OverviewAll LeaderboardsMethodology
New Chat

Text Arena

Which model is the best at everyday chat?

Nov 18, 2026
168,829 votes
321 models

Text Arena

Frontier
Gemini 4 Argon (High)1,576 rating. 53 points above rank 2.
Daily Driver
DeepSeek-V4-ProNear-frontier performance at 1/10th the price.
Best open model
GLM-5.3 (Max)96% of the frontier score.
1,4001,5001,600
  1. 1,576
    Gemini 4 ArgonHigh
  2. 1,523
    Meta
    Muse WonderMax
  3. 1,521
    Gemini 3 Pro
  4. 1,518
    Anthropic
    Claude Opus 5.5High
  5. 1,512
    Meta
    Muse Spark
  6. 1,512
    Meta
    Muse Spark 1.3Max
  7. 1,511
    GLM-5.3Max
  8. 1,510
    Gemini 3.7 FlashHigh
  9. 1,507
    Anthropic
    Claude Opus 4.6High
  10. 1,506
    Anthropic
    Claude Opus 4.7High
  11. 1,503
    GPT-5.6 SolxHigh
  12. 1,501
    Anthropic
    Claude Opus 5Max
  13. 1,500
    Gemini 3.8 FlashHigh
  14. 1,499
    Gemini 3 Flash
  15. 1,498
    Kimi K3Max
Model RankingScoreCost per task (P50)Blended price $/M (3:1)
  1. 1Gemini 4 Argon (High)1,576$0.03$8
  2. 2MetaMuse Wonder (Max)1,523$0.10$16
  3. 3Gemini 3 Pro1,521N/A$9.50
  4. 4AnthropicClaude Opus 5.5 (High)1,518$0.08$16
  5. 5MetaMuse Spark1,512N/AN/A
  6. 6MetaMuse Spark 1.3 (Max)1,512$0.02$3.50
  7. 7GLM-5.3 (Max)1,511$0.03$3.65
  8. 8Gemini 3.7 Flash (High)1,510$0.01$3
  9. 9AnthropicClaude Opus 4.6 (High)1,507$0.07$20
  10. 10AnthropicClaude Opus 4.7 (High)1,506$0.06$20
  11. 11GPT-5.6 Sol (xHigh)1,503$0.07$16
  12. 12AnthropicClaude Opus 5 (Max)1,501$0.16$20
  13. 13Gemini 3.8 Flash (High)1,500$0.01$3
  14. 14Gemini 3 Flash1,499N/A$3.21
  15. 15Kimi K3 (Max)1,498$0.06N/A

Pareto frontier

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

Median cost per task

Frontier
Gemini 4 Argon (High)1,576 rating. 53 points above rank 2.
Daily Driver
DeepSeek-V4-ProNear-frontier performance at 1/10th the price.
Best open model
GLM-5.3 (Max)96% of the frontier score.
On the frontierScore$/task
  1. Gemini 4 Argon (High)1,576$0.03
  2. MetaMuse Spark 1.3 (Max)1,512$0.02
  3. Gemini 3.7 Flash (High)1,510$0.01
  4. Gemini 3.8 Flash (High)1,500$0.01
  5. Grok 4.20 Beta 11,489$0.01
  6. DeepSeek-V4.1-Flash-20260910 (Max)1,480$0.01
  7. Gemini 3 Flash (Minimal)1,476$0.01
  8. DeepSeek-V4-Pro1,468$0.01
  9. AnthropicClaude Haiku 5.5 (High)1,458$0.01
  10. MiMo-V2.6-Flash1,446$0.01
  11. DeepSeek-V4-Flash1,423$0.01
225 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.

