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. | 12B | >1T |
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. | 128k | 256k |
| 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. | $0.0166Io Net | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.0216Io Net | — |
| $4.40Io Net · fp16 | — | |
| These models have no shared benchmark scores. | ||
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. | — | 75.3% |
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. | — | 85.9% |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | — | 30.2% |
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. | — | 49.8% |
HellaSwagReasoning — commonsense completion of short scenarios | 83.5% | — |
WinoGrandeReasoning — resolving ambiguous pronouns in context | 76.8% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 87.4% |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 70.9% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 85.7% |
MMLUGeneral knowledge — A 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. | 68% | — |
| Overview | ||
| Company | Mistral | Qwen |
| Release date | Jul 18 2024 | Jan 26 2026 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Mistral NeMovsClaude Fable 5.2Qwen3-Max-ThinkingvsClaude Fable 5.2Mistral NeMovsGPT-6.2 AstraQwen3-Max-ThinkingvsGPT-6.2 AstraMistral NeMovsGemini 4 NeonQwen3-Max-ThinkingvsGemini 4 NeonMistral NeMovsMuse EmberQwen3-Max-ThinkingvsMuse EmberMistral NeMovsGrok 4.7Qwen3-Max-ThinkingvsGrok 4.7Mistral NeMovsDeepSeek-V4.1-Flash-1017Qwen3-Max-ThinkingvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Mistral NeMo and Qwen3-Max-Thinking don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Mistral NeMo shipped 557 days before Qwen3-Max-Thinking, so benchmark comparisons should account for the intervening progress.
Mistral NeMo has 12B parameters, while Qwen3-Max-Thinking has >1T. Context windows are 128k (Mistral NeMo) vs 256k (Qwen3-Max-Thinking). Mistral NeMo is open weight, while Qwen3-Max-Thinking is closed.
Direct benchmark comparisons are unavailable — Mistral NeMo and Qwen3-Max-Thinking don't publish scores on any of the same benchmarks.