/best/chatbotsupdated July 2026120 models evaluated
Best AI for chatbots
Customer-facing conversational AI, support agents, and interactive assistants.
Chatbot quality hinges on three things most benchmarks ignore: persona consistency (does it stay in character when users push back?), safety calibration (does it refuse harmful requests without refusing legitimate ones?), and multilingual fluency (can it handle non-English users without degrading?).
What matters: a model that maintains character across long conversations, handles adversarial inputs gracefully, and produces natural-sounding responses in multiple languages. Latency matters too — users expect sub-second responses in a chat interface.
Our chatbots rank weights persona consistency (2×), safety calibration (1.5×), and multilingual (1×). For customer support specifically, add structured output weight if the model needs to trigger actions (refunds, escalations, ticket creation) based on conversation context.
Full rankings
All 120 models, scored for chatbots
| # | Model | Provider | Task score | $/in | $/out | Context |
|---|---|---|---|---|---|---|
| 01 | MiMo-V2.5 | XXiaomi | 5.00/5.0 | $0.105 | $0.280 | 1.0M |
| 02 | Xiaomi: MiMo-V2-Flash | XXiaomi | 5.00/5.0 | $0.100 | $0.300 | 262K |
| 03 | ByteDance Seed: Seed-2.0-Mini | BBytedance-seed | 5.00/5.0 | $0.100 | $0.400 | 262K |
| 04 | inclusionAI: Ring-2.6-1T | IInclusionai | 5.00/5.0 | $0.075 | $0.625 | 262K |
| 05 | Nex-N2-Pro | NNex AGI | 5.00/5.0 | $0.250 | $1.00 | 262K |
| 06 | Z.ai: GLM 5.2 | ZZhipu AI | 5.00/5.0 | $0.406 | $1.28 | 1.0M |
| 07 | Gemini 3.1 Flash Lite Preview | GGoogle | 5.00/5.0 | $0.250 | $1.50 | 1.0M |
| 08 | Google: Gemini 3.1 Flash Lite | GGoogle | 5.00/5.0 | $0.250 | $1.50 | 1.0M |
| 09 | GLM-4.7 | ZZhipu AI | 5.00/5.0 | $0.400 | $1.75 | 203K |
| 10 | Qwen: Qwen3.6 27B | QQwen | 5.00/5.0 | $0.285 | $2.40 | 262K |
| 11 | MoonshotAI: Kimi K2.6 | MMoonshotAI | 5.00/5.0 | $0.660 | $3.41 | 262K |
| 12 | Kimi K2.7 Code | MMoonshot AI | 5.00/5.0 | $0.720 | $3.50 | 262K |
| 13 | OpenAI: GPT-5.6 Luna | OOpenAI | 5.00/5.0 | $1.00 | $6.00 | 1.1M |
| 14 | Qwen: Qwen3.6 Max Preview | QQwen | 5.00/5.0 | $1.04 | $6.24 | 262K |
| 15 | Anthropic: Claude Sonnet 5 | AAnthropic | 5.00/5.0 | $2.00 | $10.00 | 1M |
| 16 | GPT-5.2 | OOpenAI | 5.00/5.0 | $1.75 | $14.00 | 400K |
| 17 | GPT-5.4 | OOpenAI | 5.00/5.0 | $2.50 | $15.00 | 1.1M |
| 18 | OpenAI: GPT-5.6 Terra | OOpenAI | 5.00/5.0 | $2.50 | $15.00 | 1.1M |
| 19 | OpenAI: GPT-5.6 Terra Pro | OOpenAI | 5.00/5.0 | $2.50 | $15.00 | 1.1M |
