OverviewAll LeaderboardsMethodology
New Chat

Text Arena

Which model is the best at everyday chat?

Nov 18, 2026
617,675 votes
394 models

Text Arena

Frontier
Gemini 4 Argon (High)1,526 rating. 1 point above rank 2.
Daily Driver
GLM-5.3-FlashNear-frontier performance at 1/10th the price.
Efficient
Granite 4.1 8BSolid performance at 1/100th the price.
1,4001,500
  1. 1,526
    Gemini 4 ArgonHigh
  2. 1,525
    Gemini 4 CarbonHigh
  3. 1,521
    Meta
    Muse WonderMax
  4. 1,513
    Anthropic
    Claude Opus 5.5High
  5. 1,512
    Anthropic
    Claude Opus 4.7High
  6. 1,511
    Meta
    Muse Spark 1.2xHigh
  7. 1,511
    Anthropic
    Claude Fable 5High
  8. 1,510
    Anthropic
    Claude Opus 4.6High
  9. 1,508
    Anthropic
    Claude Opus 4.6
  10. 1,508
    Gemini 4 HydrogenHigh
  11. 1,507
    GPT-6.1 SolMax
  12. 1,506
    Kimi K3Max
  13. 1,504
    Gemini 4 NeonHigh
  14. 1,502
    Anthropic
    Claude Fable 5.1Max
  15. 1,502
    Anthropic
    Claude Opus 5Max
Model RankingScoreCost per task (P50)Blended price $/M (3:1)
  1. 1Gemini 4 Argon (High)1,526$0.03$8
  2. 2Gemini 4 Carbon (High)1,525$0.05$8
  3. 3MetaMuse Wonder (Max)1,521$0.10$16
  4. 4AnthropicClaude Opus 5.5 (High)1,513$0.08$16
  5. 5AnthropicClaude Opus 4.7 (High)1,512$0.06$20
  6. 6MetaMuse Spark 1.2 (xHigh)1,511$0.01$3.50
  7. 7AnthropicClaude Fable 5 (High)1,511$0.14$40
  8. 8AnthropicClaude Opus 4.6 (High)1,510$0.07$20
  9. 9AnthropicClaude Opus 4.61,508$0.06$20
  10. 10Gemini 4 Hydrogen (High)1,508$0.05$6
  11. 11GPT-6.1 Sol (Max)1,507$0.04$8
  12. 12Kimi K3 (Max)1,506$0.06N/A
  13. 13Gemini 4 Neon (High)1,504$0.08N/A
  14. 14AnthropicClaude Fable 5.1 (Max)1,502$0.46$40
  15. 15AnthropicClaude Opus 5 (Max)1,502$0.16$20

Pareto frontier

Best score for the cost
1,3501,4001,4501,500
Meta
$0.001$0.01$0.10

Median cost per task

Frontier
Gemini 4 Argon (High)1,526 rating. 1 point above rank 2.
Daily Driver
GLM-5.3-FlashNear-frontier performance at 1/10th the price.
Efficient
Granite 4.1 8BSolid performance at 1/100th the price.
On the frontierScore$/task
  1. Gemini 4 Argon (High)1,526$0.03
  2. MetaMuse Spark 1.2 (xHigh)1,511$0.01
  3. Gemini 3.8 Flash (High)1,494$0.01
  4. DeepSeek-V4-Pro (High, 20260813)1,482$0.01
  5. Grok 4.51,479$0.01
  6. GLM-5.3-Flash1,476$0.01
  7. MiMo-V2.5-Pro1,475$0.01
  8. DeepSeek-V4-Pro1,474$0.01
  9. DeepSeek-V4-Flash Preview (High)1,457$0.01
  10. DeepSeek-V4-Flash1,448$0.01
  11. Granite 4.1 8B1,350$0.01
288 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.

