whatmodel.sh / Command R Plus (04-2024)

Command R Plus (04-2024)

+ contribute

Command R Plus (04-2024) is an open-weights language model from Cohere, released April 2024. Its published size is 104B parameters and a 128k-token context window. Licence: cc-by-nc-4.0.

Catalogue identity notes

Arena entry 'command-r-plus' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'command-r-plus' as 'Command R+ (04-2024)' (Cohere, CC-BY-NC-4.0), linking https://txt.cohere.com/command-r-plus-microsoft-azure/. Maker repo CohereLabs/c4ai-command-r-plus @3de12c8: licence tag cc-by-nc-4.0. 103,810,674,688 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-04: month the maker's Hugging Face repo was created (createdAt 2024-04-03). Arena key 'command-r-plus'; LMArena's table labels it 'Command R+ (04-2024)'. The ollama 104b-q4_0/q8_0 tags are the original build (separate digests from the 104b-08-2024 tags). Cohere deprecations: effective September 15, 2025 'command-r-plus-04-2024 (and the alias command-r-plus)' deprecated.

44.6±0.5#448 of 719 LLMsfrom 20 benchmark results across 12 sources

$ how it compares

The LLMs ranked either side of Command R Plus (04-2024), out of 828 with a score, then more from Cohere.

#	model	score	where	RAM	released
535	Mistral Small (2402) Mistral	45±1	comparison only		2024-02
536	Llama 3.1 8B Instruct Meta	45±0	api $0.22/M +local	~6.2GB	2024-07
537	Command R Plus (04-2024) Cohere	45±1	local	~43GB	2024-04
538	Mistral NeMo Instruct (2407) Mistral	44±1	local	~8.7GB	2024-07
539	LLaVA-OneVision Qwen2 72B (ov-sft) LLaVA (lmms-lab)	44±3	local	~155GB	2024-08
	more from Cohere
76	North Small Translate 1.0 Cohere	71±6	api price unknown		2026-08
175	Command A+ (05-2026) Cohere	64±1	api price unknown +local	~71GB	2026-05
277	Command A (03-2025) Cohere	57±1	api $4.38/M +local	~37GB	2025-03

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #261 of 300 * · 0.5% of its score · 1 test

Beats DeepSeek R1 0528 Qwen3 8B, Magistral Small 1.0 (2506), Llama 4 Scout (109B-A17B) here, though they rank higher overall. Trails Granite 4.0 H 1B, Granite 4.0 1B, Qwen2.5 3B Instruct here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
BFCL v3	48.0% ✎	▁▁▁▁▁▃▅█▅▄▁▁ beats 31/114	medium · avg 52%	▇ 0.5%	blunt · at its level

coding▁▁▁▃▆██▇▆▄▃▁ #338 of 458 · 48% of its score · 5 tests

Beats GLM-4.7-Flash, LFM2.5 2.6B, LFM2.5 8B-A1B here, though they rank higher overall. Trails Phi-3-mini-128k-instruct (Apr 2024), DeepSeek LLM 67B Chat, WizardLM 70B V1.0 here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
HumanEval	64.0% ✎	▁·▁▁▃▄▆▅█▃▁▁ beats 49/99	easy · avg 79%	▇▇▇▇▇▇▇▇ 21%	sharp · at its level
HumanEval+	56.7% ✎	▁·▁▁▁▃▄▄▄█▃▁ beats 47/99	easy · avg 74%	▇▇▇▇▇▇ 16%	sharp · at its level
Aider code editing (133 Exercism Python exercises, two attempts)	31.6% ✎	▁·▁▃▄▁▆▄█▆▂▂ beats 4/62	medium · avg 54%	▇▇ 4.4%	at its level
HumanEval (Vector Institute, Inspect Evals)	62.2% ✎	▄·▄·█·█·█·▄▄ beats 0/9	easy · avg 79%	▇ 3.5%	at its level
MBPP+	63.5% ✎	▁···▁▁▂▅▇█▆▂ beats 46/75	easy · avg 68%	▇ 2.9%	at its level

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #267 of 393 · 10% of its score · 3 tests

Beats Ministral 3 14B Reasoning 2512, Ministral 3 14B, Phi-4 14B here, though they rank higher overall. Trails Flan-T5 XXL, LFM2 1.2B, Granite 4.0 H 1B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Arena-Hard (v0.1, GPT-4-1106 judge)	33.1% ✎	▂▁▁▅█▅▄▃▃▅▃▁ beats 28/60	medium · avg 52%	▇▇ 5.6%	sharp · at its level
Polyrating rating (bias-aware re-fit of Chatbot Arena votes, mid-2024)	1214.0 ✎	▂▁▂▁▃▇█▆▇▄▂▂ beats 86/95	avg 1201	▇ 2.4%	blunt
LMArena (text)	1261.7 ✎	▁▁▁▂▃▃▃▆▆▇█▃ beats 98/379	avg 1268	▇ 2.4%	blunt

math▁▂▃▅▆▅▄█▄▁▁▁ #350 of 398 * · 9.2% of its score · 2 tests

Trails Qwen3 0.6B, Tulu 2 DPO 7B, Gemma 7B (base) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
MATH (Vector Institute, Inspect Evals)	26.3% ✎	▄··██▄··▄·▄█ beats 0/9	medium · avg 53%	▇▇ 4.6%	sharp · at its level
GSM8K (ZeroEval, zero-shot)	80.1% ✎	▁▄·▁▄█▅▅▅███ beats 11/43	very easy · avg 89%	▇▇ 4.6%	sharp