| 20 | Claude Sonnet 4.6 | AAnthropic | 5.00/5.0 | $3.00 | $15.00 | 1M |
| 21 | Claude Opus 4.6 | AAnthropic | 5.00/5.0 | $5.00 | $25.00 | 1M |
| 22 | Anthropic: Claude Opus 4.8 | AAnthropic | 5.00/5.0 | $5.00 | $25.00 | 1M |
| 23 | OpenAI: GPT-5.6 Sol | OOpenAI | 5.00/5.0 | $5.00 | $30.00 | 1.1M |
| 24 | Anthropic: Claude Opus 4.8 (Fast) | AAnthropic | 5.00/5.0 | $10.00 | $50.00 | 1M |
| 25 | Qwen: Qwen3.5-9B | QQwen | 4.67/5.0 | $0.100 | $0.150 | 262K |
| 26 | NVIDIA: Nemotron 3 Nano 30B A3B | NNVIDIA | 4.67/5.0 | $0.050 | $0.200 | 262K |
| 27 | GLM-4.7 Flash | ZZhipu AI | 4.67/5.0 | $0.060 | $0.400 | 203K |
| 28 | Kwaipilot: KAT-Coder-Pro V2 | KKwaipilot | 4.67/5.0 | $0.300 | $1.20 | 256K |
| 29 | Qwen: Qwen3.5 Plus 2026-04-20 | QQwen | 4.67/5.0 | $0.300 | $1.80 | 1M |
| 30 | Gemini 2.5 Flash | GGoogle | 4.67/5.0 | $0.300 | $2.50 | 1.0M |
| 31 | OpenAI: GPT-5.6 Luna Pro | OOpenAI | 4.67/5.0 | $1.00 | $6.00 | 1.1M |
| 32 | GPT-5.5 | OOpenAI | 4.67/5.0 | $5.00 | $30.00 | 1.1M |
| 33 | GPT-5 Nano | OOpenAI | 4.33/5.0 | $0.050 | $0.400 | 400K |
| 34 | MiniMax: MiniMax M2.1 | MMinimax | 4.33/5.0 | $0.300 | $1.20 | 205K |
| 35 | GPT-5.4 Nano | OOpenAI | 4.33/5.0 | $0.200 | $1.25 | 400K |
| 36 | Qwen: Qwen3.7 Plus | QQwen | 4.33/5.0 | $0.320 | $1.28 | 1M |
| 37 | GPT-5 Mini | OOpenAI | 4.33/5.0 | $0.250 | $2.00 | 400K |
| 38 | ByteDance Seed: Seed-2.0-Lite | BBytedance-seed | 4.33/5.0 | $0.250 | $2.00 | 262K |
| 39 | o4 Mini | OOpenAI | 4.33/5.0 | $1.10 | $4.40 | 200K |
| 40 | OpenAI: GPT-5.6 Sol Pro | OOpenAI | 4.33/5.0 | $5.00 | $30.00 | 1.1M |
| 41 | Anthropic: Claude Fable 5 | AAnthropic | 4.33/5.0 | $10.00 | $50.00 | 1M |
| 42 | inclusionAI: Ling-2.6-flash | IInclusionai | 4.00/5.0 | $0.010 | $0.030 | 262K |
| 43 | StepFun: Step 3.5 Flash | SStepfun | 4.00/5.0 | $0.100 | $0.300 | 262K |
| 44 | Gemma 4 31B | GGoogle | 4.00/5.0 | $0.120 | $0.350 | 262K |
| 45 | DeepSeek V3.2 | DDeepSeek | 4.00/5.0 | $0.214 | $0.322 | 131K |
| 46 | Mistral Small 4 | MMistral | 4.00/5.0 | $0.150 | $0.600 | 262K |
| 47 | GPT-4o-mini | OOpenAI | 4.00/5.0 | $0.150 | $0.600 | 128K |
| 48 | inclusionAI: Ling-2.6-1T | IInclusionai | 4.00/5.0 | $0.075 | $0.625 | 262K |
| 49 | DeepSeek V4 Pro | DDeepSeek | 4.00/5.0 | $0.435 | $0.870 | 1.0M |
| 50 | MiMo-V2.5-Pro | XXiaomi | 4.00/5.0 | $0.435 | $0.870 | 1.0M |
| 51 | MiniMax: MiniMax M2.7 | MMinimax | 4.00/5.0 | $0.240 | $0.960 | 205K |
| 52 | Qwen: Qwen3.6 Flash | QQwen | 4.00/5.0 | $0.188 | $1.13 | 1M |
| 53 | MiniMax: MiniMax M3 | MMinimax | 4.00/5.0 | $0.300 | $1.20 | 1.0M |
| 54 | GPT-4.1 Mini | OOpenAI | 4.00/5.0 | $0.400 | $1.60 | 1.0M |
