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. | 24B | 397B |
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. | 40k | 1M |
| API pricingUSD per 1M tokens · lower wins · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $0.40 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | — | $1.60 |
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. | — | $0.32Alibaba |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $1.28Alibaba |
| — | $128Alibaba | |
| Benchmarks | ||
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. | 59.17% | 89.6% |
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. | — | 77.7% |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | — | 34.7% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 70.52% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 62.03% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 65.78% | — |
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | — | 73.3% |
| Overview | ||
| Company | Mistral | Qwen |
| Release date | Jul 24 2025 | Jun 1 2026 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Magistral Small 1.1vsClaude Fable 5.2Qwen3.7-PlusvsClaude Fable 5.2Magistral Small 1.1vsGPT-6.2 AstraQwen3.7-PlusvsGPT-6.2 AstraMagistral Small 1.1vsGemini 4 HydrogenQwen3.7-PlusvsGemini 4 HydrogenMagistral Small 1.1vsMuse EmberQwen3.7-PlusvsMuse EmberMagistral Small 1.1vsGrok 4.7Qwen3.7-PlusvsGrok 4.7Magistral Small 1.1vsDeepSeek-V4.1-Flash-1017Qwen3.7-PlusvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Qwen3.7-Plus leads Magistral Small 1.1 on 1 of the 1 benchmark they both report (LiveCodeBench). Only Qwen3.7-Plus has a verified first-party price for an available API: $0.40 per million input tokens and $1.60 per million output tokens. No currently available pay-as-you-go API rate is tracked for Magistral Small 1.1. Magistral Small 1.1 shipped 312 days before Qwen3.7-Plus, so benchmark comparisons should account for the intervening progress.
Magistral Small 1.1 has 24B parameters, while Qwen3.7-Plus has 397B. Context windows are 40k (Magistral Small 1.1) vs 1M (Qwen3.7-Plus). Magistral Small 1.1 is open weight, while Qwen3.7-Plus is closed.
On LiveCodeBench, Qwen3.7-Plus leads at 89.6% vs Magistral Small 1.1 at 59.17%.