  • 16Gemini 3 Pro
  • 17Muse Spark
  • 34Claude Opus 4.5 (High, 32K, 20251101)
  • 36Gemini 3 Flash
  • 38Claude Opus 4.5 (20251101)
  • 52Grok 4.1 (Thinking)
  • 55Grok 4.1
  • 63Gemini 2.5 Pro
  • 66GPT-4.5 Preview (2025-02-27)
  • 67GLM-5
  • 70GPT-5.1 (High)
  • 74DeepSeek-V3.1-Terminus (Thinking)
  • 76Claude Sonnet 4.5 (20250929)
  • 77Gemma 4 26B A4B
  • 78Claude Sonnet 4.5 (High, 32K, 20250929)
  • 79Claude Opus 4.1 (Thinking 16K, 20250805)
  • 82GPT-5 (High)
  • 83Qwen3.6-Max-Preview
  • 84ChatGPT-4o Latest (20250326)
  • 85GPT-5 Chat
  • 86Claude Opus 4.1 (20250805)
  • 87ERNIE-5.0-Preview (1203)
  • 94Gemma 4 31B
  • 95GLM-4.7
  • 97o3 (2025-04-16)
  • 98GPT-5.1
  • 99Kimi K2 Preview (0905)
  • 100ERNIE-5.0-Preview (1022)
  • 101GPT-5.2 (High)
  • 109amazon-nova-experimental-chat (26-02-10)
  • 114Kimi K2.5 (Instant)
  • 119Claude Opus 4 (20250514)
  • 120ERNIE 5.0 (0110)
  • 122GPT-4.1 (2025-04-14)
  • 123GLM-4.6
  • 124Kimi K2 Thinking Turbo
  • 125Claude Opus 4 (Thinking 16K, 20250514)
  • 126Qwen3-235B-A22B-Instruct (2507)
  • 127Muse Glimmer
  • 128Beam 1.0 501B A23B
  • 129DeepSeek-V3.2
  • 131Qwen3-Max-Preview
  • 132Qwen3-VL-235B-A22B-Instruct
  • 134DeepSeek-V3.2 (Thinking)
  • 135NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4)
  • 136LongCat-Flash-Chat Exp (2602)
  • 137Grok 4.1 Fast (Reasoning)
  • 138Gemini 2.5 Flash
  • 139Grok 4 Fast (Reasoning)
  • 140Gemini 2.5 Flash Preview (09-2025)
  • 141Grok 3 Preview (02-24)
  • 142DeepSeek-V3.2-Exp (Thinking)
  • 144Grok 4 (0709)
  • 145Grok 4 Fast (Non-Reasoning)
  • 147DeepSeek-V3.1 (Thinking)
  • 148DeepSeek-V3.1
  • 149Kimi K2 Preview (0711)
  • 150DeepSeek-V3.1-Terminus
  • 151GLM-4.5
  • 152Mistral Medium 3.1 (2508)
  • 155DeepSeek-R1 (0528)
  • 156DeepSeek-V3.2-Exp
  • 157Qwen3-Max (2025-09-23)
  • 158Mistral Medium 3 (2505)
  • 160DeepSeek-V3 (0324)
  • 161Claude Sonnet 4 (20250514)
  • 162Qwen3-Next-80B-A3B-Instruct
  • 163o1 (2024-12-17)
  • 164Hunyuan T1 (20250711)
  • 165Claude Sonnet 4 (Thinking 32K, 20250514)
  • 167Qwen3-VL-235B-A22B-Thinking
  • 168Qwen3-235B-A22B (Non-Thinking)
  • 171GLM-4.6V
  • 173Qwen3-Coder-480B-A35B-Instruct
  • 175o4-mini (2025-04-16)
  • 176DeepSeek-R1
  • 177amazon-nova-experimental-chat (12-10)
  • 178GPT-5 mini (High)
  • 179Qwen3-235B-A22B-Thinking (2507)
  • 180amazon-nova-experimental-chat (26-01-10)
  • 181Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
  • 182Claude 3.7 Sonnet (Thinking 32K, 20250219)
  • 183GPT-4.1 mini (2025-04-14)
  • 184MiMo-V2-Flash (Thinking)
  • 185LongCat-Flash-Chat
  • 188MiniMax-M2.1 Preview
  • 189Claude 3.7 Sonnet (20250219)
  • 191o1-preview
  • 192MiMo-V2-Flash (Non-Thinking)
  • 193Qwen2.5-Max
  • 194Grok 3 Mini (High)
  • 195Gemma 3 27B IT