| 55 | Qwen: Qwen3.6 Plus | QQwen | 4.00/5.0 | $0.325 | $1.95 | 1M |
| 56 | Mistral Medium 3.1 | MMistral | 4.00/5.0 | $0.400 | $2.00 | 131K |
| 57 | R1 0528 | DDeepSeek | 4.00/5.0 | $0.500 | $2.15 | 164K |
| 58 | MiniMax: MiniMax M1 | MMinimax | 4.00/5.0 | $0.400 | $2.20 | 1M |
| 59 | NVIDIA: Nemotron 3 Ultra | NNVIDIA | 4.00/5.0 | $0.500 | $2.20 | 1M |
| 60 | Qwen 3.7 Max | QQwen | 4.00/5.0 | $1.25 | $3.75 | 1M |
| 61 | GPT-5.4 Mini | OOpenAI | 4.00/5.0 | $0.750 | $4.50 | 400K |
| 62 | Claude Haiku 4.5 | AAnthropic | 4.00/5.0 | $1.00 | $5.00 | 200K |
| 63 | Grok 4.5 | XXAI | 4.00/5.0 | $2.00 | $6.00 | 500K |
| 64 | Mistral Medium 3.5 | MMistral | 4.00/5.0 | $1.50 | $7.50 | 262K |
| 65 | Gemini 3.5 Flash | GGoogle | 4.00/5.0 | $1.50 | $9.00 | 1.0M |
| 66 | GPT-5 | OOpenAI | 4.00/5.0 | $1.25 | $10.00 | 400K |
| 67 | GPT-5.1 | OOpenAI | 4.00/5.0 | $1.25 | $10.00 | 400K |
| 68 | Gemini 3.1 Pro Preview | GGoogle | 4.00/5.0 | $2.00 | $12.00 | 1.0M |
| 69 | Grok 4 | XXAI | 4.00/5.0 | $3.00 | $15.00 | 256K |
| 70 | Grok 3 | XXAI | 4.00/5.0 | $3.00 | $15.00 | 131K |
| 71 | Claude Opus 4.7 | AAnthropic | 4.00/5.0 | $5.00 | $25.00 | 1M |
| 72 | Qwen: Qwen3 235B A22B Instruct 2507 | QQwen | 3.67/5.0 | $0.090 | $0.100 | 262K |
| 73 | Poolside: Laguna XS 2.1 | PPoolside | 3.67/5.0 | $0.060 | $0.120 | 262K |
| 74 | DeepSeek V4 Flash | DDeepSeek | 3.67/5.0 | $0.077 | $0.154 | 1.0M |
| 75 | Gemma 4 26B A4B | GGoogle | 3.67/5.0 | $0.060 | $0.330 | 262K |
| 76 | Gemini 2.5 Flash Lite | GGoogle | 3.67/5.0 | $0.100 | $0.400 | 1.0M |
| 77 | NVIDIA: Nemotron 3 Super | NNVIDIA | 3.67/5.0 | $0.080 | $0.450 | 1M |
| 78 | Grok 4.1 Fast | XXAI | 3.67/5.0 | $0.200 | $0.500 | 2M |
| 79 | Grok 3 Mini | XXAI | 3.67/5.0 | $0.300 | $0.500 | 131K |
| 80 | Llama 4 Maverick | MMeta | 3.67/5.0 | $0.150 | $0.600 | 1.0M |
| 81 | Qwen: Qwen3.6 35B A3B | QQwen | 3.67/5.0 | $0.140 | $1.00 | 262K |
| 82 | Qwen: Qwen3.5-35B-A3B | QQwen | 3.67/5.0 | $0.140 | $1.00 | 262K |
| 83 | MiniMax: MiniMax M2 | MMinimax | 3.67/5.0 | $0.255 | $1.02 | 205K |
| 84 | StepFun: Step 3.7 Flash | SStepfun | 3.67/5.0 | $0.200 | $1.15 | 256K |
| 85 | ByteDance Seed: Seed 1.6 | BBytedance-seed | 3.67/5.0 | $0.250 | $2.00 | 262K |
| 86 | R1 | DDeepSeek | 3.67/5.0 | $0.700 | $2.50 | 164K |
| 87 | Grok 4.3 | XXAI | 3.67/5.0 | $1.25 | $2.50 | 1M |
| 88 | Grok 4.20 | XXAI | 3.67/5.0 | $1.25 | $2.50 | 2M |
| 89 | Gemini 3 Flash Preview | GGoogle | 3.67/5.0 | $0.500 | $3.00 | 1.0M |
| 90 | GPT-4.1 | OOpenAI | 3.67/5.0 | $2.00 | $8.00 | 1.0M |
| 91 | o3 | OOpenAI | 3.67/5.0 | $2.00 | $8.00 | 200K |
