Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | 22B | 120B |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 32k | 1M |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | — | $0.10Crusoe |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $0.40Crusoe |
| — | $40.00Crusoe · bf16 | |
| These models have no shared benchmark scores. | ||
SWE-Bench ProAgentic coding — Can the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | — | 51.78% |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | — | 71.1% |
SWE-Bench MultilingualMultilingual coding — Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | — | 67.72% |
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | — | 88.22% |
Terminal-Bench 2.1Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | — | 66.7% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 78% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 89.52% |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 70.86% |
| Overview | ||
| Company | Mistral | NVIDIA |
| Release date | May 29 2024 | Oct 15 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Codestral 22BvsClaude Haiku 5.5Nemotron 3.5 Super VLvsClaude Haiku 5.5Codestral 22BvsGPT-6.1 SolNemotron 3.5 Super VLvsGPT-6.1 SolCodestral 22BvsGemini 4 ArgonNemotron 3.5 Super VLvsGemini 4 ArgonCodestral 22BvsMuse Spark OpenNemotron 3.5 Super VLvsMuse Spark OpenCodestral 22BvsGrok 4.7Nemotron 3.5 Super VLvsGrok 4.7Codestral 22BvsDeepSeek-V4.1-Flash-1017Nemotron 3.5 Super VLvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Codestral 22B and Nemotron 3.5 Super VL don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Codestral 22B shipped 869 days before Nemotron 3.5 Super VL, so benchmark comparisons should account for the intervening progress.
Codestral 22B has 22B parameters, while Nemotron 3.5 Super VL has 120B. Context windows are 32k (Codestral 22B) vs 1M (Nemotron 3.5 Super VL). Codestral 22B is closed, while Nemotron 3.5 Super VL is open weight.
Direct benchmark comparisons are unavailable — Codestral 22B and Nemotron 3.5 Super VL don't publish scores on any of the same benchmarks.