OverviewAll LeaderboardsMethodology
New Chat

Text Arena

Which model is the best at everyday chat?

Nov 20, 2026
3,060,669 votes
426 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. 1,518
    Gemini 4 NeonHigh
  4. 1,516
    Anthropic
    Claude Opus 5.5High
  5. 1,511
    Anthropic
    Claude Opus 4.6High
  6. 1,509
    Anthropic
    Claude Fable 5High
  7. 1,503
    Anthropic
    Claude Opus 4.7High
  8. 1,503
    Anthropic
    Claude Fable 5.1Max
  9. 1,502
    Anthropic
    Claude Fable 5.2Max
  10. 1,498
    Anthropic
    Claude Opus 4.6
  11. 1,498
    Gemini 4 HydrogenHigh
  12. 1,496
    Meta
    Muse WonderMax
  13. 1,496
    Anthropic
    Claude Opus 5High
  14. 1,494
    Anthropic
    Claude Opus 5Max
  15. 1,493
    Anthropic
    Claude Opus 4.7
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. 3Gemini 4 Neon (High)1,518$0.08$6
  4. 4AnthropicClaude Opus 5.5 (High)1,516$0.08$16
  5. 5AnthropicClaude Opus 4.6 (High)1,511$0.07$20
  6. 6AnthropicClaude Fable 5 (High)1,509$0.14$40
  7. 7AnthropicClaude Opus 4.7 (High)1,503$0.06$20
  8. 8AnthropicClaude Fable 5.1 (Max)1,503$0.46$40
  9. 9AnthropicClaude Fable 5.2 (Max)1,502$0.25$32
  10. 10AnthropicClaude Opus 4.61,498$0.06$20
  11. 11Gemini 4 Hydrogen (High)1,498$0.05$6
  12. 12MetaMuse Wonder (Max)1,496$0.10$16
  13. 13AnthropicClaude Opus 5 (High)1,496$0.12$20
  14. 14AnthropicClaude Opus 5 (Max)1,494$0.16$20
  15. 15AnthropicClaude Opus 4.71,493$0.06$20

Pareto frontier

Best score for the cost
1,3001,3501,4001,4501,500
$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. Gemini 3.8 Flash (High)1,492$0.01
  3. DeepSeek-V4.1-Flash-20260910 (Max)1,475$0.01
  4. GLM-5.3-Flash1,474$0.01
  5. MiMo-V2.5-Pro1,467$0.01
  6. DeepSeek-V4-Pro1,453$0.01
  7. MiMo-V2.6-Flash1,435$0.01
  8. DeepSeek-V4-Flash1,428$0.01
  9. Granite 4.1 8B1,287$0.01
315 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)
  • 35Claude Opus 4.5 (20251101)
  • 40Gemini 3 Pro
  • 52Muse Spark
  • 53Claude Sonnet 4.5 (High, 32K, 20250929)
  • 55Claude Sonnet 4.5 (20250929)
  • 60Claude Opus 4.1 (Thinking 16K, 20250805)
  • 61Gemini 3 Flash
  • 66Claude Opus 4.1 (20250805)
  • 69Gemma 4 31B
  • 72Qwen3.6-Max-Preview
  • 73GPT-5.1 (High)
  • 78GLM-5
  • 83Claude Opus 4 (Thinking 16K, 20250514)
  • 88Gemini 2.5 Pro
  • 89Gemma 4 26B A4B
  • 91GPT-4.5 Preview (2025-02-27)
  • 100Beam 1.0 501B A23B
  • 101Kimi K2.5 (Instant)
  • 103Grok 4.1
  • 104Grok 4.1 (Thinking)
  • 108GPT-5.2 (High)
  • 109ChatGPT-4o Latest (20250326)
  • 110GPT-5.1
  • 111GLM-4.7
  • 113ERNIE 5.0 (0110)
  • 114Qwen3-Max-Preview
  • 119DeepSeek-V3.2
  • 121DeepSeek-V3.2 (Thinking)
  • 122ERNIE-5.0-Preview (1203)
  • 123Kimi K2 Thinking Turbo
