The LLM benchmark aggregator.

Command R+ (08-2024)

Cohere

Strongest in Factual grounding (#30 of 102), weakest in Safety (#270 of 331). Above par in 2 of 18 scopes. Among the models it meets almost everywhere, it finishes behind O3 and O1 and ahead of Jamba 1.6 Mini and Jamba 1.5 Mini.

§ 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.

Professional42.1−21#169/1881/2

Legal42.4−23.5#136/1641/1

Medical32.9−33.6#144/1491/1

Knowledge40−22.7#178/1911/3

Academic knowledge26−37.9#122/1231/1

Reasoning35.2−29.7#183/1902/5

Science26.1−37.4#119/1221/1

Reasoning35.2−31.5#137/1441/3

Human preference44.8−23.8#247/3501/1

Safety46−15.4#270/3313/3

Factual grounding57.8−13#30/1021/1

Safe-prompt compliance49.3−11.1#60/821/1

Jailbreak resistance57.2−7.8#78/2711/1

Harm refusal46.6−14.9#210/2962/2

Toxicity avoidance44.2−14.8#233/2711/1

Fairness42.5−27.5#251/2962/2

Secure code26−40.3#264/2731/1

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

GPT-3.5 Turbowon 8 · lost 3

Mixtral 8x7B Instructwon 8 · lost 4

Jamba 1.5 Miniwon 7 · lost 4

Jamba 1.6 Miniwon 8 · lost 5

Llama 3.1 8B Instructwon 4 · lost 7

Mixtral 8x22B Instructwon 4 · lost 7

Llama 3.1 70B Instructwon 4 · lost 7

Jamba 1.6 Largewon 4 · lost 9

DeepSeek R1won 5 · lost 12

Grok 4.1 Fastwon 5 · lost 12

GPT OSS 120Bwon 5 · lost 13

Jamba 1.5 Largewon 3 · lost 8

Gemini 1.5 Flashwon 4 · lost 11

Gemma 4 31Bwon 4 · lost 11

MiMo V2.6 Flashwon 3 · lost 9

GPT OSS 20Bwon 4 · lost 12

Command A (03-2025)won 4 · lost 12

Mistral Smallwon 3 · lost 10

Llama 4 Scout Instructwon 4 · lost 14

Grok 3won 4 · lost 14

GLM-4.6won 3 · lost 13

DeepSeek V4 Flashwon 3 · lost 13

Kimi K2.6won 3 · lost 13

Gemini 3.6 Flashwon 3 · lost 13

NVIDIA Nemotron 3 Super 120B A12Bwon 2 · lost 9

GPT-4.1 nanowon 3 · lost 14

Gemini 1.5 Prowon 3 · lost 14

Grok 4won 3 · lost 14

Grok 4 Fastwon 2 · lost 10

Llama 4 Maverick Instructwon 3 · lost 15

GPT-4owon 3 · lost 15

DeepSeek V3won 3 · lost 15

Claude Haiku 4.5won 3 · lost 15

Kimi K2won 3 · lost 15

Ling 3.0 Flashwon 2 · lost 11

Mistral Large 4won 2 · lost 11

Mistral Largewon 2 · lost 13

GLM-4.5won 2 · lost 13

MiMo V2.5 Prowon 2 · lost 13

GPT-4o miniwon 2 · lost 14

NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4)won 2 · lost 14

MiniMax M3won 2 · lost 14

Qwen3.7 Maxwon 2 · lost 14

GLM-5.3 Flashwon 2 · lost 14

GLM-5.2won 2 · lost 14

Gemini 3.5 Flashwon 2 · lost 14

DeepSeek V3.2won 2 · lost 15

Kimi K2.5won 2 · lost 15

DeepSeek-V4-Pro (High, 20260813)won 2 · lost 15

GPT-5.5won 2 · lost 15

GPT-5.6 Solwon 2 · lost 15

GPT-5 nanowon 2 · lost 16

Gemini 2.5 Flashwon 2 · lost 16

Qwen3 235B A22B Instructwon 2 · lost 16

Gemini 2.5 Prowon 2 · lost 16

GPT-5.1won 2 · lost 16

Claude 3 Opuswon 1 · lost 10