  • 3Gemini 3 Pro
  • 5Muse Spark
  • 14Gemini 3 Flash
  • 35Claude Opus 4.5 (20251101)
  • 37GPT-4.5 Preview (2025-02-27)
  • 38Claude Opus 4.5 (High, 32K, 20251101)
  • 47Gemini 2.5 Pro
  • 54Grok 4.1
  • 59Grok 4.1 (Thinking)
  • 60GPT-5.2 (High)
  • 61ERNIE-5.0-Preview (1203)
  • 64Claude Sonnet 4.5 (High, 32K, 20250929)
  • 71GLM-5
  • 73GPT-5.1 (High)
  • 76Claude Opus 4.1 (Thinking 16K, 20250805)
  • 78Claude Opus 4 (Thinking 16K, 20250514)
  • 79Qwen3-Max-Preview
  • 82NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4)
  • 85GPT-5 (High)
  • 88DeepSeek-V3.2-Exp
  • 89Claude Sonnet 4.5 (20250929)
  • 92Claude Opus 4.1 (20250805)
  • 94GPT-5.1
  • 95o3 (2025-04-16)
  • 97Qwen3-Max (2025-09-23)
  • 100DeepSeek-V3.2-Exp (Thinking)
  • 103Kimi K2.5 (Instant)
  • 106Claude Opus 4 (20250514)
  • 107ERNIE 5.0 (0110)
  • 109ChatGPT-4o Latest (20250326)
  • 111GLM-4.6
  • 112GLM-4.7
  • 113Qwen3-235B-A22B-Instruct (2507)
  • 115GPT-5 Chat
  • 116Kimi K2 Preview (0905)
  • 117Kimi K2 Preview (0711)
  • 118Grok 4.1 Fast (Reasoning)
  • 119Grok 3 Preview (02-24)
  • 120DeepSeek-V3.2 (Thinking)
  • 121Grok 4 (0709)
  • 122Qwen3-VL-235B-A22B-Thinking
  • 124DeepSeek-V3.2
  • 126Gemini 2.5 Flash Preview (09-2025)
  • 128Qwen3-VL-235B-A22B-Instruct
  • 129Kimi K2 Thinking Turbo
  • 131GPT-4.1 (2025-04-14)
  • 132DeepSeek-V3.1
  • 133Gemini 2.5 Flash
  • 134Mistral Medium 3.1 (2508)
  • 135Qwen3-235B-A22B-Thinking (2507)
  • 137DeepSeek-R1
  • 138DeepSeek-V3.1 (Thinking)
  • 139Mistral Medium 3 (2505)
  • 140GPT-4.1 mini (2025-04-14)
  • 142Claude Sonnet 4 (20250514)
  • 143DeepSeek-R1 (0528)
  • 146DeepSeek-V3 (0324)
  • 148MiMo-V2-Flash (Thinking)
  • 149Qwen3-Next-80B-A3B-Instruct
  • 151Claude 3.7 Sonnet (Thinking 32K, 20250219)
  • 152Grok 4 Fast (Reasoning)
  • 153GPT-5 mini (High)
  • 154Qwen3-235B-A22B
  • 156MiniMax-M2.1 Preview
  • 157Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
  • 158Qwen3-235B-A22B (Non-Thinking)
  • 159Claude Sonnet 4 (Thinking 32K, 20250514)
  • 160Claude 3.5 Sonnet (20241022)
  • 161Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
  • 162LongCat-Flash-Chat Exp (2602)
  • 163LongCat-Flash-Chat
  • 164GLM-4.5
  • 165o4-mini (2025-04-16)
  • 167o1 (2024-12-17)
  • 168Gemma 3 12B IT
  • 169Gemma 3 27B IT
  • 170Qwen3-30B-A3B-Instruct (2507)
  • 171Claude 3.7 Sonnet (20250219)
  • 172MiniMax-M1
  • 174Qwen3-Next-80B-A3B-Thinking
  • 175Command A (03-2025)
  • 177Gemini 2.0 Flash (001)
  • 178MiMo-V2-Flash (Non-Thinking)
  • 179MiniMax-M2
  • 180Step-3
  • 181GLM-4.5-Air
  • 182Mistral Small 3.2 (2506)
  • 183Qwen2.5-Max
  • 184o1-preview
  • 185DeepSeek-V3
  • 186Qwen3-Coder-480B-A35B-Instruct
  • 187Hunyuan TurboS (20250416)
  • 188GLM-4-Plus (0111)
  • 189GPT-5 nano (High)
  • 191GLM-4.7-Flash
  • 192Grok 3 Mini (High)
  • 193Qwen3-32B
  • 194Grok 3 Mini Beta
  • 195Claude 3.5 Sonnet (20240620)
  • 196Llama 4 Maverick 17B 128E Instruct
  • 197Gemini 2.0 Flash-Lite Preview (02-05)
  • 198amazon-nova-experimental-chat (10-20)
  • 199GPT-4o (2024-05-13)
  • 200amazon-nova-experimental-chat (11-10)
  • 201gpt-oss-120b
  • 202Gemini Advanced (0514)
  • 203o3-mini (High)
  • 204o3-mini
  • 205NVIDIA-Nemotron-3.5-Lightning-30B-A3B (NVFP4)