  • 124DeepSeek-V3.1-Terminus (Thinking)
  • 125DeepSeek-V3.1 (Thinking)
  • 126DeepSeek-V3.2-Exp (Thinking)
  • 127LongCat-Flash-Chat Exp (2602)
  • 128Claude Sonnet 4 (Thinking 32K, 20250514)
  • 130GPT-5 Chat
  • 131Claude Opus 4 (20250514)
  • 132amazon-nova-experimental-chat (26-02-10)
  • 133DeepSeek-V3.2-Exp
  • 135Qwen3-235B-A22B-Instruct (2507)
  • 136Qwen3-Max (2025-09-23)
  • 137GLM-4.6
  • 138NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
  • 139Muse Glimmer
  • 140Claude 3.7 Sonnet (Thinking 32K, 20250219)
  • 141GPT-5 (High)
  • 144Qwen3-VL-235B-A22B-Instruct
  • 146o1 (2024-12-17)
  • 148NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4)
  • 149GLM-4.5
  • 150GPT-4.1 (2025-04-14)
  • 152o3 (2025-04-16)
  • 153Grok 3 Preview (02-24)
  • 154DeepSeek-V3.1
  • 155Grok 4.1 Fast (Reasoning)
  • 157Gemini 2.5 Flash Preview (09-2025)
  • 158Gemini 2.5 Flash
  • 159ERNIE-5.0-Preview (1022)
  • 160DeepSeek-R1
  • 161amazon-nova-experimental-chat (26-01-10)
  • 164Grok 4 (0709)
  • 165Claude Sonnet 4 (20250514)
  • 166Hunyuan Vision 1.5 Thinking
  • 167Mistral Medium 3.1 (2508)
  • 168Grok 4 Fast (Non-Reasoning)
  • 169DeepSeek-V3.1-Terminus
  • 170DeepSeek-R1 (0528)
  • 171Kimi K2 Preview (0905)
  • 172Grok 4 Fast (Reasoning)
  • 174LongCat-Flash-Chat
  • 176Qwen3-235B-A22B-Thinking (2507)
  • 177MiniMax-M2.1 Preview
  • 178Claude 3.7 Sonnet (20250219)
  • 180Qwen3-Coder-480B-A35B-Instruct
  • 181MiMo-V2-Flash (Non-Thinking)
  • 183Qwen3-VL-235B-A22B-Thinking
  • 184o1-preview
  • 185Kimi K2 Preview (0711)
  • 187Qwen3-235B-A22B (Non-Thinking)
  • 188DeepSeek-V3 (0324)
  • 190Qwen3-Next-80B-A3B-Instruct
  • 191amazon-nova-experimental-chat (12-10)
  • 192MiMo-V2-Flash (Thinking)
  • 193Claude 3.5 Sonnet (20241022)
  • 194Hunyuan T1 (20250711)
  • 195GPT-4.1 mini (2025-04-14)
  • 196GPT-5 mini (High)
  • 198Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
  • 199o4-mini (2025-04-16)
  • 200GLM-4.6V
  • 201o3-mini (High)
  • 202Mistral Medium 3 (2505)
  • 203Qwen3-30B-A3B-Instruct (2507)
  • 204Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
  • 205GLM-4.5-Air
  • 206Grok 3 Mini (High)
  • 207amazon-nova-experimental-chat (11-10)
  • 208Qwen3-Next-80B-A3B-Thinking
  • 210Qwen3-235B-A22B
  • 211Qwen2.5-Max
  • 212Hunyuan TurboS (20250416)
  • 213Grok 3 Mini Beta
  • 214Llama 3.1 Nemotron Ultra 253B v1
  • 215Hunyuan TurboS (20250226)
  • 216Gemini 2.0 Flash (001)
  • 217GLM-4.7-Flash
  • 218amazon-nova-experimental-chat (10-20)
  • 219MiniMax-M1
  • 220Step-3
  • 221o3-mini
  • 222Gemma 3 27B IT
  • 223NVIDIA-Nemotron-3.5-Lightning-30B-A3B (NVFP4)
  • 224DeepSeek-V3
  • 225NVIDIA-Nemotron-3-Super-120B-A12B
  • 226Command A (03-2025)
