claude Opus 4.1 (20250805)
  • 83Gemma 4 31B
  • 87LongCat-Flash-Chat Exp (2602)
  • 89Grok 4.1 (Thinking)
  • 90GLM-5
  • 91Claude Opus 4 (Thinking 16K, 20250514)
  • 97Grok 4.1
  • 99GPT-5.1 (High)
  • 104ERNIE 5.0 (0110)
  • 105GPT-5.2 (High)
  • 110Kimi K2 Thinking Turbo
  • 111amazon-nova-experimental-chat (26-02-10)
  • 114GLM-4.7
  • 116Gemma 4 26B A4B
  • 119amazon-nova-experimental-chat (26-01-10)
  • 120Muse Glimmer
  • 121Qwen3-Max-Preview
  • 125DeepSeek-V3.2 (Thinking)
  • 126GPT-5.1
  • 127DeepSeek-V3.2-Exp (Thinking)
  • 128Claude Sonnet 4 (Thinking 32K, 20250514)
  • 129NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4)
  • 130Qwen3-Max (2025-09-23)
  • 132Qwen3-235B-A22B-Instruct (2507)
  • 133LongCat-Flash-Chat
  • 134GPT-5 (High)
  • 136ERNIE-5.0-Preview (1203)
  • 137DeepSeek-V3.2
  • 138Kimi K2 Preview (0905)
  • 139DeepSeek-V3.2-Exp
  • 140ChatGPT-4o Latest (20250326)
  • 141Claude Opus 4 (20250514)
  • 142Gemini 2.5 Pro
  • 143DeepSeek-R1 (0528)
  • 144Qwen3-VL-235B-A22B-Instruct
  • 145GPT-5 Chat
  • 146Grok 4.1 Fast (Reasoning)
  • 148o3 (2025-04-16)
  • 149NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
  • 150DeepSeek-V3.1-Terminus (Thinking)
  • 152Kimi K2 Preview (0711)
  • 154GLM-4.6
  • 155GPT-4.5 Preview (2025-02-27)
  • 157Grok 4 Fast (Non-Reasoning)
  • 158Qwen3-Coder-480B-A35B-Instruct
  • 159GPT-4.1 (2025-04-14)
  • 160DeepSeek-V3.1 (Thinking)
  • 161GLM-4.5
  • 162Mistral Medium 3.1 (2508)
  • 164Claude 3.7 Sonnet (Thinking 32K, 20250219)
  • 165Qwen3-VL-235B-A22B-Thinking
  • 167Claude Sonnet 4 (20250514)
  • 169DeepSeek-V3.1
  • 170MiMo-V2-Flash (Non-Thinking)
  • 172Qwen3-235B-A22B (Non-Thinking)
  • 173Qwen3-Next-80B-A3B-Instruct
  • 174DeepSeek-R1
  • 176Grok 3 Preview (02-24)
  • 177Qwen3-235B-A22B-Thinking (2507)
  • 178DeepSeek-V3.1-Terminus
  • 179Grok 4 Fast (Reasoning)
  • 180Qwen3-30B-A3B-Instruct (2507)
  • 181MiniMax-M2.1 Preview
  • 182Hunyuan Vision 1.5 Thinking
  • 183Claude 3.5 Sonnet (20241022)
  • 184amazon-nova-experimental-chat (12-10)
  • 186Grok 4 (0709)
  • 188o3-mini (High)
  • 189o4-mini (2025-04-16)
  • 190GPT-4.1 mini (2025-04-14)
  • 191o1 (2024-12-17)
  • 192GPT-5 mini (High)
  • 193Mistral Medium 3 (2505)
  • 194MiMo-V2-Flash (Thinking)
  • 195Claude 3.7 Sonnet (20250219)
  • 196Qwen3-235B-A22B
  • 197ERNIE-5.0-Preview (1022)
  • 198NVIDIA-Nemotron-3.5-Lightning-30B-A3B (NVFP4)
  • 199DeepSeek-V3 (0324)
  • 200Gemini 2.5 Flash Preview (09-2025)
  • 201GLM-4.5-Air
  • 202Gemini 2.5 Flash
  • 203GLM-4.7-Flash
  • 204Qwen3-Next-80B-A3B-Thinking
  • 205amazon-nova-experimental-chat (11-10)
  • 206GLM-4.6V
  • 207o3-mini
  • 208MiniMax-M1
  • 209o1-preview
  • 210INTELLECT-3
  • 212Mistral Small 3.2 (2506)
  • 213amazon-nova-experimental-chat (10-20)
  • 214Step-3
  • 215Ling-flash-2.0
  • 216NVIDIA-Nemotron-3-Super-120B-A12B
  • 217Qwen3-32B
  • 218Llama 3.3 Nemotron Super 49B v1.5
  • 219GLM-4.5V
  • 220Qwen2.5-Max
  • 221Hunyuan T1 (20250711)
  • 222Claude 3.5 Sonnet (20240620)
  • 223Hunyuan TurboS (20250226)
  • 224Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