Qwen3.5 Flashwon 1 · lost 10

Gemini 3.1 Flash-Litewon 1 · lost 10

GPT-5.4 miniwon 1 · lost 10

Qwen2.5 72B Instructwon 1 · lost 11

MiniMax M2.1won 1 · lost 11

MiniMax M2.5won 1 · lost 11

GPT-5.4 nanowon 1 · lost 11

Mistral Large 3won 1 · lost 11

GLM-4.7won 1 · lost 11

Claude Opus 4.1won 1 · lost 11

GLM-5won 1 · lost 11

Gemini 3 Flashwon 1 · lost 11

Claude Opus 4.5 (High, 32K, 20251101)won 1 · lost 11

Gemini 3.1 Prowon 1 · lost 11

O1 Miniwon 1 · lost 12

DeepSeek V3.1won 1 · lost 12

Kimi K2 Thinkingwon 1 · lost 13

Claude 3.5 Haikuwon 1 · lost 13

GPT-6 Lunawon 1 · lost 13

Grok 4.3won 1 · lost 14

GPT-6 Solwon 1 · lost 14

Claude Sonnet 4.6won 1 · lost 14

Gemini 3 Prowon 1 · lost 14

Claude Opus 4.6won 1 · lost 14

Llama 3.3 70B Instructwon 1 · lost 15

MiniMax M2.7won 1 · lost 15

GPT-5.6 Lunawon 1 · lost 15

Grok 4.6won 1 · lost 15

GLM-5.1won 1 · lost 15

Grok 4.5won 1 · lost 15

GPT-5.6 Terrawon 1 · lost 15

Qwen3.8 Maxwon 1 · lost 15

Claude Opus 5won 1 · lost 15

Gemini 3.8 Flashwon 1 · lost 15

Gemini 2.0 Flashwon 1 · lost 16

GPT-4.1 miniwon 1 · lost 16

GPT-5.2won 1 · lost 16

GPT-5.4won 1 · lost 16

Claude Opus 4.7won 1 · lost 16

GPT-5 miniwon 1 · lost 17

O4 Miniwon 1 · lost 17

Claude Sonnet 4won 1 · lost 17

GPT-4.1won 1 · lost 17

Claude Opus 4won 1 · lost 17

GPT-5won 1 · lost 17

Claude Sonnet 4.5 (High, 32K, 20250929)won 1 · lost 17

Llama 3.1 405B Instruct (BF16)won 0 · lost 13

Grok 4.7won 0 · lost 13

MiMo V2.6 Prowon 0 · lost 13

GPT-4 Turbowon 0 · lost 14

Grok 3 Miniwon 0 · lost 14

Gemini 2.5 Flash-Litewon 0 · lost 14

Claude Opus 5.5won 0 · lost 14

Muse Spark 1.1won 0 · lost 15

Claude 3.5 Sonnetwon 0 · lost 16

Inklingwon 0 · lost 16

Claude Sonnet 5won 0 · lost 16

Claude Opus 4.8won 0 · lost 16

O3 Miniwon 0 · lost 17

Claude 3.7 Sonnetwon 0 · lost 17

O1won 0 · lost 17

O3won 0 · lost 17

§ 3 · Sources

Where the numbers come from

6 publications, 18 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-10-21

LMArena Text 1276

SimpleBench ↗1 measureread 2026-10-21

SimpleBench 17.4%

Vals.ai ↗4 measuresread 2026-10-21

Vals · LegalBench 68.29%Vals · MedQA 2.65%Vals · GPQA Diamond 31.06%Vals · MMLU Pro 44%

HELM Safety ↗5 measuresread 2026-10-21

HELM Safety · HarmBench 48.5%HELM Safety · SimpleSafetyTests 100%HELM Safety · Anthropic Red Team 98%HELM Safety · BBQ 89.9%HELM Safety · XSTest 93.8%

Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-10-21

Enkrypt · Jailbreak risk 6.7%Enkrypt · Harmful content risk 60%Enkrypt · CBRN risk 9.2%Enkrypt · Toxicity risk 10.1%Enkrypt · Bias risk 98.7%Enkrypt · Insecure code risk 86.7%

Vectara Hallucination Leaderboard ↗1 measureread 2026-10-21

Vectara · Factual consistency 93.1%

Badge

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