Codestral vs Command R vs Llama-3.2-11B-Vision-Instruct
Llama-3.2-11B-Vision-Instruct comes out ahead, 58 to 51 and 48 on our weighted score.
Mistral AICodestral
48/100- ECI—
- Price$0.30 / $0.90
- Context256K
CohereCommand R
51/100- ECI—
- Price$0.15 / $0.60
- Context128K
- Our pick
MetaLlama-3.2-11B-Vision-Instruct
58/100- ECI—
- Price$0.197 / $0.51
- Context128K
Llama-3.2-11B-Vision-Instruct is our pick
Llama-3.2-11B-Vision-Instruct is the better all-round choice, scoring 58/100 against Command R (51) and Codestral (48). It leads on inputs & features. Codestral wins on context window. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceCommand RCommand R $0.263 · Llama-3.2-11B-Vision-Instruct $0.275 · Codestral $0.45 per 1M tokens (3:1 blend)
- Longest contextCodestralCodestral 256,000 · Command R 128,000 · Llama-3.2-11B-Vision-Instruct 128,000 tokens
- Widest inputsLlama-3.2-11B-Vision-InstructCodestral: Text · Command R: Text · Llama-3.2-11B-Vision-Instruct: Text, Images
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Codestral | Command R | Llama-3.2-11B-Vision-Instruct |
|---|---|---|---|---|
| Price | 50% | 66 | 77 | 76 |
| Inputs & features | 30% | 25 | 25 | 50 |
| Context window | 20% | 36 | 24 | 24 |
| Overall | 100% | 48/100 | 51/100 | 58/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | CodestralMistral AI | Command RCohere | Llama-3.2-11B-Vision-InstructMeta |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.30 | $0.15 (best) | $0.197 |
| Output | $0.90 | $0.60 | $0.51 (best) |
| Cached input | $0.03 | — | — |
| Blended (3:1) | $0.45 | $0.263 (best) | $0.275 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Mistral API | Official Cohere API | Median of 2 providers |
| Limits | |||
| Context window | 256,000 tokens (best) | 128,000 tokens | 128,000 tokens |
| Max output | 4,096 tokens (best) | 4,000 tokens | 4,096 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Open | Open |
| API model ID | codestral-latest | command-r-08-2024 | — |
| API providers | 3 | 5 (best) | 2 |
| Released | May 29, 2024 | Aug 30, 2024 | Sep 25, 2024 |
| Knowledge cutoff | Oct 2024 | Jun 1, 2024 | Dec 2023 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Codestral$4.80
- Command R$2.70
- Llama-3.2-11B-Vision-Instruct$2.99
Which should you choose?
Which is better: Codestral, Command R or Llama-3.2-11B-Vision-Instruct?
Llama-3.2-11B-Vision-Instruct is the better all-round choice, scoring 58/100 against Command R (51) and Codestral (48). It leads on inputs & features. Codestral wins on context window. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Codestral, Command R or Llama-3.2-11B-Vision-Instruct?
Command R is cheaper at $0.15 input / $0.60 output per million tokens (official Cohere API price). Llama-3.2-11B-Vision-Instruct costs $0.197 input / $0.51 output per million tokens (median across 2 API providers); Codestral costs $0.30 input / $0.90 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.263 per million tokens for Command R versus $0.275 for Llama-3.2-11B-Vision-Instruct (1× as much) and $0.45 for Codestral (1.7× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Codestral has not been scored yet, Command R has not been scored yet and Llama-3.2-11B-Vision-Instruct has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Codestral, Command R and Llama-3.2-11B-Vision-Instruct yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Codestral has the largest context window at 256,000 tokens, against 128,000 for Command R and 128,000 for Llama-3.2-11B-Vision-Instruct. Maximum output per response: Codestral up to 4,096, Command R up to 4,000, Llama-3.2-11B-Vision-Instruct up to 4,096 tokens.
Which can read images, PDFs, audio or video?
Codestral accepts text; Command R accepts text; Llama-3.2-11B-Vision-Instruct accepts text and images. Llama-3.2-11B-Vision-Instruct handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights, so you can self-host them.
Which is newer?
Llama-3.2-11B-Vision-Instruct is the newest, released Sep 25, 2024. Command R came out Aug 30, 2024; Codestral came out May 29, 2024. Knowledge cutoff: Codestral Oct 2024, Command R Jun 1, 2024, Llama-3.2-11B-Vision-Instruct Dec 2023.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.