  • 225Granite 4.2 30B
  • 226Hunyuan TurboS (20250416)
  • 227Amazon Nova 2 Lite
  • 228Mercury 2
  • 229Grok 3 Mini (High)
  • 230amazon-nova-experimental-chat (10-09)
  • 231Llama 3.1 Nemotron Ultra 253B v1
  • 232Ring-flash-2.0
  • 233gpt-oss-120b
  • 234Command A (03-2025)
  • 235Magistral Medium (2506)
  • 236DeepSeek-V3
  • 237Grok 3 Mini Beta
  • 238GPT-5 nano (High)
  • 239o1-mini
  • 240Claude 3.5 Haiku (20241022)
  • 241Qwen3-30B-A3B
  • 242MiniMax-M2
  • 243Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
  • 244QwQ-32B
  • 245Olmo 3.1 32B Instruct
  • 246Qwen-Plus (0125)
  • 247Llama 3.1 405B Instruct (BF16)
  • 248Granite 4.2 3B
  • 249DeepSeek-V2.5 (1210)
  • 250GPT-4.1 nano (2025-04-14)
  • 251Llama 4 Maverick 17B 128E Instruct
  • 252Step-2 16K Exp (202412)
  • 253Hunyuan Turbo (0110)
  • 254Llama 3.1 405B Instruct (FP8)
  • 255GPT-4o (2024-05-13)
  • 256Athene V2 Chat
  • 257Yi Lightning
  • 258gpt-oss-20b
  • 259Granite 4.2 8B
  • 260DeepSeek-V2.5
  • 261Hunyuan Large (2025-02-10)
  • 262Mercury
  • 263Gemini 2.0 Flash (001)
  • 264Llama 4 Scout 17B 16E Instruct
  • 265Llama 3.3 Nemotron Super 49B v1
  • 266NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
  • 267Mistral Small 3.1 24B Instruct (2503)
  • 268GPT-4o (2024-08-06)
  • 269Olmo 3 32B Think
  • 270Hunyuan Large Vision
  • 271Gemma 3 27B IT
  • 272Grok 2 (2024-08-13)
  • 273Qwen2.5-Plus (1127)
  • 274Gemini 1.5 Pro (002)
  • 275Claude 3 Opus (20240229)
  • 276Qwen2.5-72B-Instruct
  • 278Mistral Large 2 (2407)
  • 279Qwen-Max (0919)
  • 280GLM-4-Plus
  • 281Step-1o Turbo (202506)
  • 282Athene 70B (0725)
  • 283GPT-4o mini (2024-07-18)
  • 284GPT-4 Turbo (2024-04-09)
  • 285Gemini 1.5 Pro (001)
  • 286Llama 3.3 70B Instruct
  • 287Mistral Large (2411)
  • 288Amazon Nova Pro 1.0
  • 289Gemini 2.0 Flash-Lite Preview (02-05)
  • 290DeepSeek-Coder-V2
  • 291Qwen2.5-Coder-32B-Instruct
  • 292GPT-4 Turbo Preview (1106)
  • 293Olmo 3.1 32B Think
  • 294Gemini Advanced (0514)
  • 295Grok 2 mini (2024-08-13)
  • 296Llama 3.1 70B Instruct
  • 297GPT-4 Turbo Preview (0125)
  • 298Hunyuan Standard (2025-02-10)
  • 299GLM-4-Plus (0111)
  • 300Granite-4.0-H-Small
  • 301GPT-4 (0314)
  • 302Llama 3.1 Nemotron 70B Instruct
  • 303Claude 3 Sonnet (20240229)
  • 304Gemini 1.5 Flash (002)
  • 305Gemma 3 12B IT
  • 306Reka Core (20240904)
  • 307GPT-4 (0613)
  • 308Llama 3.1 Nemotron 51B Instruct
  • 309Mistral Small 24B Instruct (2501)
  • 310Jamba 1.5 Large
  • 311GLM-4 (0520)
  • 312Nemotron-4 340B Instruct
  • 313Gemini 1.5 Flash (001)
  • 314Llama 3.1 Tulu 3 70B
  • 315Gemma 3n E4B IT
  • 316Llama 3 70B Instruct
  • 317Phi-4
  • 318Amazon Nova Lite 1.0
  • 319Gemma 2 27B IT
  • 320Claude 3 Haiku (20240307)
  • 321Hunyuan Standard 256K
  • 322Qwen2-72B-Instruct
  • 323Mistral Large (2402)
  • 324Aya Expanse 32B
  • 325Reka Flash (20240904)
  • 326Amazon Nova Micro 1.0
  • 327Granite 3.1 8B Instruct
  • 328Command R (08-2024)
  • 329Command R+ (08-2024)
  • 330Qwen1.5-110B-Chat
  • 331OLMo 2 32B Instruct (0325)
  • 332Reka Flash 21B (Online, 20240226)
