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. | 1.5B/7B/8B/14B/32B/70B | 24B |
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 |
| 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. | — | $0.04DeepInfra |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $0.064DeepInfra |
| — | $14.00DeepInfra · fp8 | |
| These models have no shared benchmark scores. | ||
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. | 57.5% | — |
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | — | 84.8% |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 82.9% |
MATHReasoning — accuracy on the original competition mathematics test set | — | 70.6% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 94.5% | — |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 70% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 65.2% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 66.3% |
| Overview | ||
| Company | DeepSeek | Mistral |
| Release date | Jan 20 2025 | Jan 30 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek R1 DistillvsClaude Fable 5.2Mistral Small 3vsClaude Fable 5.2DeepSeek R1 DistillvsGPT-6.2 AstraMistral Small 3vsGPT-6.2 AstraDeepSeek R1 DistillvsGemini 4 HydrogenMistral Small 3vsGemini 4 HydrogenDeepSeek R1 DistillvsMuse EmberMistral Small 3vsMuse EmberDeepSeek R1 DistillvsGrok 4.7Mistral Small 3vsGrok 4.7DeepSeek R1 DistillvsKimi K3.1 ProMistral Small 3vsKimi K3.1 ProFrequently asked questions
DeepSeek R1 Distill and Mistral Small 3 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek R1 Distill shipped 10 days before Mistral Small 3, so benchmark comparisons should account for the intervening progress.
DeepSeek R1 Distill has 1.5B/7B/8B/14B/32B/70B parameters, while Mistral Small 3 has 24B.
Direct benchmark comparisons are unavailable — DeepSeek R1 Distill and Mistral Small 3 don't publish scores on any of the same benchmarks.