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. | 236B | — |
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 | — |
| 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. | — | $1.25 |
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. | — | $2.50 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | — | $0.20 |
| — | $375SpaceXSI list price | |
| Benchmarks | ||
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. | 16.8% | 76.7% |
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. | — | 56% |
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. | 41.8% | — |
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. | 89% | — |
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | — | 53.3% |
| Overview | ||
| Company | DeepSeek | SpaceXSI |
| Release date | Sep 5 2024 | Feb 17 2026 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek V2.5vsClaude Fable 5.2Grok 4.20 BetavsClaude Fable 5.2DeepSeek V2.5vsGPT-6.2 AstraGrok 4.20 BetavsGPT-6.2 AstraDeepSeek V2.5vsGemini 4 HydrogenGrok 4.20 BetavsGemini 4 HydrogenDeepSeek V2.5vsMuse EmberGrok 4.20 BetavsMuse EmberDeepSeek V2.5vsMistral Large 4Grok 4.20 BetavsMistral Large 4DeepSeek V2.5vsKimi K3.1 ProGrok 4.20 BetavsKimi K3.1 ProFrequently asked questions
Grok 4.20 Beta leads DeepSeek V2.5 on 1 of the 1 benchmark they both report (SWE-Bench Verified). Only Grok 4.20 Beta has a verified first-party price for an available API: $1.25 per million input tokens and $2.50 per million output tokens. No currently available pay-as-you-go API rate is tracked for DeepSeek V2.5. DeepSeek V2.5 shipped 530 days before Grok 4.20 Beta, so benchmark comparisons should account for the intervening progress.
DeepSeek V2.5 is open weight, while Grok 4.20 Beta is closed.
On SWE-Bench Verified, Grok 4.20 Beta leads at 76.7% vs DeepSeek V2.5 at 16.8%.