other tests9 not in a task · 32% of its score

test	result	vs the others in its run	difficulty	counts	why
MMLU-Redux (ZeroEval, 2,778 questions)	68.6% ✎	▁·▁▁▄▄▄▅█▄▂▁ beats 14/53	easy · avg 77%	▇▇▇▇▇ 12%	at its level
LiveBench 2024-07-26	32.2% ✎	▁▁▁▂▂▃▂█▆▃▅▃ beats 32/61	medium · avg 41%	▇▇▇▇ 8.9%	at its level
WildBench v2 WB-Score (task macro)	36.7624 WB-Score ✎	▁·▁▁·▃█▄▇▆▅▆ beats 22/52	avg 45.199 WB-Score	▇ 2.7%	sharp
MMLU-Pro (Vector Institute, Inspect Evals)	44.1% ✎	▃····▃▅·▃▅·█ beats 0/9	medium · avg 60%	▇ 2.3%	at its level
ZebraLogic (ZeroEval, 1,000 puzzles)	13.9% ✎	▁▁▃▆██▁▁·▁▁▁ beats 19/57	hard · avg 18%	▇ 2.0%	sharp
GPQA Diamond (Vector Institute, Inspect Evals)	31.9% ✎	▃··▃▃▃▃·▃·▃█ beats 0/9	hard · avg 41%	▇ 1.8%	sharp
Open Persian LLM Leaderboard v2 average (21 tasks)	60.2% ✎	▂▄▂▃█▄▃▆▃▅▂▂ beats 51/81	medium · avg 58%	▇ 1.0%	blunt · at its level
RULER 64k	84.3% ✎	▁▁·▁·▂▃▄█▂·▁ beats 12/22	easy · avg 83%	▇ 0.6%	typical

1 more test

test	result	vs the others in its run	difficulty	counts	why
RULER 128k	63.1% ✎	▄··▂▄▂▆██▄▄▂ beats 6/21	easy · avg 68%	▇ 0.2%	at its level · noisy

$ where to run it

llama.cpp · recommended

version

Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
macOS / Linux
curl -LsSf https://llama.app/install.sh | sh
Windows
irm https://llama.app/install.ps1 | iex
other ways to install ↗
Run Command R Plus (04-2024) · needs ~62.8 GB · from huggingface.co/bartowski
chat in the terminal
llama cli -hf bartowski/c4ai-command-r-plus-GGUF:Q4_K_M
Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf bartowski/c4ai-command-r-plus-GGUF:Q4_K_M

LM Studio

version

Install LM Studio · Open the app once before using the lms command.
download it (macOS / Windows / Linux) ↗
Run Command R Plus (04-2024) · needs ~62.8 GB · from huggingface.co/bartowski
open in LM Studio ↗
Or download it in the terminal
lms get https://huggingface.co/bartowski/c4ai-command-r-plus-GGUF@Q4_K_M -y
Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

Install Ollama
download it (macOS / Windows) ↗
Linux
curl -fsSL https://ollama.com/install.sh | sh
Run Command R Plus (04-2024) · needs ~62.9 GB · from ollama.com
chat in the terminal
ollama run command-r-plus:104b-q4_0

MLX (Mac)

version

Install MLX (Mac) · Apple silicon Macs only, text only.
with uv
uv tool install mlx-lm
or
pip install mlx-lm
Run Command R Plus (04-2024) · needs ~62.9 GB, Mac only · from huggingface.co/mlx-community
chat in the terminal
mlx_lm.chat --model mlx-community/c4ai-command-r-plus-4bit
Or start an OpenAI-compatible server at http://localhost:8080/v1
mlx_lm.server --model mlx-community/c4ai-command-r-plus-4bit

Weights and documentation: huggingface.co/CohereLabs ↗

$ how the score was worked out · EvalPlus / EvalPerf published… 40%, WildEval ZeroEval published r… 19%, Vector Institute Evaluation L… 12% and 9 more

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

source	results	share of the score	licence
EvalPlus / EvalPerf published evaluation runs	3	▇▇▇▇▇▇▇▇▇▇▇▇ 40%	Apache-2.0
WildEval ZeroEval published results	3	▇▇▇▇▇▇ 19%	Apache-2.0
Vector Institute Evaluation Leaderboard (Inspect Evals runs)	4	▇▇▇▇ 12%	Apache-2.0
LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasets	1	▇▇▇ 9%	Apache-2.0 (stated in the LiveBench datasheet)
Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)	1	▇▇ 6%	Apache-2.0
Aider code editing benchmark runs (old edit leaderboard)	1	▇ 4%	Apache-2.0
WildBench v2 leaderboard data (Ai2)	1	▇ 3%	Apache-2.0
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)	1	▇ 2%	CC-BY-4.0
LMArena leaderboard dataset	1	▇ 2%	CC BY 4.0
Open Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)	1	▇ 1%	Apache-2.0
NVIDIA RULER repository README results table	2	▇ 1%	Apache-2.0
Berkeley Function Calling Leaderboard result archive	1	▇ 1%	Apache-2.0
prior · pull toward the middle		▇ 0%
weighted average		= 44.6

$ improve this page

Update model information Add a place to run it Add a test result Propose a benchmark Correct a benchmark score Edit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated 2026-10-11 02:20 UTC · sources and licences · json