Value ranking
Best value on Chatbot Arena Elo
As of October 25, 2026, the best value on Chatbot Arena Elo is DeepSeek V4.1 Flash, at 4155.50 normalized points per dollar of input price ($0.02 per million tokens, score 83.1).
Crowdsourced pairwise human preference rankings of LLM responses. Higher Elo means more frequently preferred by users.
“Value” is normalized benchmark score (0–100 for this leaderboard cohort) divided by input price per million tokens. Higher means more capability per dollar on this axis only — always sanity-check latency, context length, and your real workload.
- 1DeepSeek V4.1 FlashDeepSeek4155.5083.1 / $0.02/M
- 2gpt-oss-20bOpenAI1916.6734.5 / $0.02/M
- 3GPT-5 nanoOpenAI1738.0043.5 / $0.03/M
- 4GPT-6 LunaOpenAI1255.6062.8 / $0.05/M
- 5Gemini 2.5 Flash LiteGoogle1139.6057.0 / $0.05/M
- 6Qwen3.5-FlashAlibaba (Qwen)994.1564.6 / $0.07/M
- 7Gemma 3 12BGoogle947.0047.4 / $0.05/M
- 8Gemma 3 4BGoogle885.2535.4 / $0.04/M
- 9GLM 4.7 FlashZhipu AI (GLM)857.8551.9 / $0.06/M
- 10Nemotron 3 Nano 30B A3BNVIDIA852.1751.1 / $0.06/M
- 11DeepSeek V4 Flash 0423DeepSeek815.3874.2 / $0.09/M
- 12Qwen3 235BAlibaba (Qwen)785.6770.7 / $0.09/M
- 13Qwen3 Next 80B A3B InstructAlibaba (Qwen)779.0070.1 / $0.09/M
- 14GPT-5.6 LunaOpenAI739.8074.0 / $0.10/M
- 15Qwen3 30B A3B Instruct 2507Alibaba (Qwen)677.3361.0 / $0.09/M
- 16Gemma 3 27BGoogle672.6353.8 / $0.08/M
- 17Nemotron 3.5 LightningNVIDIA662.0046.3 / $0.07/M
- 18Step 3.5 FlashStepFun661.9066.2 / $0.10/M
- 19Claude Haiku 5.5Anthropic656.1065.6 / $0.10/M
- 20MiMo-V2.5Xiaomi (MiMo)614.3773.1 / $0.12/M
- 21Qwen3 32BAlibaba (Qwen)612.0049.0 / $0.08/M
- 22GPT-5.4 NanoOpenAI578.0057.8 / $0.10/M
- 23Hy3Tencent (Hunyuan)575.7676.0 / $0.13/M
- 24MiMo-V2.6-FlashXiaomi (MiMo)569.0079.7 / $0.14/M
- 25GLM 5.3 FlashZhipu AI (GLM)568.8785.3 / $0.15/M
AI Model Analyzer does not recommend specific vendors; rankings are derived from public data only.