The LLM benchmark aggregator.

OpenChat 3.5

OpenChat

Strongest in Human preference (#294 of 350), weakest in Human preference (#294 of 350). Above par in 0 of 2 scopes. Among the models it meets almost everywhere, it finishes behind Gemini 4 Argon and Muse Wonder and ahead of Gemma 1.1 7B IT and Snowflake Arctic Instruct.

§ 1 · Profile

What it is good at

Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.

Human preference35.9−32.7#294/3501/1

§ 2 · Head to head

What it beats, and what beats it

The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for OpenChat 3.5, left for the other.

Koala 13Bwon 2 · lost 0

OpenAssistant Pythia 12Bwon 2 · lost 0

RWKV-4 Raven 14Bwon 2 · lost 0

Alpaca 13Bwon 2 · lost 0

OLMo 7B Instructwon 2 · lost 0

FastChat-T5 3Bwon 2 · lost 0

ChatGLM 6Bwon 2 · lost 0

ChatGLM3 6Bwon 2 · lost 0

MPT 7B Chatwon 2 · lost 0

StableLM Tuned Alpha 7Bwon 2 · lost 0

Dolly 2.0 12Bwon 2 · lost 0

ChatGLM2 6Bwon 2 · lost 0

GPT4All 13B Snoozywon 2 · lost 0

LLaMA 13Bwon 2 · lost 0

Qwen1.5 4B Chatwon 2 · lost 0

Gemma 2B ITwon 2 · lost 0

Llama 2 7B Chatwon 2 · lost 0

Llama 3.2 1B Instructwon 2 · lost 0

Mistral 7B Instructwon 2 · lost 0

Vicuna 7Bwon 2 · lost 0

SmolLM2 1.7B Instructwon 2 · lost 0

Gemma 1.1 2B ITwon 2 · lost 0

Code Llama 70B Instructwon 2 · lost 0

StripedHyena Nous 7Bwon 2 · lost 0

Zephyr 7B Alphawon 2 · lost 0

Guanaco 33Bwon 2 · lost 0

Phi-3 Mini 128K Instructwon 2 · lost 0

Zephyr 7B Betawon 2 · lost 0

Code Llama 34B Instructwon 2 · lost 0

Gemma 7B ITwon 2 · lost 0

PaLM 2won 2 · lost 0

Qwen 14B Chatwon 2 · lost 0

Vicuna 13Bwon 2 · lost 0

Llama 2 13B Chatwon 2 · lost 0

Phi-3 Mini 4K Instructwon 2 · lost 0

Qwen1.5 7B Chatwon 2 · lost 0

Falcon 180B Chatwon 2 · lost 0

Mistral 7B Instruct v0.2won 2 · lost 0

WizardLM 13Bwon 2 · lost 0

MPT 30B Chatwon 2 · lost 0

Dolphin 2.2.1 Mistral 7Bwon 2 · lost 0

SOLAR 10.7B Instruct v1.0won 2 · lost 0

Llama 2 70B SteerLM Chatwon 2 · lost 0

Granite 3.0 2B Instructwon 2 · lost 0

Nous Hermes 2 Mixtral 8x7B DPOwon 2 · lost 0

Llama 3.2 3B Instructwon 2 · lost 0

Starling LM 7B Alphawon 2 · lost 0

Llama 2 70B Chatwon 2 · lost 0

Phi-3 Small 8K Instructwon 2 · lost 0

Starling LM 7B Betawon 2 · lost 0

Vicuna 33Bwon 2 · lost 0

OpenHermes 2.5 Mistral 7Bwon 2 · lost 0

Tulu 2 DPO 70Bwon 2 · lost 0

Granite 3.1 2B Instructwon 2 · lost 0