  • 333Mixtral 8x22B Instruct v0.1
  • 334Qwen1.5-72B-Chat
  • 335GPT-3.5 Turbo (0125)
  • 336Ministral 8B (2410)
  • 337Gemma 3 4B IT
  • 338Command R+
  • 339Gemini 1.5 Flash-8B (001)
  • 340Gemma 2 9B IT SimPO
  • 341Gemma 2 9B IT
  • 342Reka Flash 21B (20240226)
  • 343Jamba 1.5 Mini
  • 344Mistral Medium
  • 345Qwen1.5-32B-Chat
  • 346GPT-3.5 Turbo (1106)
  • 347Llama 3.1 8B Instruct
  • 348Aya Expanse 8B
  • 349Llama 3 8B Instruct
  • 350Llama 3.1 Tulu 3 8B
  • 351DBRX Instruct Preview
  • 352Granite 3.1 2B Instruct
  • 353InternLM2.5 20B Chat
  • 354Yi 1.5 34B Chat
  • 355Gemini Pro
  • 356Zephyr ORPO 141B A35B v0.1
  • 357Command R
  • 358Granite 3.0 8B Instruct
  • 359Qwen1.5-14B-Chat
  • 360Mixtral 8x7B Instruct v0.1
  • 361Gemini Pro (Dev API)
  • 362Starling LM 7B Beta
  • 363Phi-3 Medium 4K Instruct
  • 364OpenChat 3.5 (0106)
  • 365Snowflake Arctic Instruct
  • 366DeepSeek LLM 67B Chat
  • 367Gemma 1.1 7B IT
  • 368Tulu 2 DPO 70B
  • 369Qwen1.5-7B-Chat
  • 370Granite 3.0 2B Instruct
  • 371Starling LM 7B Alpha
  • 372Yi 34B Chat
  • 373Phi-3 Small 8K Instruct
  • 374OpenChat 3.5
  • 375Qwen-14B-Chat
  • 376Phi-3 Mini 4K Instruct (June 2024)
  • 377Vicuna 33B
  • 378WizardLM 70B
  • 379Gemma 2 2B IT
  • 380Phi-3 Mini 4K Instruct
  • 381OpenHermes 2.5 Mistral 7B
  • 382Mistral 7B Instruct v0.2
  • 383SOLAR 10.7B Instruct v1.0
  • 384Llama 2 70B Chat
  • 385Llama 3.2 3B Instruct
  • 386Nous Hermes 2 Mixtral 8x7B DPO
  • 387QwQ-32B-Preview
  • 388Gemma 1.1 2B IT
  • 389MPT 30B Chat
  • 390Zephyr 7B Alpha
  • 391Gemma 7B IT
  • 392Vicuna 13B
  • 393Llama 2 13B Chat
  • 394SmolLM2 1.7B Instruct
  • 395Code Llama 34B Instruct
  • 396Phi-3 Mini 128K Instruct
  • 397PaLM 2
  • 398Zephyr 7B Beta
  • 399WizardLM 13B
  • 400Llama 3.2 1B Instruct
  • 401Llama 2 70B SteerLM Chat
  • 402Mistral 7B Instruct
  • 403Gemma 2B IT
  • 404Vicuna 7B
  • 405Qwen1.5-4B-Chat
  • 406StripedHyena Nous 7B
  • 407Guanaco 33B
  • 408OLMo 7B Instruct
  • 409Llama 2 7B Chat
  • 410ChatGLM3 6B
  • 411Koala 13B
  • 412MPT 7B Chat
  • 413RWKV-4 Raven 14B
  • 414OpenAssistant Pythia 12B
  • 415ChatGLM 6B
  • 416ChatGLM2 6B
  • 417StableLM Tuned Alpha 7B
  • 418Alpaca 13B
  • 419Dolly 2.0 12B
  • 420FastChat-T5 3B
  • 421LLaMA 13B

Default Leaderboard Plots

Previous pillar · Agent
Tool Use Index

Which model is the best at using tools?

Next
Search

Which model is the best at online search?

USE CASES

  • Chat with AI
  • Build Apps & Websites
  • Write & Edit Text
  • Search the Web
  • Generate Images
  • Generate Videos
  • Chose any model
  • Compare Models Side by Side

LEADERBOARD RANKINGS

  • Overall
  • Agent
  • Alignment Index
  • Text
  • WebDev
  • Image-to-WebDev
  • Text to Image
  • Image Edit
  • Text to Video
  • Image to Video
  • Video Edit
  • Vision
  • Document
  • Search

COMPANY

  • About Us
  • How It Works
  • Blog
  • Careers
  • Leaderboard Changelog
  • Product Changelog
  • Help Center
  • FAQ

LEGAL

  • Terms
  • Privacy
  • Cookies

FOLLOW

  • X
  • LinkedIn
  • YouTube
  • Discord

© Arena Intelligence