Leaderboard · Model · Updated
Command R+
Cohere's RAG-tuned 104B model — strong multilingual and tool use.
At a glance
| Provider | Cohere |
|---|---|
| Released | 2024-08 |
| Tier | general-purpose |
| License | Open-weights (CC-BY-NC-4.0) |
| Modalities | text |
| Context window | 128k tokens |
| Max output | 4.096k tokens |
| API price · input | $2.50 / 1M tokens |
| API price · output | $10.00 / 1M tokens |
| Hugging Face | CohereForAI/c4ai-command-r-plus-08-2024 |
Benchmark performance
How Command R+ stacks up against the current leader (GPT-5) and the median model in the leaderboard:
| Benchmark | Command R+ | GPT-5 | Median |
|---|---|---|---|
| Chatbot Arena Elo | 1216 | 1410 | 1320 |
| MMLU-Pro | 53.0 | 86.8 | 78.0 |
| GPQA Diamond | 42.5 | 87.3 | 65.0 |
| MATH | 30.7 | 96.7 | 78.3 |
| HumanEval | 70.7 | 95.1 | 92.0 |
| SWE-Bench Verified | N/A | 74.9 | 49.0 |
Numbers compiled from provider technical reports and Chatbot Arena. See methodology for the composite-score formula.
OpenRouter routes your requests across Command R+, GPT-5, Claude, Gemini, and 100+ other models behind a single API key — pay-as-you-go, no monthly minimum. Try OpenRouter → (affiliate · supports this site)
What does Command R+ cost in practice?
API pricing is $2.50 per 1M input tokens and $10.00 per 1M output tokens. Assuming a 50/50 input/output split, here is what that looks like at three workload sizes:
| Volume | Per day | Per month | Per year |
|---|---|---|---|
| 1M tokens/day | $6.25 | $187.50 | $2,281 |
| 10M tokens/day | $62.50 | $1,875 | $22,813 |
| 100M tokens/day | $625.00 | $18,750 | $228,125 |
Strengths & weaknesses
Where it shines
No clear top-tier strengths — this is a mid-pack model.
Where it lags
- Arena: 1216 (rank #27 of 27, below average)
- MMLU-Pro: 53.0 (rank #29 of 29, below average)
- MATH: 30.7 (rank #29 of 29, below average)
Best alternatives
The closest models to Command R+ by tier and benchmark score:
| Model | Score | $ in / out | Context | Action |
|---|---|---|---|---|
| Mistral Large 2 Mistral AI |
63.7 | $2.00 / $6.00 | 128k | Try → · vs Command |
| GPT-4o OpenAI |
66.8 | $2.50 / $10.00 | 128k | Try → · vs Command |
| Gemini 1.5 Pro |
67.9 | $1.25 / $5.00 | 2M | Try → · vs Command |
| Claude 3.5 Sonnet Anthropic |
69.1 | $3.00 / $15.00 | 200k | Try → · vs Command |
| GPT-4.1 OpenAI |
74.5 | $2.00 / $8.00 | 1M | Try → · vs Command |
Frequently asked questions
Is Command R+ a good model?
Command R+ scores 47.0 on the llmrank.top composite (rank #29 of 30). It trails the frontier — for top performance, look at GPT-5 (86.0). Whether it's the right fit depends on your workload — see the use-case discussion on this page.
How much does Command R+ cost?
Command R+ is priced at $2.50 per 1M input tokens and $10.00 per 1M output tokens (USD). For a 10M-token-per-day workload split 50/50, that works out to roughly $62.50/day or $22,813/year.
What is Command R+'s context window?
128k tokens. For very long inputs, consider a 1M+ context model like Gemini 2.5 Pro or GPT-4.1.
Is Command R+ open source?
Yes — released under the CC-BY-NC-4.0 license, weights are downloadable from the provider or Hugging Face.
What is Command R+'s SWE-Bench score?
Command R+ scores not reported on SWE-Bench Verified — the benchmark that measures real-world GitHub issue resolution. Its Chatbot Arena Elo is 1216.
What are the best alternatives to Command R+?
Closest alternatives by tier and score: Mistral Large 2, GPT-4o, Gemini 1.5 Pro. See the alternatives section on this page for side-by-side numbers.
Related: Mistral Large 2 · GPT-4o · Gemini 1.5 Pro · Full leaderboard
Spotted out-of-date numbers? Open an issue — corrections usually ship within 24h.
Try Command R+ now
Direct link to the official playground — or use OpenRouter to A/B test it against any other model on a single API key.