Snowflake Arctic Instructwon 2 · lost 0

Gemma 1.1 7B ITwon 2 · lost 0

Granite 3.0 8B Instructwon 0 · lost 2

Yi 34B Chatwon 0 · lost 2

WizardLM 70Bwon 0 · lost 2

DeepSeek LLM 67B Chatwon 0 · lost 2

InternLM2.5 20B Chatwon 0 · lost 2

Qwen1.5 14B Chatwon 0 · lost 2

DBRX Instructwon 0 · lost 2

Mixtral 8x7B Instructwon 0 · lost 2

Phi-3 Medium 4K Instructwon 0 · lost 2

Gemma 2 2B ITwon 0 · lost 2

Qwen1.5 32B Chatwon 0 · lost 2

GPT-3.5 Turbowon 0 · lost 2

Granite 3.1 8B Instructwon 0 · lost 2

Llama 3.1 8B Instructwon 0 · lost 2

Yi 1.5 34B Chatwon 0 · lost 2

Zephyr ORPO 141B A35B v0.1won 0 · lost 2

Llama 3.1 Tulu 3 8Bwon 0 · lost 2

Mistral Mediumwon 0 · lost 2

Aya Expanse 8Bwon 0 · lost 2

Llama 3 8B Instructwon 0 · lost 2

Gemini Prowon 0 · lost 2

Reka Flash 21Bwon 0 · lost 2

Mixtral 8x22B Instructwon 0 · lost 2

Hunyuan Standard 256Kwon 0 · lost 2

Qwen1.5 72B Chatwon 0 · lost 2

Qwen1.5 110B Chatwon 0 · lost 2

Reka Flash 21B (Online, 20240226)won 0 · lost 2

Gemini Pro (Dev API)won 0 · lost 2

Ministral 8Bwon 0 · lost 2

Jamba 1.5 Miniwon 0 · lost 2

Amazon Nova Micro 1.0won 0 · lost 2

Command R (08-2024)won 0 · lost 2

OLMo 2 32B Instructwon 0 · lost 2

Phi 4won 0 · lost 2

Gemini 1.5 Flash-8Bwon 0 · lost 2

Amazon Nova Lite 1.0won 0 · lost 2

Claude 3 Haikuwon 0 · lost 2

Qwen2 72B Instructwon 0 · lost 2

DeepSeek Coder V2won 0 · lost 2

Gemma 2 9B ITwon 0 · lost 2

Aya Expanse 32Bwon 0 · lost 2

Qwen2.5 Coder 32B Instructwon 0 · lost 2

Reka Flashwon 0 · lost 2

Mistral Small 24B Instructwon 0 · lost 2

GLM-4won 0 · lost 2

GPT-4won 0 · lost 2

Command R+ (08-2024)won 0 · lost 2

Llama 3 70B Instructwon 0 · lost 2

Nemotron-4 340B Instructwon 0 · lost 2

Gemma 2 9B IT SimPOwon 0 · lost 2

Claude 3 Sonnetwon 0 · lost 2

Olmo 3.1 32B Thinkwon 0 · lost 2

Llama 3.1 Tulu 3 70Bwon 0 · lost 2

Granite 4.0 H Smallwon 0 · lost 2

Llama 3.1 Nemotron 51B Instructwon 0 · lost 2

Reka Corewon 0 · lost 2

Gemma 2 27B ITwon 0 · lost 2

Amazon Nova Pro 1.0won 0 · lost 2

Jamba 1.5 Largewon 0 · lost 2

Granite 4.2 8Bwon 0 · lost 2

Granite 4.2 3Bwon 0 · lost 2

Llama 3.1 70B Instructwon 0 · lost 2

Hunyuan Large Visionwon 0 · lost 2

Llama 3.1 Nemotron 70B Instructwon 0 · lost 2

Qwen2.5 72B Instructwon 0 · lost 2

Mistral Small 3.1 24B Instructwon 0 · lost 2

Gemma 3 4B ITwon 0 · lost 2

Granite 4.1 8Bwon 0 · lost 2