  • 227Granite 4.2 30B
  • 228Gemini 1.5 Pro (002)
  • 229GLM-4.5V
  • 230Claude 3.5 Sonnet (20240620)
  • 231Mistral Small 3.2 (2506)
  • 232MiniMax-M2
  • 233INTELLECT-3
  • 234o1-mini
  • 235Qwen-Plus (0125)
  • 236Gemini 2.0 Flash-Lite Preview (02-05)
  • 237Qwen3-32B
  • 238Amazon Nova 2 Lite
  • 239Mercury 2
  • 240GPT-5 nano (High)
  • 241GPT-4o (2024-05-13)
  • 242Llama 3.3 Nemotron Super 49B v1
  • 243gpt-oss-120b
  • 244QwQ-32B
  • 245Llama 3.3 Nemotron Super 49B v1.5
  • 246Gemma 3 12B IT
  • 247Olmo 3.1 32B Instruct
  • 248GPT-4o (2024-08-06)
  • 249Gemini Advanced (0514)
  • 250Claude 3.5 Haiku (20241022)
  • 251Ring-flash-2.0
  • 252Hunyuan Large (2025-02-10)
  • 253Ling-flash-2.0
  • 254Step-2 16K Exp (202412)
  • 255Llama 3.1 405B Instruct (FP8)
  • 256GLM-4-Plus (0111)
  • 257Claude 3 Opus (20240229)
  • 258Llama 3.1 405B Instruct (BF16)
  • 259DeepSeek-V2.5 (1210)
  • 260Llama 4 Maverick 17B 128E Instruct
  • 261Hunyuan Turbo (0110)
  • 262amazon-nova-experimental-chat (10-09)
  • 263Grok 2 (2024-08-13)
  • 264Gemini 1.5 Pro (001)
  • 265Qwen3-30B-A3B
  • 266Yi Lightning
  • 267Step-1o Turbo (202506)
  • 268Molmo 2 8B
  • 269GPT-4 Turbo (2024-04-09)
  • 270Athene V2 Chat
  • 271Qwen-Max (0919)
  • 272GLM-4-Plus
  • 273Magistral Medium (2506)
  • 274GPT-4.1 nano (2025-04-14)
  • 275Mistral Large 2 (2407)
  • 276Llama 4 Scout 17B 16E Instruct
  • 277Olmo 3 32B Think
  • 278GPT-4 Turbo Preview (1106)
  • 279Mistral Large (2411)
  • 280Qwen2.5-Plus (1127)
  • 281GPT-4o mini (2024-07-18)
  • 282Mistral Small 3.1 24B Instruct (2503)
  • 283Llama 3.3 70B Instruct
  • 284Qwen2.5-72B-Instruct
  • 285DeepSeek-V2.5
  • 286NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
  • 287GPT-4 Turbo Preview (0125)
  • 288Gemini 1.5 Flash (002)
  • 290Hunyuan Large Vision
  • 291GPT-4 (0314)
  • 292Grok 2 mini (2024-08-13)
  • 293Granite 4.2 3B
  • 294Granite 4.2 8B
  • 295Gemma 3n E4B IT
  • 296Hunyuan Standard (2025-02-10)
  • 297gpt-oss-20b
  • 298Olmo 3.1 32B Think
  • 299Llama 3.1 Nemotron 70B Instruct
  • 300Athene 70B (0725)
  • 301GPT-4 (0613)
  • 302Amazon Nova Pro 1.0
  • 303Llama 3.1 70B Instruct
  • 304Llama 3.1 Tulu 3 70B
  • 305Gemma 2 27B IT
  • 306Mercury
  • 307Granite-4.0-H-Small
  • 308Claude 3 Sonnet (20240229)
  • 309Gemma 3 4B IT
  • 310Jamba 1.5 Large
  • 311Gemini 1.5 Flash (001)
  • 312Qwen2.5-Coder-32B-Instruct
  • 313Llama 3.1 Nemotron 51B Instruct
  • 314Reka Core (20240904)
  • 315Nemotron-4 340B Instruct
  • 316Llama 3 70B Instruct
  • 317GLM-4 (0520)
  • 318Mistral Small 24B Instruct (2501)
  • 319Command R+ (08-2024)
  • 320DeepSeek-Coder-V2
  • 321Gemma 2 9B IT SimPO
  • 322Reka Flash (20240904)
  • 323Aya Expanse 32B