  • 196Qwen3-30B-A3B-Instruct (2507)
  • 197DeepSeek-V3
  • 198Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
  • 199Gemma 3 12B IT
  • 201Claude 3.5 Sonnet (20241022)
  • 202Hunyuan TurboS (20250416)
  • 203GLM-4-Plus (0111)
  • 204Gemini 2.0 Flash (001)
  • 205Gemini 2.0 Flash-Lite Preview (02-05)
  • 206GLM-4.7-Flash
  • 207NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
  • 208Qwen-Plus (0125)
  • 209Command A (03-2025)
  • 211Gemini Advanced (0514)
  • 212GLM-4.5-Air
  • 213GPT-4o (2024-05-13)
  • 214Mistral Small 3.2 (2506)
  • 215Llama 3.1 405B Instruct (BF16)
  • 216Llama 3.1 405B Instruct (FP8)
  • 217GLM-4.5V
  • 218Gemini 1.5 Pro (002)
  • 219NVIDIA-Nemotron-3-Super-120B-A12B
  • 220Qwen3-235B-A22B
  • 221Grok 2 (2024-08-13)
  • 222Yi Lightning
  • 223amazon-nova-experimental-chat (11-10)
  • 224MiniMax-M1
  • 225Grok 3 Mini Beta
  • 226Qwen3-Next-80B-A3B-Thinking
  • 227o3-mini (High)
  • 228MiniMax-M2
  • 229Olmo 3.1 32B Instruct
  • 230Claude 3.5 Sonnet (20240620)
  • 231Llama 3.3 Nemotron Super 49B v1.5
  • 232Claude 3.5 Haiku (20241022)
  • 233GPT-4.1 nano (2025-04-14)
  • 235GLM-4-Plus
  • 236Claude 3 Opus (20240229)
  • 237Step-2 16K Exp (202412)
  • 238GPT-4o (2024-08-06)
  • 239GPT-4o mini (2024-07-18)
  • 240Ling-flash-2.0
  • 241o1-mini
  • 242Llama 3.3 70B Instruct
  • 243Llama 4 Maverick 17B 128E Instruct
  • 244NVIDIA-Nemotron-3.5-Lightning-30B-A3B (NVFP4)
  • 245Step-3
  • 246Llama 4 Scout 17B 16E Instruct
  • 247gpt-oss-120b
  • 248o3-mini
  • 249Gemma 3 4B IT
  • 250amazon-nova-experimental-chat (10-09)
  • 251QwQ-32B
  • 252Hunyuan Standard (2025-02-10)
  • 253amazon-nova-experimental-chat (10-20)
  • 254Mistral Large 2 (2407)
  • 255GPT-4 Turbo (2024-04-09)
  • 256Step-1o Turbo (202506)
  • 257Hunyuan Large (2025-02-10)
  • 258Amazon Nova 2 Lite
  • 259Athene 70B (0725)
  • 260Gemini 1.5 Pro (001)
  • 261Qwen2.5-72B-Instruct
  • 262Llama 3.1 Nemotron 51B Instruct
  • 263DeepSeek-V2.5
  • 264Grok 2 mini (2024-08-13)
  • 265Reka Core (20240904)
  • 266GPT-5 nano (High)
  • 267Llama 3.1 70B Instruct
  • 268Llama 3.1 Nemotron 70B Instruct
  • 269Gemini 1.5 Flash (002)
  • 270INTELLECT-3
  • 271Athene V2 Chat
  • 272Qwen3-32B
  • 273Qwen-Max (0919)
  • 274Gemma 3n E4B IT
  • 275Gemma 2 9B IT SimPO
  • 276Mistral Large (2411)
  • 277Granite 4.2 30B
  • 278DeepSeek-V2.5 (1210)
  • 279Amazon Nova Pro 1.0
  • 280Jamba 1.5 Large
  • 281GPT-4 Turbo Preview (0125)
  • 282Qwen2.5-Plus (1127)
  • 283Qwen3-30B-A3B
  • 284gpt-oss-20b
  • 285Command R+ (08-2024)
  • 286Nemotron-4 340B Instruct
  • 287GPT-4 Turbo Preview (1106)
  • 288Granite 4.2 3B
  • 289Command R+
  • 290GLM-4 (0520)
  • 291Gemma 2 27B IT
  • 292Qwen2.5-Coder-32B-Instruct