Magistral Mediumwon 0 · lost 2

Mistral Largewon 0 · lost 2

Olmo 3 32B Thinkwon 0 · lost 2

Mercurywon 0 · lost 2

Athene 70Bwon 0 · lost 2

Grok 2 miniwon 0 · lost 2

Gemini 1.5 Flashwon 0 · lost 2

Hunyuan Standardwon 0 · lost 2

Mistral Large 2won 0 · lost 2

NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)won 0 · lost 2

Athene V2 Chatwon 0 · lost 2

Qwen2.5 Pluswon 0 · lost 2

GPT-4o miniwon 0 · lost 2

Llama 3.3 70B Instructwon 0 · lost 2

Gemma 3n E4B ITwon 0 · lost 2

Qwen Maxwon 0 · lost 2

GPT OSS 20Bwon 0 · lost 2

Step-1o Turbowon 0 · lost 2

Claude 3 Opuswon 0 · lost 2

Llama 4 Scout Instructwon 0 · lost 2

GPT-4.1 nanowon 0 · lost 2

Molmo 2 8Bwon 0 · lost 2

Ring Flash 2.0won 0 · lost 2

DeepSeek V2.5won 0 · lost 2

Claude 3.5 Haikuwon 0 · lost 2

GPT-4 Turbowon 0 · lost 2

Hunyuan Largewon 0 · lost 2

Llama 4 Maverick Instructwon 0 · lost 2

Yi Lightningwon 0 · lost 2

Llama 3.3 Nemotron Super 49B v1won 0 · lost 2

Olmo 3.1 32B Instructwon 0 · lost 2

Step-2 16Kwon 0 · lost 2

Amazon Nova 2 Litewon 0 · lost 2

Gemini Advancedwon 0 · lost 2

QwQ 32Bwon 0 · lost 2

Llama 3.1 405B Instruct (BF16)won 0 · lost 2

Grok 2won 0 · lost 2

GPT-4owon 0 · lost 2

O1 Miniwon 0 · lost 2

GPT-5 nanowon 0 · lost 2

Granite 4.2 30Bwon 0 · lost 2

Hunyuan Turbowon 0 · lost 2

Mercury 2won 0 · lost 2

Gemma 3 12B ITwon 0 · lost 2

Llama 3.3 Nemotron Super 49B v1.5won 0 · lost 2

GLM-4 Pluswon 0 · lost 2

Ling Flash 2.0won 0 · lost 2

MiniMax M2won 0 · lost 2

Qwen Pluswon 0 · lost 2

Qwen3 32Bwon 0 · lost 2

Llama 3.1 Nemotron Ultra 253B v1won 0 · lost 2

Step 3won 0 · lost 2

Gemini 1.5 Prowon 0 · lost 2

GLM-4.5Vwon 0 · lost 2

GPT OSS 120Bwon 0 · lost 2

NVIDIA-Nemotron-3.5-Lightning-30B-A3B (NVFP4)won 0 · lost 2

Gemini 2.0 Flash-Litewon 0 · lost 2

Command A (03-2025)won 0 · lost 2

INTELLECT 3won 0 · lost 2

Mistral Small 3.2won 0 · lost 2

NVIDIA Nemotron 3 Super 120B A12Bwon 0 · lost 2

Gemini 2.0 Flashwon 0 · lost 2

O3 Miniwon 0 · lost 2

Grok 3 Miniwon 0 · lost 2

MiniMax M1won 0 · lost 2

GLM-4.7 Flashwon 0 · lost 2

Gemma 3 27B ITwon 0 · lost 2

Trinity Largewon 0 · lost 2

Qwen3 Next 80B A3B Thinkingwon 0 · lost 2

GLM-4.5 Airwon 0 · lost 2

Qwen2.5 Maxwon 0 · lost 2

Claude 3.5 Sonnetwon 0 · lost 2

Gemini 2.5 Flash-Litewon 0 · lost 2

GLM-4.6Vwon 0 · lost 2

Qwen3 30B A3B Instructwon 0 · lost 2

Hunyuan TurboSwon 0 · lost 2

