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 | 5.1B/8B/26B/31B |
| 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. | — | $0.04Darkbloom |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $0.10Modal |
| — | $15.50Darkbloom | |
| 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. | 57.5% | 80% |
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% | 84.3% |
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | — | 25% |
Humanity's Last Exam · no toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | — | 19.5% |
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. | — | 26.5% |
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% | — |
AIME 2026Reasoning — single-answer accuracy on the 2026 invitational mathematics exam without tools | — | 89.2% |
MMMLUKnowledge — average accuracy on multilingual translations of MMLU | — | 88.4% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 85.2% |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 76.9% |
MRCR v2 (8-needle) · 128k averageLong context — Tests whether the AI can find specific details buried inside a very long document (around 128k tokens — roughly a long book). Higher is better. | — | 66.4% |
| Overview | ||
| Company | DeepSeek | |
| Release date | Jan 20 2025 | Apr 2 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek R1 DistillvsClaude Fable 5.2Gemma 4vsClaude Fable 5.2DeepSeek R1 DistillvsGPT-6.2 AstraGemma 4vsGPT-6.2 AstraDeepSeek R1 DistillvsMuse EmberGemma 4vsMuse EmberDeepSeek R1 DistillvsGrok 4.7Gemma 4vsGrok 4.7DeepSeek R1 DistillvsMistral Large 4Gemma 4vsMistral Large 4DeepSeek R1 DistillvsKimi K3.1 ProGemma 4vsKimi K3.1 ProFrequently asked questions
Gemma 4 leads DeepSeek R1 Distill on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). DeepSeek R1 Distill shipped 437 days before Gemma 4, so benchmark comparisons should account for the intervening progress.
DeepSeek R1 Distill has 1.5B/7B/8B/14B/32B/70B parameters, while Gemma 4 has 5.1B/8B/26B/31B.
On LiveCodeBench, Gemma 4 leads at 80% vs DeepSeek R1 Distill at 57.5%. On GPQA Diamond, Gemma 4 leads at 84.3% vs DeepSeek R1 Distill at 65.2%.