  • 206GPT-4.1 nano (2025-04-14)
  • 207Gemma 3n E4B IT
  • 208Claude 3 Opus (20240229)
  • 209Grok 2 (2024-08-13)
  • 210NVIDIA-Nemotron-3-Super-120B-A12B
  • 211Gemini 1.5 Pro (002)
  • 212GPT-4o (2024-08-06)
  • 213Claude 3.5 Haiku (20241022)
  • 214GPT-4 Turbo (2024-04-09)
  • 215Llama 4 Scout 17B 16E Instruct
  • 216QwQ-32B
  • 217Magistral Medium (2506)
  • 218Amazon Nova 2 Lite
  • 219NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
  • 220GLM-4-Plus
  • 221Qwen3-30B-A3B
  • 222Llama 3.1 405B Instruct (BF16)
  • 223Mistral Large 2 (2407)
  • 224Llama 3.1 405B Instruct (FP8)
  • 225GPT-4o mini (2024-07-18)
  • 226Gemini 1.5 Pro (001)
  • 227o1-mini
  • 228Olmo 3.1 32B Instruct
  • 229GPT-4 Turbo Preview (1106)
  • 230Mistral Small 3.1 24B Instruct (2503)
  • 231Step-1o Turbo (202506)
  • 232Grok 2 mini (2024-08-13)
  • 233GPT-4 Turbo Preview (0125)
  • 234Yi Lightning
  • 235Gemma 3 4B IT
  • 236Llama 3.3 70B Instruct
  • 237DeepSeek-V2.5 (1210)
  • 238Athene 70B (0725)
  • 239Mistral Large (2411)
  • 240Qwen-Max (0919)
  • 241Olmo 3 32B Think
  • 242Reka Core (20240904)
  • 243Athene V2 Chat
  • 244Amazon Nova Pro 1.0
  • 245Gemini 1.5 Flash (002)
  • 246GPT-4 (0314)
  • 247gpt-oss-20b
  • 248Claude 3 Sonnet (20240229)
  • 249Gemma 2 27B IT
  • 250Gemma 2 9B IT SimPO
  • 251Olmo 3.1 32B Think
  • 252Gemini 1.5 Flash (001)
  • 253Qwen2.5-72B-Instruct
  • 254DeepSeek-V2.5
  • 255Amazon Nova Lite 1.0
  • 256Command R+ (08-2024)
  • 257Llama 3.1 70B Instruct
  • 258Mistral Small 24B Instruct (2501)
  • 259Phi-4
  • 260Jamba 1.5 Large
  • 261GPT-4 (0613)
  • 262Command R+
  • 263Qwen2.5-Plus (1127)
  • 264Claude 3 Haiku (20240307)
  • 265Gemma 2 9B IT
  • 266Nemotron-4 340B Instruct
  • 267Command R (08-2024)
  • 268Mistral Large (2402)
  • 269Aya Expanse 32B
  • 270DeepSeek-Coder-V2
  • 271Gemini 1.5 Flash-8B (001)
  • 272Reka Flash (20240904)
  • 273GLM-4 (0520)
  • 274Llama 3 70B Instruct
  • 275Amazon Nova Micro 1.0
  • 276Qwen2-72B-Instruct
  • 277Aya Expanse 8B
  • 278Reka Flash 21B (20240226)
  • 279Reka Flash 21B (Online, 20240226)
  • 280Mixtral 8x22B Instruct v0.1
  • 281Mistral Medium
  • 282Jamba 1.5 Mini
  • 283Gemini Pro (Dev API)
  • 284GPT-3.5 Turbo (0125)
  • 285Command R
  • 286Qwen1.5-110B-Chat
  • 287Mixtral 8x7B Instruct v0.1
  • 288GPT-3.5 Turbo (1106)
  • 289Llama 3.1 8B Instruct
  • 290Phi-3 Medium 4K Instruct
  • 291Llama 3 8B Instruct
  • 292Gemma 2 2B IT
  • 293Gemma 1.1 7B IT
  • 294Yi 1.5 34B Chat
  • 295Qwen1.5-72B-Chat
  • 296WizardLM 70B
  • 297Phi-3 Small 8K Instruct
  • 298Snowflake Arctic Instruct
  • 299DBRX Instruct Preview
  • 300OpenChat 3.5 (0106)
  • 301Vicuna 33B
  • 302Qwen1.5-32B-Chat
  • 303Llama 3.2 3B Instruct
  • 304Starling LM 7B Beta
  • 305Qwen1.5-14B-Chat
  • 306Phi-3 Mini 4K Instruct
  • 307Phi-3 Mini 4K Instruct (June 2024)
  • 308Yi 34B Chat
  • 309Llama 2 70B Chat
  • 310Phi-3 Mini 128K Instruct
  • 311InternLM2.5 20B Chat
  • 312Starling LM 7B Alpha
  • 313Vicuna 13B
  • 314Llama 2 13B Chat
  • 315Llama 3.2 1B Instruct
  • 316Zephyr 7B Beta
  • 317Mistral 7B Instruct v0.2
  • 318Gemma 1.1 2B IT
  • 319Llama 2 7B Chat
  • 320Mistral 7B Instruct
  • 321Qwen1.5-4B-Chat

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