GPT-4.1 miniwon 0 · lost 2

MiniMax M2.1won 0 · lost 2

MiMo V2 Flashwon 0 · lost 2

Hunyuan T1won 0 · lost 2

Mistral Medium 3won 0 · lost 2

Qwen3 Coder 480B A35B Instructwon 0 · lost 2

Solar Pro 4won 0 · lost 2

Claude 3.7 Sonnetwon 0 · lost 2

GPT-5 miniwon 0 · lost 2

MiniMax M2.5won 0 · lost 2

O4 Miniwon 0 · lost 2

Step 3.5 Flashwon 0 · lost 2

Hunyuan Vision 1.5won 0 · lost 2

Qwen3.5 35B A3Bwon 0 · lost 2

Qwen3 VL 235B A22B Thinkingwon 0 · lost 2

DeepSeek V3won 0 · lost 2

Qwen3.5 Flashwon 0 · lost 2

Qwen3 Next 80B A3B Instructwon 0 · lost 2

Qwen3 235B A22B Thinkingwon 0 · lost 2

LongCat Flash Chatwon 0 · lost 2

GPT-5.4 nanowon 0 · lost 2

O1won 0 · lost 2

Claude Sonnet 4won 0 · lost 2

Grok 4 Fastwon 0 · lost 2

Inkling Smallwon 0 · lost 2

Mistral Medium 3.1won 0 · lost 2

Qwen3.5 27Bwon 0 · lost 2

Gemini 2.5 Flashwon 0 · lost 2

GLM-4.5won 0 · lost 2

Grok 3won 0 · lost 2

Grok 4won 0 · lost 2

Qwen3 VL 235B A22B Instructwon 0 · lost 2

NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)won 0 · lost 2

GPT-4.1won 0 · lost 2

Mistral Large 3won 0 · lost 2

MiniMax M2.7won 0 · lost 2

Claude Haiku 4.5won 0 · lost 2

DeepSeek V3.1 Terminuswon 0 · lost 2

DeepSeek V3.1won 0 · lost 2

Qwen3.5 122B A10Bwon 0 · lost 2

Kimi K2won 0 · lost 2

DeepSeek R1won 0 · lost 2

DeepSeek V3.2won 0 · lost 2

Qwen3 235B A22B Instructwon 0 · lost 2

Qwen3 Maxwon 0 · lost 2

GLM-4.6won 0 · lost 2

Muse Glimmerwon 0 · lost 2

Nova Experimental Chatwon 0 · lost 2

NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4)won 0 · lost 2

Mistral Medium 3.5won 0 · lost 2

GPT-5 Chatwon 0 · lost 2

Claude Opus 4won 0 · lost 2

Kimi K2 Thinking Turbowon 0 · lost 2

Grok 4.1 Fastwon 0 · lost 2

Kimi K2.5 (Instant)won 0 · lost 2

MiMo V2 Omniwon 0 · lost 2

O3won 0 · lost 2

Mistral Large 4won 0 · lost 2

GLM-5V Turbowon 0 · lost 2

Gemini 3.1 Flash-Litewon 0 · lost 2

MiMo V2.5won 0 · lost 2

GPT-5won 0 · lost 2

eam 1.0 501B A23won 0 · lost 2

Gemma 4 26B A4Bwon 0 · lost 2

Qwen3.8 27Bwon 0 · lost 2

GPT-5.2won 0 · lost 2

DeepSeek V4 Flashwon 0 · lost 2

GLM-4.7won 0 · lost 2

Inklingwon 0 · lost 2

MiniMax M3won 0 · lost 2

GPT-6 Lunawon 0 · lost 2

Qwen3.5 397B A17Bwon 0 · lost 2

Grok 4.7won 0 · lost 2

Grok 4.3won 0 · lost 2

Qwen3.6 Pluswon 0 · lost 2

ChatGPT-4owon 0 · lost 2

GPT-4.5won 0 · lost 2

