Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Command R (08-2024)

Cohere

Strongest in Safe-prompt compliance (#58 of 82), weakest in Safety (#299 of 331). Above par in 0 of 8 scopes. Among the models it meets almost everywhere, it finishes behind Gemini 3 Pro and Claude Sonnet 4.5 (High, 32K, 20250929) and ahead of Nous Hermes 2 Mixtral 8x7B DPO and Gemma 7B IT.

§ 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.

Professional43.7#156/188
Legal35#160/164
Human preference42.4#262/350
Human preference42.4#262/350
Safety43#299/331
Safe-prompt compliance49.5#58/82
Harm refusal42.2#271/296
Fairness35.4#290/296

§ 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 Command R (08-2024), left for the other.

DBRX Instructwon 5 · lost 1
GPT-3.5 Turbowon 4 · lost 2
Mixtral 8x7B Instructwon 5 · lost 3
SmolLM2 1.7B Instructwon 3 · lost 2
Gemma 7B ITwon 3 · lost 2
Nous Hermes 2 Mixtral 8x7B DPOwon 3 · lost 2
DeepSeek LLM 67B Chatwon 3 · lost 3
Llama 3.1 8B Instructwon 3 · lost 4
Jamba 1.5 Miniwon 3 · lost 4
Gemma 2B ITwon 2 · lost 3
Llama 3.2 1B Instructwon 2 · lost 3
Phi-3 Mini 128K Instructwon 2 · lost 3
Zephyr 7B Betawon 2 · lost 3
Phi-3 Mini 4K Instructwon 2 · lost 3
Mistral 7B Instruct v0.2won 2 · lost 3
Granite 3.0 2B Instructwon 2 · lost 3
Llama 3.2 3B Instructwon 2 · lost 3
Phi-3 Small 8K Instructwon 2 · lost 3
Starling LM 7B Betawon 2 · lost 3
Granite 3.1 2B Instructwon 2 · lost 3
Granite 3.0 8B Instructwon 2 · lost 3
Qwen1.5 14B Chatwon 2 · lost 3
Phi-3 Medium 4K Instructwon 2 · lost 3
Gemma 2 2B ITwon 2 · lost 3
Granite 3.1 8B Instructwon 2 · lost 3
Llama 3.1 Tulu 3 8Bwon 2 · lost 3
Qwen3 30B A3B Instructwon 2 · lost 3
Llama 3 8B Instructwon 2 · lost 4
Qwen1.5 72B Chatwon 2 · lost 4
Claude 3 Haikuwon 2 · lost 4
Mixtral 8x22B Instructwon 2 · lost 5
Command R+ (08-2024)won 2 · lost 6
Gemini 1.5 Flashwon 2 · lost 6
GPT OSS 20Bwon 2 · lost 6
Gemini 1.5 Prowon 2 · lost 6
Jamba 1.6 Miniwon 1 · lost 4
Jamba 1.6 Largewon 1 · lost 4
Grok 4 Fastwon 1 · lost 4
OLMo 2 32B Instructwon 1 · lost 5
Claude 3 Sonnetwon 1 · lost 5
Claude 3 Opuswon 1 · lost 5
Gemini 2.0 Flash-Litewon 1 · lost 5
Jamba 1.5 Largewon 1 · lost 6
Llama 3.1 70B Instructwon 1 · lost 6
GPT-4o miniwon 1 · lost 6
Claude 3.5 Haikuwon 1 · lost 6
Command A (03-2025)won 1 · lost 6
Grok 4.1 Fastwon 1 · lost 6
Llama 4 Scout Instructwon 1 · lost 7
GPT-4.1 nanowon 1 · lost 7
Llama 4 Maverick Instructwon 1 · lost 7
GPT-5 nanowon 1 · lost 7
GPT OSS 120Bwon 1 · lost 7
Grok 4won 1 · lost 7
Claude Haiku 4.5won 1 · lost 7
DeepSeek R1won 1 · lost 7
Gemini 2.0 Prowon 0 · lost 5
Ling 3.0 Flashwon 0 · lost 5
Kimi K2 Thinkingwon 0 · lost 5
Phi 4won 0 · lost 5
Mistral Small 24B Instructwon 0 · lost 5
GPT-4won 0 · lost 5
Granite 4.0 H Smallwon 0 · lost 5
Gemma 3 4B ITwon 0 · lost 5
Magistral Mediumwon 0 · lost 5
Qwen Maxwon 0 · lost 5
QwQ 32Bwon 0 · lost 5
Mercury 2won 0 · lost 5
Gemma 3 12B ITwon 0 · lost 5
MiniMax M2won 0 · lost 5
NVIDIA Nemotron 3 Super 120B A12Bwon 0 · lost 5
Gemma 3 27B ITwon 0 · lost 5
Trinity Largewon 0 · lost 5
MiniMax M2.1won 0 · lost 5
MiniMax M2.5won 0 · lost 5
Qwen3.5 35B A3Bwon 0 · lost 5
Qwen3.5 Flashwon 0 · lost 5
GPT-5.4 nanowon 0 · lost 5
Qwen3.5 27Bwon 0 · lost 5
Qwen3 VL 235B A22B Instructwon 0 · lost 5
Mistral Large 3won 0 · lost 5
Qwen3.5 122B A10Bwon 0 · lost 5
Gemini 3.1 Flash-Litewon 0 · lost 5