  • 293Mistral Small 3.1 24B Instruct (2503)
  • 294Gemini 1.5 Flash (001)
  • 295Olmo 3.1 32B Think
  • 296Claude 3 Sonnet (20240229)
  • 297NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
  • 298Magistral Medium (2506)
  • 299Command R (08-2024)
  • 300Llama 3 70B Instruct
  • 301Aya Expanse 32B
  • 302Phi-4
  • 303Olmo 3 32B Think
  • 304GPT-4 (0314)
  • 305Gemini 1.5 Flash-8B (001)
  • 306Ring-flash-2.0
  • 307Hunyuan Large Vision
  • 308Granite 4.2 8B
  • 309Jamba 1.5 Mini
  • 310Claude 3 Haiku (20240307)
  • 311Reka Flash (20240904)
  • 312Gemma 2 9B IT
  • 313Granite-4.0-H-Small
  • 314Amazon Nova Lite 1.0
  • 315Reka Flash 21B (Online, 20240226)
  • 316Command R
  • 317Mistral Small 24B Instruct (2501)
  • 318DeepSeek-Coder-V2
  • 319OLMo 2 32B Instruct (0325)
  • 320Qwen2-72B-Instruct
  • 321GPT-4 (0613)
  • 322Ministral 8B (2410)
  • 323Mistral Large (2402)
  • 324Qwen1.5-110B-Chat
  • 325Aya Expanse 8B
  • 326Amazon Nova Micro 1.0
  • 327Gemini Pro (Dev API)
  • 328Reka Flash 21B (20240226)
  • 329Qwen1.5-72B-Chat
  • 330Mixtral 8x22B Instruct v0.1
  • 331Mistral Medium
  • 332Yi 1.5 34B Chat
  • 333Granite 3.1 8B Instruct
  • 334GPT-3.5 Turbo (0125)
  • 335Llama 3.1 8B Instruct
  • 336Llama 3 8B Instruct
  • 337OpenChat 3.5
  • 338Qwen1.5-32B-Chat
  • 339Mixtral 8x7B Instruct v0.1
  • 340Zephyr ORPO 141B A35B v0.1
  • 341Gemini Pro
  • 342Gemma 2 2B IT
  • 343Yi 34B Chat
  • 344WizardLM 70B
  • 345Tulu 2 DPO 70B
  • 346Phi-3 Medium 4K Instruct
  • 347OpenHermes 2.5 Mistral 7B
  • 348Gemma 1.1 7B IT
  • 349Starling LM 7B Beta
  • 350DBRX Instruct Preview
  • 351Qwen1.5-14B-Chat
  • 352OpenChat 3.5 (0106)
  • 353Starling LM 7B Alpha
  • 354GPT-3.5 Turbo (1106)
  • 355DeepSeek LLM 67B Chat
  • 356Snowflake Arctic Instruct
  • 357InternLM2.5 20B Chat
  • 358WizardLM 13B
  • 359Phi-3 Small 8K Instruct
  • 360Granite 3.0 8B Instruct
  • 361Llama 2 70B Chat
  • 362Vicuna 33B
  • 363Llama 3.2 3B Instruct
  • 364Zephyr 7B Beta
  • 365Mistral 7B Instruct v0.2
  • 366SOLAR 10.7B Instruct v1.0
  • 367Granite 3.0 2B Instruct
  • 368Qwen1.5-7B-Chat
  • 369Qwen-14B-Chat
  • 370Vicuna 13B
  • 371Code Llama 34B Instruct
  • 372Gemma 7B IT
  • 373Llama 2 13B Chat
  • 374QwQ-32B-Preview
  • 375Phi-3 Mini 4K Instruct
  • 376PaLM 2
  • 377Phi-3 Mini 4K Instruct (June 2024)
  • 378Llama 3.2 1B Instruct
  • 379Mistral 7B Instruct
  • 380Vicuna 7B
  • 381Gemma 2B IT
  • 382Llama 2 7B Chat
  • 383Qwen1.5-4B-Chat
  • 384Gemma 1.1 2B IT
  • 385Phi-3 Mini 128K Instruct
  • 386StripedHyena Nous 7B
  • 387RWKV-4 Raven 14B
  • 388OLMo 7B Instruct
  • 389ChatGLM3 6B
  • 390Alpaca 13B
  • 391Koala 13B
  • 392OpenAssistant Pythia 12B
  • 393FastChat-T5 3B
  • 394ChatGLM 6B

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