  • 324Gemma 2 9B IT
  • 325Claude 3 Haiku (20240307)
  • 326Phi-4
  • 327Amazon Nova Lite 1.0
  • 328Hunyuan Standard 256K
  • 329Qwen2-72B-Instruct
  • 330Command R+
  • 331Gemini 1.5 Flash-8B (001)
  • 332Mistral Large (2402)
  • 333Command R (08-2024)
  • 334OLMo 2 32B Instruct (0325)
  • 335Gemini Pro
  • 336Qwen1.5-110B-Chat
  • 337GPT-3.5 Turbo (0125)
  • 338Mixtral 8x22B Instruct v0.1
  • 339Amazon Nova Micro 1.0
  • 340Qwen1.5-72B-Chat
  • 341Ministral 8B (2410)
  • 342Gemini Pro (Dev API)
  • 343Mistral Medium
  • 344Llama 3.1 Tulu 3 8B
  • 345Jamba 1.5 Mini
  • 346Aya Expanse 8B
  • 347Reka Flash 21B (Online, 20240226)
  • 348Command R
  • 349GPT-3.5 Turbo (1106)
  • 350Zephyr ORPO 141B A35B v0.1
  • 351Granite 3.1 8B Instruct
  • 352Llama 3 8B Instruct
  • 353Reka Flash 21B (20240226)
  • 354Llama 3.1 8B Instruct
  • 355Yi 1.5 34B Chat
  • 356DBRX Instruct Preview
  • 357Qwen1.5-32B-Chat
  • 358Mixtral 8x7B Instruct v0.1
  • 359InternLM2.5 20B Chat
  • 360Phi-3 Medium 4K Instruct
  • 361Granite 3.1 2B Instruct
  • 362Granite 3.0 8B Instruct
  • 363Gemma 2 2B IT
  • 364Tulu 2 DPO 70B
  • 365Qwen1.5-14B-Chat
  • 366WizardLM 70B
  • 367DeepSeek LLM 67B Chat
  • 368Gemma 1.1 7B IT
  • 369OpenChat 3.5 (0106)
  • 370OpenChat 3.5
  • 371Phi-3 Small 8K Instruct
  • 372Snowflake Arctic Instruct
  • 373OpenHermes 2.5 Mistral 7B
  • 374Yi 34B Chat
  • 375Llama 3.2 3B Instruct
  • 376Starling LM 7B Beta
  • 377QwQ-32B-Preview
  • 378Vicuna 33B
  • 379Starling LM 7B Alpha
  • 380MPT 30B Chat
  • 381Llama 2 70B Chat
  • 382Falcon 180B Chat
  • 383Granite 3.0 2B Instruct
  • 384Dolphin 2.2.1 Mistral 7B
  • 385Llama 2 70B SteerLM Chat
  • 386Phi-3 Mini 4K Instruct (June 2024)
  • 387WizardLM 13B
  • 388Qwen1.5-7B-Chat
  • 389Mistral 7B Instruct v0.2
  • 390Qwen-14B-Chat
  • 391PaLM 2
  • 392Vicuna 13B
  • 393SOLAR 10.7B Instruct v1.0
  • 394Phi-3 Mini 4K Instruct
  • 395Llama 2 13B Chat
  • 396Nous Hermes 2 Mixtral 8x7B DPO
  • 397Gemma 7B IT
  • 398Code Llama 34B Instruct
  • 399SmolLM2 1.7B Instruct
  • 400Gemma 1.1 2B IT
  • 401Phi-3 Mini 128K Instruct
  • 402Zephyr 7B Alpha
  • 403Code Llama 70B Instruct
  • 404StripedHyena Nous 7B
  • 405Zephyr 7B Beta
  • 406Mistral 7B Instruct
  • 407Llama 3.2 1B Instruct
  • 408Vicuna 7B
  • 409Gemma 2B IT
  • 410Qwen1.5-4B-Chat
  • 411Llama 2 7B Chat
  • 412Guanaco 33B
  • 413GPT4All 13B Snoozy
  • 414ChatGLM3 6B
  • 415OLMo 7B Instruct
  • 416Koala 13B
  • 417Alpaca 13B
  • 418MPT 7B Chat
  • 419OpenAssistant Pythia 12B
  • 420ChatGLM2 6B
  • 421ChatGLM 6B
  • 422RWKV-4 Raven 14B
  • 423FastChat-T5 3B
  • 424Dolly 2.0 12B
  • 425LLaMA 13B
  • 426StableLM Tuned Alpha 7B

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