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. | 16B | — |
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 | 1M |
| These models have no shared benchmark scores. | ||
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. | — | 48% |
SWE-Bench ProAgentic coding — Can the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | — | 43.3% |
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. | — | 76.2% |
Next.js EvalsNext.js coding — Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | — | 50% |
LiveCodeBench ProCompetitive programming — Elo rating on competitive programming problems in LiveCodeBench Pro | — | 2439 |
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. | 57.3% | — |
Terminal-Bench 2.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | — | 54.2% |
APEX-AgentsExpert agentic work — expert-level agentic work tasks (AI Productivity Index) | — | 18.4% |
MCP Atlas · original harnessMulti-step tool use — pass rate under the original tool-use harness, before Scale changed the judge and retry handling in April 2026 | — | 54.1% |
τ²-bench · retailAgentic tasks — task success in the retail domain of the second-generation customer-service evaluation | — | 85.3% |
τ²-bench · telecomAgentic tasks — task success in the telecom domain of the second-generation customer-service evaluation | — | 98% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 59.2% |
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. | — | 37.5% |
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. | — | 45.8% |
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. | — | 31.1% |
MATHReasoning — accuracy on the original competition mathematics test set | 27.9% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 95% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 91.9% |
SimpleQA VerifiedKnowledge — accuracy on the vetted factual questions in SimpleQA Verified | — | 72.1% |
MMMLUKnowledge — average accuracy on multilingual translations of MMLU | — | 91.8% |
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. | 55.7% | — |
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. | 72% | — |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | — | 81.4% |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 81% |
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. | — | 77% |
MRCR v2 (8-needle) · 1M pointwiseLong context — Tests whether the AI can find specific details buried inside an enormous document (around 1 million tokens — many books). Higher is better. | — | 26.3% |
| Overview | ||
| Company | DeepSeek | |
| Release date | May 16 2024 | Nov 18 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek V2 LitevsClaude Fable 5.2Gemini 3.0 ProvsClaude Fable 5.2DeepSeek V2 LitevsGPT-6.2 AstraGemini 3.0 ProvsGPT-6.2 AstraDeepSeek V2 LitevsMuse EmberGemini 3.0 ProvsMuse EmberDeepSeek V2 LitevsGrok 4.7Gemini 3.0 ProvsGrok 4.7DeepSeek V2 LitevsMistral Large 4Gemini 3.0 ProvsMistral Large 4DeepSeek V2 LitevsKimi K3.1 ProGemini 3.0 ProvsKimi K3.1 ProFrequently asked questions
DeepSeek V2 Lite and Gemini 3.0 Pro don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek V2 Lite shipped 551 days before Gemini 3.0 Pro, so benchmark comparisons should account for the intervening progress.
Context windows are 32k (DeepSeek V2 Lite) vs 1M (Gemini 3.0 Pro). DeepSeek V2 Lite is open weight, while Gemini 3.0 Pro is closed.
Direct benchmark comparisons are unavailable — DeepSeek V2 Lite and Gemini 3.0 Pro don't publish scores on any of the same benchmarks.