| 92 | Gemini 2.5 Pro | GGoogle | 3.67/5.0 | $1.25 | $10.00 | 1.0M |
| 93 | OpenAI: gpt-oss-120b | OOpenAI | 3.33/5.0 | $0.036 | $0.180 | 131K |
| 94 | Ministral 3 8B 2512 | MMistral | 3.33/5.0 | $0.150 | $0.150 | 262K |
| 95 | Qwen: Qwen3 30B A3B Instruct 2507 | QQwen | 3.33/5.0 | $0.048 | $0.193 | 131K |
| 96 | Ministral 3 14B 2512 | MMistral | 3.33/5.0 | $0.200 | $0.200 | 262K |
| 97 | GPT-4.1 Nano | OOpenAI | 3.33/5.0 | $0.100 | $0.400 | 1.0M |
| 98 | Inception: Mercury 2 | IInception | 3.33/5.0 | $0.250 | $0.750 | 128K |
| 99 | DeepSeek V3.1 | DDeepSeek | 3.33/5.0 | $0.210 | $0.790 | 164K |
| 100 | Arcee AI: Trinity Large Thinking | AArcee-ai | 3.33/5.0 | $0.250 | $0.800 | 262K |
| 101 | MiniMax: MiniMax M2.5 | MMinimax | 3.33/5.0 | $0.150 | $0.900 | 205K |
| 102 | DeepSeek V3.1 Terminus | DDeepSeek | 3.33/5.0 | $0.270 | $0.950 | 164K |
| 103 | Grok Code Fast 1 | XXAI | 3.33/5.0 | $0.200 | $1.50 | 256K |
| 104 | Devstral 2 2512 | MMistral | 3.33/5.0 | $0.400 | $2.00 | 262K |
| 105 | xAI: Grok Build 0.1 | XXAI | 3.33/5.0 | $1.00 | $2.00 | 256K |
| 106 | GPT-4o | OOpenAI | 3.33/5.0 | $2.50 | $10.00 | 128K |
| 107 | IBM: Granite 4.0 Micro | IIbm-granite | 3.00/5.0 | $0.017 | $0.112 | 131K |
| 108 | Ministral 3 3B 2512 | MMistral | 3.00/5.0 | $0.100 | $0.100 | 131K |
| 109 | OpenAI: gpt-oss-20b | OOpenAI | 3.00/5.0 | $0.030 | $0.140 | 131K |
| 110 | ByteDance Seed: Seed 1.6 Flash | BBytedance-seed | 3.00/5.0 | $0.075 | $0.300 | 262K |
| 111 | Llama 4 Scout | MMeta | 3.00/5.0 | $0.100 | $0.300 | 10M |
| 112 | Llama 3.3 70B Instruct | MMeta | 3.00/5.0 | $0.100 | $0.320 | 131K |
| 113 | Mistral Large 3 2512 | MMistral | 3.00/5.0 | $0.500 | $1.50 | 262K |
| 114 | IBM: Granite 4.1 8B | IIbm-granite | 2.67/5.0 | $0.050 | $0.100 | 131K |
| 115 | Mistral Small 3.2 24B | MMistral | 2.67/5.0 | $0.075 | $0.200 | 128K |
| 116 | Qwen: Qwen3 Coder 30B A3B Instruct | QQwen | 2.67/5.0 | $0.070 | $0.270 | 160K |
| 117 | Codestral 2508 | MMistral | 2.67/5.0 | $0.300 | $0.900 | 256K |
| 118 | MiniMax: MiniMax M2-her | MMinimax | 2.67/5.0 | $0.300 | $1.20 | 66K |
| 119 | Mistral Small 3.1 24B | MMistral | 2.33/5.0 | $0.351 | $0.555 | 128K |
| 120 | MiniMax: MiniMax-01 | MMinimax | 2.33/5.0 | $0.200 | $1.10 | 1.0M |
Pricing — top 5 for chatbots
X
5.00/5.0
X
5.00/5.0
B
5.00/5.0
I
5.00/5.0
N
5.00/5.0
The best AI for chatbots changes every month.
We'll email you when rankings shift, new models hit the top 5, or pricing cuts reshuffle the value leaders.
Get notified when models change
Price drops, new models, benchmark updates. One email per change, no spam.