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. | — | 671B |
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. | 100k | 128k |
| 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. | — | $0.27SiliconFlow |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $1.00SiliconFlow |
| — | $104SiliconFlow · fp8 | |
| 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. | — | 68.4% |
SWE-Bench MultilingualMultilingual coding — Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | — | 57.8% |
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. | — | 74.9% |
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. | 58.7% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 80.7% |
GSM8KGrade-school math — Grade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. | 86.7% | — |
| Overview | ||
| Company | Anthropic | DeepSeek |
| Release date | Aug 9 2023 | Sep 22 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Claude Instant 1.2vsGPT-6.1 SolDeepSeek V3.1 TerminusvsGPT-6.1 SolClaude Instant 1.2vsGemini 4 ArgonDeepSeek V3.1 TerminusvsGemini 4 ArgonClaude Instant 1.2vsMuse Spark OpenDeepSeek V3.1 TerminusvsMuse Spark OpenClaude Instant 1.2vsGrok 4.7DeepSeek V3.1 TerminusvsGrok 4.7Claude Instant 1.2vsMistral Large 4DeepSeek V3.1 TerminusvsMistral Large 4Claude Instant 1.2vsKimi K3DeepSeek V3.1 TerminusvsKimi K3Frequently asked questions
Claude Instant 1.2 and DeepSeek V3.1 Terminus don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Claude Instant 1.2 shipped 775 days before DeepSeek V3.1 Terminus, so benchmark comparisons should account for the intervening progress.
Context windows are 100k (Claude Instant 1.2) vs 128k (DeepSeek V3.1 Terminus). Claude Instant 1.2 is closed, while DeepSeek V3.1 Terminus is open weight.
Direct benchmark comparisons are unavailable — Claude Instant 1.2 and DeepSeek V3.1 Terminus don't publish scores on any of the same benchmarks.