Gemma 4 26B A4Bwon 0 · lost 5
GLM-4.7won 0 · lost 5
Qwen3.5 397B A17Bwon 0 · lost 5
GPT-5.4 miniwon 0 · lost 5
Claude Opus 4.1won 0 · lost 5
Hy3won 0 · lost 5
GLM-5won 0 · lost 5
Gemini 3 Flashwon 0 · lost 5
Claude Opus 4.5 (High, 32K, 20251101)won 0 · lost 5
GPT-6 Astrawon 0 · lost 5
Gemini 3.1 Prowon 0 · lost 5
Gemini 4 Argonwon 0 · lost 5
Qwen 2.5 Instruct (7B)won 0 · lost 6
Qwen2 72B Instructwon 0 · lost 6
Llama 3 70B Instructwon 0 · lost 6
Mistral Largewon 0 · lost 6
Qwen3 Next 80B A3B Thinkingwon 0 · lost 6
GLM-4.5 Airwon 0 · lost 6
GPT-4.5won 0 · lost 6
Gemma 2 9B ITwon 0 · lost 7
Gemma 2 27B ITwon 0 · lost 7
Llama 3.3 70B Instructwon 0 · lost 7
Llama 3.1 405B Instruct (BF16)won 0 · lost 7
O1 Miniwon 0 · lost 7
Claude 3.5 Sonnetwon 0 · lost 7
GLM-4.5won 0 · lost 7
MiniMax M2.7won 0 · lost 7
DeepSeek V3.1won 0 · lost 7
DeepSeek V3.2won 0 · lost 7
GLM-4.6won 0 · lost 7
NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4)won 0 · lost 7
Mistral Large 4won 0 · lost 7
GPT-5.2won 0 · lost 7
DeepSeek V4 Flashwon 0 · lost 7
Inklingwon 0 · lost 7
MiniMax M3won 0 · lost 7
GPT-6 Lunawon 0 · lost 7
Grok 4.7won 0 · lost 7
Grok 4.3won 0 · lost 7
MiMo V2.6 Flashwon 0 · lost 7
Kimi K2.5won 0 · lost 7
Gemma 4 31Bwon 0 · lost 7
GPT-5.6 Lunawon 0 · lost 7
Grok 4.6won 0 · lost 7
GPT-6 Solwon 0 · lost 7
Kimi K2.6won 0 · lost 7
Claude Sonnet 5won 0 · lost 7
DeepSeek-V4-Pro (High, 20260813)won 0 · lost 7
GLM-5.1won 0 · lost 7
Grok 4.5won 0 · lost 7
MiMo V2.5 Prowon 0 · lost 7
GPT-5.6 Terrawon 0 · lost 7
Claude Sonnet 4.6won 0 · lost 7
Qwen3.7 Maxwon 0 · lost 7
GLM-5.3 Flashwon 0 · lost 7
GPT-5.4won 0 · lost 7
GLM-5.2won 0 · lost 7
Gemini 3.5 Flashwon 0 · lost 7
MiMo V2.6 Prowon 0 · lost 7
Claude Opus 4.8won 0 · lost 7
GPT-5.5won 0 · lost 7
Qwen3.8 Maxwon 0 · lost 7
Gemini 3.6 Flashwon 0 · lost 7
GPT-5.6 Solwon 0 · lost 7
Muse Spark 1.1won 0 · lost 7
Claude Opus 5won 0 · lost 7
Gemini 3.8 Flashwon 0 · lost 7
Claude Opus 4.7won 0 · lost 7
Claude Opus 4.6won 0 · lost 7
Claude Opus 5.5won 0 · lost 7
Qwen2.5 72B Instructwon 0 · lost 8
GPT-4 Turbowon 0 · lost 8
GPT-4owon 0 · lost 8
Gemini 2.0 Flashwon 0 · lost 8
O3 Miniwon 0 · lost 8
Grok 3 Miniwon 0 · lost 8
Gemini 2.5 Flash-Litewon 0 · lost 8
GPT-4.1 miniwon 0 · lost 8
Claude 3.7 Sonnetwon 0 · lost 8
GPT-5 miniwon 0 · lost 8
O4 Miniwon 0 · lost 8
DeepSeek V3won 0 · lost 8
O1won 0 · lost 8
Claude Sonnet 4won 0 · lost 8
Gemini 2.5 Flashwon 0 · lost 8
Grok 3won 0 · lost 8
GPT-4.1won 0 · lost 8
Kimi K2won 0 · lost 8
Qwen3 235B A22B Instructwon 0 · lost 8
Claude Opus 4won 0 · lost 8
O3won 0 · lost 8
GPT-5won 0 · lost 8
Gemini 2.5 Prowon 0 · lost 8
GPT-5.1won 0 · lost 8
Claude Sonnet 4.5 (High, 32K, 20250929)won 0 · lost 8
Gemini 3 Prowon 0 · lost 8

§ 3 · Sources

Where the numbers come from

3 publications, 7 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-10-21
LMArena Text 1251
Vals.ai ↗1 measureread 2026-10-21
Vals · LegalBench 32.97%
HELM Safety ↗5 measuresread 2026-10-21
HELM Safety · HarmBench 50.4%HELM Safety · SimpleSafetyTests 94.3%HELM Safety · Anthropic Red Team 93.7%HELM Safety · BBQ 72.4%HELM Safety · XSTest 93.9%

Badge

PublicAI Index badge for Command R (08-2024)[![PublicAI Index](https://publicai.io/model-index/badge?model=command-r-08-2024-2)](https://publicai.io/model-index/m/command-r-08-2024-2)