Gemini 2.5 Prowon 0 · lost 2

Step 5won 0 · lost 2

ERNIE 5.0won 0 · lost 2

GPT-5.4 miniwon 0 · lost 2

MiMo V2 Prowon 0 · lost 2

MiMo V2.6 Flashwon 0 · lost 2

GPT-5.3 Chatwon 0 · lost 2

Kimi K2.5won 0 · lost 2

Claude Opus 4.1won 0 · lost 2

Gemma 4 31Bwon 0 · lost 2

GPT-5.6 Lunawon 0 · lost 2

Hy3won 0 · lost 2

Grok 4.6won 0 · lost 2

Gemini 3.5 Flash-Litewon 0 · lost 2

GPT-5.1won 0 · lost 2

Qwen3.7 Pluswon 0 · lost 2

Claude Sonnet 4.5 (High, 32K, 20250929)won 0 · lost 2

Dola Seed 2.0 Prowon 0 · lost 2

GLM-5won 0 · lost 2

GPT-6 Solwon 0 · lost 2

Qwen3.6 Maxwon 0 · lost 2

Kimi K2.6won 0 · lost 2

Claude Sonnet 5won 0 · lost 2

DeepSeek-V4-Pro (High, 20260813)won 0 · lost 2

Qwen3.5 Maxwon 0 · lost 2

GLM-5.1won 0 · lost 2

Grok 4.5won 0 · lost 2

Grok 4.1won 0 · lost 2

MiMo V2.5 Prowon 0 · lost 2

ERNIE 5.1won 0 · lost 2

GPT-5.6 Terrawon 0 · lost 2

Grok 4.20 Multi-Agentwon 0 · lost 2

Grok 4.20 (Reasoning, 0309)won 0 · lost 2

Claude Sonnet 4.6won 0 · lost 2

GPT-5.5 Instantwon 0 · lost 2

Gemini 3 Flashwon 0 · lost 2

Qwen3.7 Maxwon 0 · lost 2

Claude Opus 4.5 (High, 32K, 20251101)won 0 · lost 2

DeepSeek V4.1 Flashwon 0 · lost 2

Grok 4.20 1won 0 · lost 2

GLM-5.3 Flashwon 0 · lost 2

GPT-5.4won 0 · lost 2

GPT-5.2 Chatwon 0 · lost 2

GPT-6 Astrawon 0 · lost 2

GLM-5.2won 0 · lost 2

Claude Sonnet 5.5won 0 · lost 2

Gemini 3.5 Flashwon 0 · lost 2

GPT-6.1 Solwon 0 · lost 2

MiMo V2.6 Prowon 0 · lost 2

GLM-5.3won 0 · lost 2

Claude Opus 4.8won 0 · lost 2

GPT-5.5won 0 · lost 2

Qwen3.8 Maxwon 0 · lost 2

Gemini 3.6 Flashwon 0 · lost 2

GPT-5.6 Solwon 0 · lost 2

Gemini 3 Prowon 0 · lost 2

Gemini 3.1 Prowon 0 · lost 2

Kimi K3won 0 · lost 2

Muse Sparkwon 0 · lost 2

Gemini 3.7 Flashwon 0 · lost 2

Muse Spark 1.1won 0 · lost 2

Claude Opus 5won 0 · lost 2

Muse Spark 1.2won 0 · lost 2

Muse Spark 1.3won 0 · lost 2

Gemini 3.8 Flashwon 0 · lost 2

Claude Opus 4.7won 0 · lost 2

Claude Fable 5.1won 0 · lost 2

Claude Opus 4.6won 0 · lost 2

Claude Fable 5won 0 · lost 2

Claude Opus 5.5won 0 · lost 2

Muse Wonderwon 0 · lost 2

Gemini 4 Argonwon 0 · lost 2

§ 3 · Sources

Where the numbers come from

1 publication, 1 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-10-21

LMArena Text 1183

Badge

[![PublicAI Index](https://publicai.io/model-index/badge?model=openchat-3-5)](https://publicai.io/model-index/m/openchat-3-5)